Initial upload of fine-tuned model
Browse files- .gitattributes +3 -0
- README.md +58 -0
- chat_template.jinja +21 -0
- checkpoint-3670/chat_template.jinja +21 -0
- checkpoint-3670/config.json +132 -0
- checkpoint-3670/configuration_hymba.py +122 -0
- checkpoint-3670/generation_config.json +10 -0
- checkpoint-3670/model.safetensors +3 -0
- checkpoint-3670/modeling_hymba.py +0 -0
- checkpoint-3670/optimizer.pt +3 -0
- checkpoint-3670/rng_state.pth +3 -0
- checkpoint-3670/scheduler.pt +3 -0
- checkpoint-3670/special_tokens_map.json +17 -0
- checkpoint-3670/tokenizer.json +3 -0
- checkpoint-3670/tokenizer_config.json +2063 -0
- checkpoint-3670/trainer_state.json +3346 -0
- checkpoint-3670/training_args.bin +3 -0
- checkpoint-7340/chat_template.jinja +21 -0
- checkpoint-7340/config.json +132 -0
- checkpoint-7340/configuration_hymba.py +122 -0
- checkpoint-7340/generation_config.json +10 -0
- checkpoint-7340/model.safetensors +3 -0
- checkpoint-7340/modeling_hymba.py +0 -0
- checkpoint-7340/optimizer.pt +3 -0
- checkpoint-7340/rng_state.pth +3 -0
- checkpoint-7340/scheduler.pt +3 -0
- checkpoint-7340/special_tokens_map.json +17 -0
- checkpoint-7340/tokenizer.json +3 -0
- checkpoint-7340/tokenizer_config.json +2063 -0
- checkpoint-7340/trainer_state.json +0 -0
- checkpoint-7340/training_args.bin +3 -0
- config.json +132 -0
- configuration_hymba.py +122 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- modeling_hymba.py +0 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-3670/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-7340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Maxtimer97/Llama2Hymba_raw
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: model
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- sft
|
| 8 |
+
- trl
|
| 9 |
+
licence: license
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for model
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [Maxtimer97/Llama2Hymba_raw](https://huggingface.co/Maxtimer97/Llama2Hymba_raw).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
+
|
| 17 |
+
## Quick start
|
| 18 |
+
|
| 19 |
+
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
+
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="None", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Training procedure
|
| 29 |
+
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/maxtimer/huggingface/runs/0tli9m2w)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
This model was trained with SFT.
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- TRL: 0.19.1
|
| 38 |
+
- Transformers: 4.53.0
|
| 39 |
+
- Pytorch: 2.6.0
|
| 40 |
+
- Datasets: 3.6.0
|
| 41 |
+
- Tokenizers: 0.21.1
|
| 42 |
+
|
| 43 |
+
## Citations
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
+
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
+
}
|
| 58 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
{{- bos_token }}
|
| 3 |
+
{%- for message in messages %}
|
| 4 |
+
{%- if message['role'] == 'assistant' %}
|
| 5 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 6 |
+
' }}
|
| 7 |
+
{%- generation %}
|
| 8 |
+
{{- message['content'] + '<|eot_id|>' }}
|
| 9 |
+
{%- endgeneration %}
|
| 10 |
+
{{- '
|
| 11 |
+
' }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 14 |
+
' + message['content'] + '<|eot_id|>' + '
|
| 15 |
+
' }}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- endfor %}
|
| 18 |
+
{%- if add_generation_prompt %}
|
| 19 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>
|
| 20 |
+
' }}
|
| 21 |
+
{%- endif %}
|
checkpoint-3670/chat_template.jinja
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
{{- bos_token }}
|
| 3 |
+
{%- for message in messages %}
|
| 4 |
+
{%- if message['role'] == 'assistant' %}
|
| 5 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 6 |
+
' }}
|
| 7 |
+
{%- generation %}
|
| 8 |
+
{{- message['content'] + '<|eot_id|>' }}
|
| 9 |
+
{%- endgeneration %}
|
| 10 |
+
{{- '
|
| 11 |
+
' }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 14 |
+
' + message['content'] + '<|eot_id|>' + '
|
| 15 |
+
' }}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- endfor %}
|
| 18 |
+
{%- if add_generation_prompt %}
|
| 19 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>
|
| 20 |
+
' }}
|
| 21 |
+
{%- endif %}
|
checkpoint-3670/config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HymbaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"attn_factor": 0.5,
|
| 7 |
+
"attn_hidden_size": -1,
|
| 8 |
+
"attn_implementation": "flash_attention_2",
|
| 9 |
+
"attn_implementation_new": "flash_attention_2",
|
| 10 |
+
"attn_only_wo_proj": true,
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoConfig": "configuration_hymba.HymbaConfig",
|
| 13 |
+
"AutoModelForCausalLM": "modeling_hymba.HymbaForCausalLM"
|
| 14 |
+
},
|
| 15 |
+
"bos_token_id": 128000,
|
| 16 |
+
"calc_logits_for_entire_prompt": false,
|
| 17 |
+
"conv_dim": {
|
| 18 |
+
"0": 3200,
|
| 19 |
+
"1": 3200,
|
| 20 |
+
"10": 3200,
|
| 21 |
+
"11": 3200,
|
| 22 |
+
"12": 3200,
|
| 23 |
+
"13": 3200,
|
| 24 |
+
"14": 3200,
|
| 25 |
+
"15": 3200,
|
| 26 |
+
"16": 3200,
|
| 27 |
+
"17": 3200,
|
| 28 |
+
"18": 3200,
|
| 29 |
+
"19": 3200,
|
| 30 |
+
"2": 3200,
|
| 31 |
+
"20": 3200,
|
| 32 |
+
"21": 3200,
|
| 33 |
+
"22": 3200,
|
| 34 |
+
"23": 3200,
|
| 35 |
+
"24": 3200,
|
| 36 |
+
"25": 3200,
|
| 37 |
+
"26": 3200,
|
| 38 |
+
"27": 3200,
|
| 39 |
+
"28": 3200,
|
| 40 |
+
"29": 3200,
|
| 41 |
+
"3": 3200,
|
| 42 |
+
"30": 3200,
|
| 43 |
+
"31": 3200,
|
| 44 |
+
"4": 3200,
|
| 45 |
+
"5": 3200,
|
| 46 |
+
"6": 3200,
|
| 47 |
+
"7": 3200,
|
| 48 |
+
"8": 3200,
|
| 49 |
+
"9": 3200
|
| 50 |
+
},
|
| 51 |
+
"eos_token_id": [
|
| 52 |
+
128001,
|
| 53 |
+
128008,
|
| 54 |
+
128009
|
| 55 |
+
],
|
| 56 |
+
"global_attn_idx": [
|
| 57 |
+
0,
|
| 58 |
+
8,
|
| 59 |
+
15
|
| 60 |
+
],
|
| 61 |
+
"head_dim": 128,
|
| 62 |
+
"hidden_act": "silu",
|
| 63 |
+
"hidden_size": 2048,
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"intermediate_size": 8192,
|
| 66 |
+
"kq_head_dim": -1,
|
| 67 |
+
"kq_norm": "none",
|
| 68 |
+
"kv_reuse_every_i_layer": -1,
|
| 69 |
+
"kv_reuse_group": null,
|
| 70 |
+
"kv_weight_reuse": false,
|
| 71 |
+
"layer_type": [
|
| 72 |
+
"h",
|
| 73 |
+
"h",
|
| 74 |
+
"h",
|
| 75 |
+
"h",
|
| 76 |
+
"h",
|
| 77 |
+
"h",
|
| 78 |
+
"h",
|
| 79 |
+
"h",
|
| 80 |
+
"h",
|
| 81 |
+
"h",
|
| 82 |
+
"h",
|
| 83 |
+
"h",
|
| 84 |
+
"h",
|
| 85 |
+
"h",
|
| 86 |
+
"h",
|
| 87 |
+
"h"
|
| 88 |
+
],
|
| 89 |
+
"mamba_conv_bias": true,
|
| 90 |
+
"mamba_d_conv": 4,
|
| 91 |
+
"mamba_d_state": 16,
|
| 92 |
+
"mamba_dt_rank": 100,
|
| 93 |
+
"mamba_expand": 1,
|
| 94 |
+
"mamba_inner_layernorms": false,
|
| 95 |
+
"mamba_proj_bias": false,
|
| 96 |
+
"max_position_embeddings": 131072,
|
| 97 |
+
"memory_tokens_interspersed_every": 0,
|
| 98 |
+
"mlp_hidden_act": "silu",
|
| 99 |
+
"model_type": "hymba",
|
| 100 |
+
"num_attention_heads": 16,
|
| 101 |
+
"num_experts": 1,
|
| 102 |
+
"num_experts_per_tok": 1,
|
| 103 |
+
"num_hidden_layers": 16,
|
| 104 |
+
"num_key_value_heads": 4,
|
| 105 |
+
"num_mamba": 1,
|
| 106 |
+
"num_memory_tokens": 0,
|
| 107 |
+
"orig_max_position_embeddings": 2048,
|
| 108 |
+
"output_router_logits": false,
|
| 109 |
+
"pad_token_id": null,
|
| 110 |
+
"pure_attn": true,
|
| 111 |
+
"rms_norm_eps": 1e-05,
|
| 112 |
+
"rope": true,
|
| 113 |
+
"rope_scaling": {
|
| 114 |
+
"factor": 32.0,
|
| 115 |
+
"high_freq_factor": 4.0,
|
| 116 |
+
"low_freq_factor": 1.0,
|
| 117 |
+
"original_max_position_embeddings": 8192,
|
| 118 |
+
"rope_type": "llama3"
|
| 119 |
+
},
|
| 120 |
+
"rope_theta": 500000.0,
|
| 121 |
+
"rope_type": "ntk",
|
| 122 |
+
"router_aux_loss_coef": 0.001,
|
| 123 |
+
"seq_length": 8192,
|
| 124 |
+
"sliding_window": 256,
|
| 125 |
+
"tie_word_embeddings": true,
|
| 126 |
+
"torch_dtype": "bfloat16",
|
| 127 |
+
"transformers_version": "4.53.0",
|
| 128 |
+
"use_cache": false,
|
| 129 |
+
"use_mamba_kernels": true,
|
| 130 |
+
"v_head_dim": 128,
|
| 131 |
+
"vocab_size": 128256
|
| 132 |
+
}
|
checkpoint-3670/configuration_hymba.py
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
class HymbaConfig(PretrainedConfig):
|
| 6 |
+
|
| 7 |
+
model_type = "hymba"
|
| 8 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 9 |
+
|
| 10 |
+
def __init__(
|
| 11 |
+
self,
|
| 12 |
+
vocab_size=65536,
|
| 13 |
+
tie_word_embeddings=False,
|
| 14 |
+
hidden_size=4096,
|
| 15 |
+
intermediate_size=14336,
|
| 16 |
+
num_hidden_layers=32,
|
| 17 |
+
num_attention_heads=32,
|
| 18 |
+
num_key_value_heads=8,
|
| 19 |
+
hidden_act="silu",
|
| 20 |
+
initializer_range=0.02,
|
| 21 |
+
rms_norm_eps=1e-6,
|
| 22 |
+
attn_only_wo_proj=False,
|
| 23 |
+
use_cache=True,
|
| 24 |
+
calc_logits_for_entire_prompt=False,
|
| 25 |
+
output_router_logits=False,
|
| 26 |
+
router_aux_loss_coef=0.001,
|
| 27 |
+
pad_token_id=0,
|
| 28 |
+
bos_token_id=1,
|
| 29 |
+
eos_token_id=2,
|
| 30 |
+
sliding_window=None,
|
| 31 |
+
max_position_embeddings=262144,
|
| 32 |
+
orig_max_position_embeddings=None,
|
| 33 |
+
attention_dropout=0.0,
|
| 34 |
+
num_experts_per_tok=2,
|
| 35 |
+
num_experts=16,
|
| 36 |
+
use_mamba_kernels=True,
|
| 37 |
+
mamba_d_state=16,
|
| 38 |
+
mamba_d_conv=4,
|
| 39 |
+
mamba_expand=2,
|
| 40 |
+
mamba_dt_rank="auto",
|
| 41 |
+
mamba_conv_bias=True,
|
| 42 |
+
mamba_proj_bias=False,
|
| 43 |
+
mamba_inner_layernorms=True,
|
| 44 |
+
kv_reuse_every_i_layer=-1,
|
| 45 |
+
kv_reuse_group=None,
|
| 46 |
+
kv_weight_reuse=False,
|
| 47 |
+
global_attn_idx=None,
|
| 48 |
+
num_mamba=1,
|
| 49 |
+
pure_attn=False,
|
| 50 |
+
attn_implementation_new='sdpa',
|
| 51 |
+
rope_type=None,
|
| 52 |
+
attn_factor=0.5,
|
| 53 |
+
**kwargs,
|
| 54 |
+
):
|
| 55 |
+
self.vocab_size = vocab_size
|
| 56 |
+
self.tie_word_embeddings = tie_word_embeddings
|
| 57 |
+
self.hidden_size = hidden_size
|
| 58 |
+
self.intermediate_size = intermediate_size
|
| 59 |
+
self.num_hidden_layers = num_hidden_layers
|
| 60 |
+
self.num_attention_heads = num_attention_heads
|
| 61 |
+
self.sliding_window = sliding_window
|
| 62 |
+
self.max_position_embeddings = max_position_embeddings
|
| 63 |
+
self.orig_max_position_embeddings = orig_max_position_embeddings
|
| 64 |
+
self.attention_dropout = attention_dropout
|
| 65 |
+
self.attn_only_wo_proj = attn_only_wo_proj
|
| 66 |
+
|
| 67 |
+
if num_key_value_heads is None:
|
| 68 |
+
num_key_value_heads = num_attention_heads
|
| 69 |
+
|
| 70 |
+
self.num_key_value_heads = num_key_value_heads
|
| 71 |
+
self.hidden_act = hidden_act
|
| 72 |
+
self.initializer_range = initializer_range
|
| 73 |
+
self.rms_norm_eps = rms_norm_eps
|
| 74 |
+
|
| 75 |
+
self.use_cache = use_cache
|
| 76 |
+
self.calc_logits_for_entire_prompt = calc_logits_for_entire_prompt
|
| 77 |
+
self.output_router_logits = output_router_logits
|
| 78 |
+
self.router_aux_loss_coef = router_aux_loss_coef
|
| 79 |
+
|
| 80 |
+
self.num_experts_per_tok = num_experts_per_tok
|
| 81 |
+
self.num_experts = num_experts
|
| 82 |
+
|
| 83 |
+
self.use_mamba_kernels = use_mamba_kernels
|
| 84 |
+
self.mamba_d_state = mamba_d_state
|
| 85 |
+
self.mamba_d_conv = mamba_d_conv
|
| 86 |
+
self.mamba_expand = mamba_expand
|
| 87 |
+
self.mamba_dt_rank = math.ceil(self.hidden_size / 16) if mamba_dt_rank == "auto" else mamba_dt_rank
|
| 88 |
+
self.mamba_conv_bias = mamba_conv_bias
|
| 89 |
+
self.mamba_proj_bias = mamba_proj_bias
|
| 90 |
+
self.mamba_inner_layernorms = mamba_inner_layernorms
|
| 91 |
+
|
| 92 |
+
self.attn_hidden_size = kwargs.pop("attn_hidden_size", -1)
|
| 93 |
+
self.attn_factor = attn_factor
|
| 94 |
+
self.kq_head_dim = kwargs.pop("kq_head_dim", -1)
|
| 95 |
+
self.v_head_dim = kwargs.pop("v_head_dim", -1)
|
| 96 |
+
self.kq_norm = kwargs.pop("kq_norm", None)
|
| 97 |
+
self.rope = kwargs.pop("rope", False)
|
| 98 |
+
self.rope_theta = kwargs.pop("rope_theta", 10000.0)
|
| 99 |
+
self.num_memory_tokens = kwargs.pop("num_memory_tokens", 0)
|
| 100 |
+
self.memory_tokens_interspersed_every = kwargs.pop("memory_tokens_interspersed_every", 0)
|
| 101 |
+
|
| 102 |
+
self.kv_reuse_every_i_layer = kv_reuse_every_i_layer
|
| 103 |
+
self.kv_reuse_group = kv_reuse_group
|
| 104 |
+
self.kv_weight_reuse = kv_weight_reuse
|
| 105 |
+
|
| 106 |
+
self.global_attn_idx = global_attn_idx
|
| 107 |
+
|
| 108 |
+
self.num_mamba = num_mamba
|
| 109 |
+
|
| 110 |
+
self.attn_implementation_new = attn_implementation_new
|
| 111 |
+
|
| 112 |
+
self.rope_type = rope_type
|
| 113 |
+
|
| 114 |
+
self.pure_attn = pure_attn
|
| 115 |
+
|
| 116 |
+
super().__init__(
|
| 117 |
+
pad_token_id=pad_token_id,
|
| 118 |
+
bos_token_id=bos_token_id,
|
| 119 |
+
eos_token_id=eos_token_id,
|
| 120 |
+
tie_word_embeddings=tie_word_embeddings,
|
| 121 |
+
**kwargs,
|
| 122 |
+
)
|
checkpoint-3670/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"transformers_version": "4.53.0"
|
| 10 |
+
}
|
checkpoint-3670/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2decd3903100797d7bee8fb369c5c169f6aee80480ac11adbec530b931b8482d
|
| 3 |
+
size 2471642200
|
checkpoint-3670/modeling_hymba.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3670/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4436563ae95994e3dc556265a03fa939edf4ae59caa01d5c852f8cfe68369dcb
|
| 3 |
+
size 4943354422
|
checkpoint-3670/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-3670/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c99d7c54f1bcd86b8012d20bcfb3cf68e8fc210787c8328b62c251974eeae7f
|
| 3 |
+
size 1064
|
checkpoint-3670/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
checkpoint-3670/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-3670/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|eot_id|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
checkpoint-3670/trainer_state.json
ADDED
|
@@ -0,0 +1,3346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3670,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0002725306171115161,
|
| 14 |
+
"grad_norm": 106.0,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 11.3973,
|
| 17 |
+
"mean_token_accuracy": 0.010489485081052408,
|
| 18 |
+
"num_tokens": 180497.0,
|
| 19 |
+
"step": 1
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.0027253061711151614,
|
| 23 |
+
"grad_norm": 57.0,
|
| 24 |
+
"learning_rate": 2.0361990950226245e-05,
|
| 25 |
+
"loss": 10.0617,
|
| 26 |
+
"mean_token_accuracy": 0.018964683349218428,
|
| 27 |
+
"num_tokens": 1772191.0,
|
| 28 |
+
"step": 10
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.005450612342230323,
|
| 32 |
+
"grad_norm": 37.75,
|
| 33 |
+
"learning_rate": 4.2986425339366516e-05,
|
| 34 |
+
"loss": 8.1695,
|
| 35 |
+
"mean_token_accuracy": 0.04115874093695311,
|
| 36 |
+
"num_tokens": 3528128.0,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.008175918513345483,
|
| 41 |
+
"grad_norm": 26.25,
|
| 42 |
+
"learning_rate": 6.561085972850679e-05,
|
| 43 |
+
"loss": 6.7807,
|
| 44 |
+
"mean_token_accuracy": 0.07557539474219084,
|
| 45 |
+
"num_tokens": 5321820.0,
|
| 46 |
+
"step": 30
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.010901224684460645,
|
| 50 |
+
"grad_norm": 20.125,
|
| 51 |
+
"learning_rate": 8.823529411764706e-05,
|
| 52 |
+
"loss": 5.4023,
|
| 53 |
+
"mean_token_accuracy": 0.1482221502577886,
|
| 54 |
+
"num_tokens": 7036353.0,
|
| 55 |
+
"step": 40
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.013626530855575806,
|
| 59 |
+
"grad_norm": 7.53125,
|
| 60 |
+
"learning_rate": 0.00011085972850678733,
|
| 61 |
+
"loss": 4.5179,
|
| 62 |
+
"mean_token_accuracy": 0.2088393464917317,
|
| 63 |
+
"num_tokens": 8794502.0,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.016351837026690966,
|
| 68 |
+
"grad_norm": 8.0625,
|
| 69 |
+
"learning_rate": 0.0001334841628959276,
|
| 70 |
+
"loss": 3.8857,
|
| 71 |
+
"mean_token_accuracy": 0.26825836482457815,
|
| 72 |
+
"num_tokens": 10519144.0,
|
| 73 |
+
"step": 60
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.019077143197806127,
|
| 77 |
+
"grad_norm": 9.3125,
|
| 78 |
+
"learning_rate": 0.00015610859728506788,
|
| 79 |
+
"loss": 3.2721,
|
| 80 |
+
"mean_token_accuracy": 0.348467530682683,
|
| 81 |
+
"num_tokens": 12272638.0,
|
| 82 |
+
"step": 70
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.02180244936892129,
|
| 86 |
+
"grad_norm": 3.703125,
|
| 87 |
+
"learning_rate": 0.00017873303167420816,
|
| 88 |
+
"loss": 2.8456,
|
| 89 |
+
"mean_token_accuracy": 0.41965038063935933,
|
| 90 |
+
"num_tokens": 14037595.0,
|
| 91 |
+
"step": 80
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.02452775554003645,
|
| 95 |
+
"grad_norm": 2.84375,
|
| 96 |
+
"learning_rate": 0.0002013574660633484,
|
| 97 |
+
"loss": 2.5555,
|
| 98 |
+
"mean_token_accuracy": 0.46718343761749564,
|
| 99 |
+
"num_tokens": 15813413.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.027253061711151612,
|
| 104 |
+
"grad_norm": 3.140625,
|
| 105 |
+
"learning_rate": 0.0002239819004524887,
|
| 106 |
+
"loss": 2.3813,
|
| 107 |
+
"mean_token_accuracy": 0.4977288795635104,
|
| 108 |
+
"num_tokens": 17606667.0,
|
| 109 |
+
"step": 100
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.029978367882266772,
|
| 113 |
+
"grad_norm": 5.03125,
|
| 114 |
+
"learning_rate": 0.000246606334841629,
|
| 115 |
+
"loss": 2.1859,
|
| 116 |
+
"mean_token_accuracy": 0.5393931507132947,
|
| 117 |
+
"num_tokens": 19387650.0,
|
| 118 |
+
"step": 110
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.03270367405338193,
|
| 122 |
+
"grad_norm": 2.125,
|
| 123 |
+
"learning_rate": 0.0002692307692307692,
|
| 124 |
+
"loss": 2.1126,
|
| 125 |
+
"mean_token_accuracy": 0.5529376215301454,
|
| 126 |
+
"num_tokens": 21111629.0,
|
| 127 |
+
"step": 120
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.03542898022449709,
|
| 131 |
+
"grad_norm": 2.390625,
|
| 132 |
+
"learning_rate": 0.00029185520361990955,
|
| 133 |
+
"loss": 2.1077,
|
| 134 |
+
"mean_token_accuracy": 0.561456169653684,
|
| 135 |
+
"num_tokens": 22855847.0,
|
| 136 |
+
"step": 130
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.038154286395612254,
|
| 140 |
+
"grad_norm": 2.8125,
|
| 141 |
+
"learning_rate": 0.0003144796380090498,
|
| 142 |
+
"loss": 1.9626,
|
| 143 |
+
"mean_token_accuracy": 0.5820818378590047,
|
| 144 |
+
"num_tokens": 24647294.0,
|
| 145 |
+
"step": 140
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.04087959256672742,
|
| 149 |
+
"grad_norm": 2.1875,
|
| 150 |
+
"learning_rate": 0.00033710407239819005,
|
| 151 |
+
"loss": 1.9295,
|
| 152 |
+
"mean_token_accuracy": 0.5896116701886058,
|
| 153 |
+
"num_tokens": 26336128.0,
|
| 154 |
+
"step": 150
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.04360489873784258,
|
| 158 |
+
"grad_norm": 2.046875,
|
| 159 |
+
"learning_rate": 0.00035972850678733033,
|
| 160 |
+
"loss": 1.9306,
|
| 161 |
+
"mean_token_accuracy": 0.5908254419453443,
|
| 162 |
+
"num_tokens": 28061528.0,
|
| 163 |
+
"step": 160
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.04633020490895774,
|
| 167 |
+
"grad_norm": 2.28125,
|
| 168 |
+
"learning_rate": 0.00038235294117647055,
|
| 169 |
+
"loss": 1.9056,
|
| 170 |
+
"mean_token_accuracy": 0.5959834239445627,
|
| 171 |
+
"num_tokens": 29834651.0,
|
| 172 |
+
"step": 170
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.0490555110800729,
|
| 176 |
+
"grad_norm": 1.6953125,
|
| 177 |
+
"learning_rate": 0.0004049773755656109,
|
| 178 |
+
"loss": 1.9277,
|
| 179 |
+
"mean_token_accuracy": 0.595614176010713,
|
| 180 |
+
"num_tokens": 31533806.0,
|
| 181 |
+
"step": 180
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05178081725118806,
|
| 185 |
+
"grad_norm": 1.921875,
|
| 186 |
+
"learning_rate": 0.0004276018099547511,
|
| 187 |
+
"loss": 1.8552,
|
| 188 |
+
"mean_token_accuracy": 0.606397076882422,
|
| 189 |
+
"num_tokens": 33328644.0,
|
| 190 |
+
"step": 190
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.054506123422303224,
|
| 194 |
+
"grad_norm": 1.6484375,
|
| 195 |
+
"learning_rate": 0.00045022624434389144,
|
| 196 |
+
"loss": 1.8461,
|
| 197 |
+
"mean_token_accuracy": 0.6106193735264241,
|
| 198 |
+
"num_tokens": 35085202.0,
|
| 199 |
+
"step": 200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.057231429593418384,
|
| 203 |
+
"grad_norm": 1.4375,
|
| 204 |
+
"learning_rate": 0.00047285067873303167,
|
| 205 |
+
"loss": 1.8531,
|
| 206 |
+
"mean_token_accuracy": 0.6109982108697295,
|
| 207 |
+
"num_tokens": 36899685.0,
|
| 208 |
+
"step": 210
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.059956735764533545,
|
| 212 |
+
"grad_norm": 1.34375,
|
| 213 |
+
"learning_rate": 0.000495475113122172,
|
| 214 |
+
"loss": 1.7533,
|
| 215 |
+
"mean_token_accuracy": 0.6274582323618233,
|
| 216 |
+
"num_tokens": 38663867.0,
|
| 217 |
+
"step": 220
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.0626820419356487,
|
| 221 |
+
"grad_norm": 1.5625,
|
| 222 |
+
"learning_rate": 0.0004994381233319287,
|
| 223 |
+
"loss": 1.7962,
|
| 224 |
+
"mean_token_accuracy": 0.62058030301705,
|
| 225 |
+
"num_tokens": 40368688.0,
|
| 226 |
+
"step": 230
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06540734810676387,
|
| 230 |
+
"grad_norm": 1.234375,
|
| 231 |
+
"learning_rate": 0.0004987357774968394,
|
| 232 |
+
"loss": 1.795,
|
| 233 |
+
"mean_token_accuracy": 0.6195226193405687,
|
| 234 |
+
"num_tokens": 42091556.0,
|
| 235 |
+
"step": 240
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.06813265427787903,
|
| 239 |
+
"grad_norm": 1.359375,
|
| 240 |
+
"learning_rate": 0.0004980334316617502,
|
| 241 |
+
"loss": 1.7885,
|
| 242 |
+
"mean_token_accuracy": 0.6225197708234191,
|
| 243 |
+
"num_tokens": 43832865.0,
|
| 244 |
+
"step": 250
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.07085796044899419,
|
| 248 |
+
"grad_norm": 1.15625,
|
| 249 |
+
"learning_rate": 0.000497331085826661,
|
| 250 |
+
"loss": 1.777,
|
| 251 |
+
"mean_token_accuracy": 0.6262112149037421,
|
| 252 |
+
"num_tokens": 45556421.0,
|
| 253 |
+
"step": 260
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.07358326662010935,
|
| 257 |
+
"grad_norm": 1.4375,
|
| 258 |
+
"learning_rate": 0.0004966287399915719,
|
| 259 |
+
"loss": 1.8368,
|
| 260 |
+
"mean_token_accuracy": 0.6205988208763301,
|
| 261 |
+
"num_tokens": 47284838.0,
|
| 262 |
+
"step": 270
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.07630857279122451,
|
| 266 |
+
"grad_norm": 1.2734375,
|
| 267 |
+
"learning_rate": 0.0004959263941564827,
|
| 268 |
+
"loss": 1.7812,
|
| 269 |
+
"mean_token_accuracy": 0.6273719569668174,
|
| 270 |
+
"num_tokens": 49025592.0,
|
| 271 |
+
"step": 280
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.07903387896233968,
|
| 275 |
+
"grad_norm": 1.1875,
|
| 276 |
+
"learning_rate": 0.0004952240483213935,
|
| 277 |
+
"loss": 1.8823,
|
| 278 |
+
"mean_token_accuracy": 0.613296614214778,
|
| 279 |
+
"num_tokens": 50771353.0,
|
| 280 |
+
"step": 290
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.08175918513345484,
|
| 284 |
+
"grad_norm": 1.265625,
|
| 285 |
+
"learning_rate": 0.0004945217024863043,
|
| 286 |
+
"loss": 1.7168,
|
| 287 |
+
"mean_token_accuracy": 0.6380896210670471,
|
| 288 |
+
"num_tokens": 52521467.0,
|
| 289 |
+
"step": 300
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.08448449130457,
|
| 293 |
+
"grad_norm": 1.1328125,
|
| 294 |
+
"learning_rate": 0.0004938193566512151,
|
| 295 |
+
"loss": 1.7443,
|
| 296 |
+
"mean_token_accuracy": 0.6318002883344889,
|
| 297 |
+
"num_tokens": 54338858.0,
|
| 298 |
+
"step": 310
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.08720979747568516,
|
| 302 |
+
"grad_norm": 1.0078125,
|
| 303 |
+
"learning_rate": 0.0004931170108161258,
|
| 304 |
+
"loss": 1.7661,
|
| 305 |
+
"mean_token_accuracy": 0.6319120707921684,
|
| 306 |
+
"num_tokens": 56014081.0,
|
| 307 |
+
"step": 320
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.08993510364680032,
|
| 311 |
+
"grad_norm": 1.109375,
|
| 312 |
+
"learning_rate": 0.0004924146649810366,
|
| 313 |
+
"loss": 1.7026,
|
| 314 |
+
"mean_token_accuracy": 0.6394819458015263,
|
| 315 |
+
"num_tokens": 57778337.0,
|
| 316 |
+
"step": 330
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.09266040981791548,
|
| 320 |
+
"grad_norm": 0.9375,
|
| 321 |
+
"learning_rate": 0.0004917123191459475,
|
| 322 |
+
"loss": 1.7264,
|
| 323 |
+
"mean_token_accuracy": 0.6390960057266056,
|
| 324 |
+
"num_tokens": 59528977.0,
|
| 325 |
+
"step": 340
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.09538571598903064,
|
| 329 |
+
"grad_norm": 0.9765625,
|
| 330 |
+
"learning_rate": 0.0004910099733108583,
|
| 331 |
+
"loss": 1.7108,
|
| 332 |
+
"mean_token_accuracy": 0.639170390740037,
|
| 333 |
+
"num_tokens": 61295985.0,
|
| 334 |
+
"step": 350
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.0981110221601458,
|
| 338 |
+
"grad_norm": 1.109375,
|
| 339 |
+
"learning_rate": 0.0004903076274757691,
|
| 340 |
+
"loss": 1.6902,
|
| 341 |
+
"mean_token_accuracy": 0.6423498384654522,
|
| 342 |
+
"num_tokens": 63026897.0,
|
| 343 |
+
"step": 360
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.10083632833126097,
|
| 347 |
+
"grad_norm": 0.78515625,
|
| 348 |
+
"learning_rate": 0.0004896052816406799,
|
| 349 |
+
"loss": 1.6393,
|
| 350 |
+
"mean_token_accuracy": 0.6515957163646817,
|
| 351 |
+
"num_tokens": 64770711.0,
|
| 352 |
+
"step": 370
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.10356163450237613,
|
| 356 |
+
"grad_norm": 0.80859375,
|
| 357 |
+
"learning_rate": 0.0004889029358055907,
|
| 358 |
+
"loss": 1.6554,
|
| 359 |
+
"mean_token_accuracy": 0.6511010814458131,
|
| 360 |
+
"num_tokens": 66551008.0,
|
| 361 |
+
"step": 380
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.10628694067349129,
|
| 365 |
+
"grad_norm": 0.734375,
|
| 366 |
+
"learning_rate": 0.0004882005899705015,
|
| 367 |
+
"loss": 1.6654,
|
| 368 |
+
"mean_token_accuracy": 0.6467505861073732,
|
| 369 |
+
"num_tokens": 68320690.0,
|
| 370 |
+
"step": 390
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.10901224684460645,
|
| 374 |
+
"grad_norm": 0.8046875,
|
| 375 |
+
"learning_rate": 0.0004874982441354123,
|
| 376 |
+
"loss": 1.5943,
|
| 377 |
+
"mean_token_accuracy": 0.6583768699318171,
|
| 378 |
+
"num_tokens": 70095284.0,
|
| 379 |
+
"step": 400
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.11173755301572161,
|
| 383 |
+
"grad_norm": 0.69921875,
|
| 384 |
+
"learning_rate": 0.0004867958983003231,
|
| 385 |
+
"loss": 1.6378,
|
| 386 |
+
"mean_token_accuracy": 0.65406036041677,
|
| 387 |
+
"num_tokens": 71803511.0,
|
| 388 |
+
"step": 410
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.11446285918683677,
|
| 392 |
+
"grad_norm": 0.68359375,
|
| 393 |
+
"learning_rate": 0.0004860935524652339,
|
| 394 |
+
"loss": 1.5457,
|
| 395 |
+
"mean_token_accuracy": 0.667325837444514,
|
| 396 |
+
"num_tokens": 73528297.0,
|
| 397 |
+
"step": 420
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.11718816535795193,
|
| 401 |
+
"grad_norm": 0.72265625,
|
| 402 |
+
"learning_rate": 0.0004853912066301447,
|
| 403 |
+
"loss": 1.5515,
|
| 404 |
+
"mean_token_accuracy": 0.6666892973706127,
|
| 405 |
+
"num_tokens": 75274289.0,
|
| 406 |
+
"step": 430
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.11991347152906709,
|
| 410 |
+
"grad_norm": 0.875,
|
| 411 |
+
"learning_rate": 0.00048468886079505545,
|
| 412 |
+
"loss": 1.6137,
|
| 413 |
+
"mean_token_accuracy": 0.6556662306189537,
|
| 414 |
+
"num_tokens": 77077403.0,
|
| 415 |
+
"step": 440
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.12263877770018225,
|
| 419 |
+
"grad_norm": 0.80859375,
|
| 420 |
+
"learning_rate": 0.0004839865149599663,
|
| 421 |
+
"loss": 1.5933,
|
| 422 |
+
"mean_token_accuracy": 0.6582868808880449,
|
| 423 |
+
"num_tokens": 78859882.0,
|
| 424 |
+
"step": 450
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.1253640838712974,
|
| 428 |
+
"grad_norm": 1.5078125,
|
| 429 |
+
"learning_rate": 0.0004832841691248771,
|
| 430 |
+
"loss": 1.6189,
|
| 431 |
+
"mean_token_accuracy": 0.6552375074476003,
|
| 432 |
+
"num_tokens": 80590976.0,
|
| 433 |
+
"step": 460
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.12808939004241257,
|
| 437 |
+
"grad_norm": 1.75,
|
| 438 |
+
"learning_rate": 0.0004825818232897879,
|
| 439 |
+
"loss": 1.5785,
|
| 440 |
+
"mean_token_accuracy": 0.6629863957874477,
|
| 441 |
+
"num_tokens": 82275126.0,
|
| 442 |
+
"step": 470
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.13081469621352773,
|
| 446 |
+
"grad_norm": 0.6796875,
|
| 447 |
+
"learning_rate": 0.00048187947745469866,
|
| 448 |
+
"loss": 1.5519,
|
| 449 |
+
"mean_token_accuracy": 0.6660696087405086,
|
| 450 |
+
"num_tokens": 84096910.0,
|
| 451 |
+
"step": 480
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.1335400023846429,
|
| 455 |
+
"grad_norm": 0.69921875,
|
| 456 |
+
"learning_rate": 0.00048117713161960953,
|
| 457 |
+
"loss": 1.5893,
|
| 458 |
+
"mean_token_accuracy": 0.6608347145840525,
|
| 459 |
+
"num_tokens": 85876326.0,
|
| 460 |
+
"step": 490
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.13626530855575805,
|
| 464 |
+
"grad_norm": 0.6484375,
|
| 465 |
+
"learning_rate": 0.0004804747857845203,
|
| 466 |
+
"loss": 1.5587,
|
| 467 |
+
"mean_token_accuracy": 0.6648266627453268,
|
| 468 |
+
"num_tokens": 87607478.0,
|
| 469 |
+
"step": 500
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.1389906147268732,
|
| 473 |
+
"grad_norm": 0.66796875,
|
| 474 |
+
"learning_rate": 0.0004797724399494311,
|
| 475 |
+
"loss": 1.4929,
|
| 476 |
+
"mean_token_accuracy": 0.6747789577580988,
|
| 477 |
+
"num_tokens": 89350066.0,
|
| 478 |
+
"step": 510
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.14171592089798837,
|
| 482 |
+
"grad_norm": 0.609375,
|
| 483 |
+
"learning_rate": 0.0004790700941143419,
|
| 484 |
+
"loss": 1.5088,
|
| 485 |
+
"mean_token_accuracy": 0.6725917850621045,
|
| 486 |
+
"num_tokens": 91067910.0,
|
| 487 |
+
"step": 520
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.14444122706910353,
|
| 491 |
+
"grad_norm": 0.57421875,
|
| 492 |
+
"learning_rate": 0.00047836774827925274,
|
| 493 |
+
"loss": 1.4991,
|
| 494 |
+
"mean_token_accuracy": 0.6736135099083185,
|
| 495 |
+
"num_tokens": 92797017.0,
|
| 496 |
+
"step": 530
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.1471665332402187,
|
| 500 |
+
"grad_norm": 0.72265625,
|
| 501 |
+
"learning_rate": 0.0004776654024441635,
|
| 502 |
+
"loss": 1.5442,
|
| 503 |
+
"mean_token_accuracy": 0.6660140948370099,
|
| 504 |
+
"num_tokens": 94606329.0,
|
| 505 |
+
"step": 540
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.14989183941133385,
|
| 509 |
+
"grad_norm": 0.64453125,
|
| 510 |
+
"learning_rate": 0.0004769630566090743,
|
| 511 |
+
"loss": 1.4942,
|
| 512 |
+
"mean_token_accuracy": 0.6727027535438538,
|
| 513 |
+
"num_tokens": 96331087.0,
|
| 514 |
+
"step": 550
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.15261714558244902,
|
| 518 |
+
"grad_norm": 0.609375,
|
| 519 |
+
"learning_rate": 0.00047626071077398513,
|
| 520 |
+
"loss": 1.5207,
|
| 521 |
+
"mean_token_accuracy": 0.6709301644004881,
|
| 522 |
+
"num_tokens": 98138711.0,
|
| 523 |
+
"step": 560
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.15534245175356418,
|
| 527 |
+
"grad_norm": 1.0625,
|
| 528 |
+
"learning_rate": 0.00047555836493889595,
|
| 529 |
+
"loss": 1.5346,
|
| 530 |
+
"mean_token_accuracy": 0.6697394871152937,
|
| 531 |
+
"num_tokens": 99885005.0,
|
| 532 |
+
"step": 570
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.15806775792467936,
|
| 536 |
+
"grad_norm": 0.75390625,
|
| 537 |
+
"learning_rate": 0.0004748560191038067,
|
| 538 |
+
"loss": 1.3995,
|
| 539 |
+
"mean_token_accuracy": 0.6897108962759375,
|
| 540 |
+
"num_tokens": 101636075.0,
|
| 541 |
+
"step": 580
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.16079306409579452,
|
| 545 |
+
"grad_norm": 0.6484375,
|
| 546 |
+
"learning_rate": 0.0004741536732687175,
|
| 547 |
+
"loss": 1.4711,
|
| 548 |
+
"mean_token_accuracy": 0.6787430424243212,
|
| 549 |
+
"num_tokens": 103349118.0,
|
| 550 |
+
"step": 590
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.16351837026690969,
|
| 554 |
+
"grad_norm": 0.60546875,
|
| 555 |
+
"learning_rate": 0.00047345132743362834,
|
| 556 |
+
"loss": 1.4826,
|
| 557 |
+
"mean_token_accuracy": 0.6767816330306232,
|
| 558 |
+
"num_tokens": 105033010.0,
|
| 559 |
+
"step": 600
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.16624367643802485,
|
| 563 |
+
"grad_norm": 0.53515625,
|
| 564 |
+
"learning_rate": 0.00047274898159853915,
|
| 565 |
+
"loss": 1.4251,
|
| 566 |
+
"mean_token_accuracy": 0.6852256084792316,
|
| 567 |
+
"num_tokens": 106723283.0,
|
| 568 |
+
"step": 610
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.16896898260914,
|
| 572 |
+
"grad_norm": 0.53515625,
|
| 573 |
+
"learning_rate": 0.0004720466357634499,
|
| 574 |
+
"loss": 1.4393,
|
| 575 |
+
"mean_token_accuracy": 0.6821009494364262,
|
| 576 |
+
"num_tokens": 108436878.0,
|
| 577 |
+
"step": 620
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.17169428878025517,
|
| 581 |
+
"grad_norm": 0.59765625,
|
| 582 |
+
"learning_rate": 0.0004713442899283608,
|
| 583 |
+
"loss": 1.4218,
|
| 584 |
+
"mean_token_accuracy": 0.6854843683540821,
|
| 585 |
+
"num_tokens": 110203157.0,
|
| 586 |
+
"step": 630
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.17441959495137033,
|
| 590 |
+
"grad_norm": 0.6484375,
|
| 591 |
+
"learning_rate": 0.00047064194409327155,
|
| 592 |
+
"loss": 1.4457,
|
| 593 |
+
"mean_token_accuracy": 0.6829626850783825,
|
| 594 |
+
"num_tokens": 111949130.0,
|
| 595 |
+
"step": 640
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.1771449011224855,
|
| 599 |
+
"grad_norm": 0.62109375,
|
| 600 |
+
"learning_rate": 0.0004699395982581823,
|
| 601 |
+
"loss": 1.4549,
|
| 602 |
+
"mean_token_accuracy": 0.6785116318613291,
|
| 603 |
+
"num_tokens": 113652926.0,
|
| 604 |
+
"step": 650
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.17987020729360065,
|
| 608 |
+
"grad_norm": 0.53125,
|
| 609 |
+
"learning_rate": 0.0004692372524230931,
|
| 610 |
+
"loss": 1.4303,
|
| 611 |
+
"mean_token_accuracy": 0.6821146721020341,
|
| 612 |
+
"num_tokens": 115334647.0,
|
| 613 |
+
"step": 660
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.1825955134647158,
|
| 617 |
+
"grad_norm": 0.54296875,
|
| 618 |
+
"learning_rate": 0.00046853490658800394,
|
| 619 |
+
"loss": 1.3843,
|
| 620 |
+
"mean_token_accuracy": 0.693703673966229,
|
| 621 |
+
"num_tokens": 117032381.0,
|
| 622 |
+
"step": 670
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.18532081963583097,
|
| 626 |
+
"grad_norm": 0.51953125,
|
| 627 |
+
"learning_rate": 0.00046783256075291475,
|
| 628 |
+
"loss": 1.4299,
|
| 629 |
+
"mean_token_accuracy": 0.6833634852431715,
|
| 630 |
+
"num_tokens": 118801553.0,
|
| 631 |
+
"step": 680
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.18804612580694613,
|
| 635 |
+
"grad_norm": 0.51953125,
|
| 636 |
+
"learning_rate": 0.0004671302149178255,
|
| 637 |
+
"loss": 1.4306,
|
| 638 |
+
"mean_token_accuracy": 0.6827819195576013,
|
| 639 |
+
"num_tokens": 120530271.0,
|
| 640 |
+
"step": 690
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.1907714319780613,
|
| 644 |
+
"grad_norm": 0.515625,
|
| 645 |
+
"learning_rate": 0.00046642786908273633,
|
| 646 |
+
"loss": 1.4207,
|
| 647 |
+
"mean_token_accuracy": 0.6865599798038602,
|
| 648 |
+
"num_tokens": 122314411.0,
|
| 649 |
+
"step": 700
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.19349673814917645,
|
| 653 |
+
"grad_norm": 0.474609375,
|
| 654 |
+
"learning_rate": 0.00046572552324764715,
|
| 655 |
+
"loss": 1.4071,
|
| 656 |
+
"mean_token_accuracy": 0.687783928308636,
|
| 657 |
+
"num_tokens": 124054113.0,
|
| 658 |
+
"step": 710
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.1962220443202916,
|
| 662 |
+
"grad_norm": 0.5078125,
|
| 663 |
+
"learning_rate": 0.00046502317741255796,
|
| 664 |
+
"loss": 1.4147,
|
| 665 |
+
"mean_token_accuracy": 0.6855330302380025,
|
| 666 |
+
"num_tokens": 125786705.0,
|
| 667 |
+
"step": 720
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.19894735049140677,
|
| 671 |
+
"grad_norm": 0.53125,
|
| 672 |
+
"learning_rate": 0.0004643208315774687,
|
| 673 |
+
"loss": 1.4339,
|
| 674 |
+
"mean_token_accuracy": 0.6828508110716939,
|
| 675 |
+
"num_tokens": 127510112.0,
|
| 676 |
+
"step": 730
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.20167265666252193,
|
| 680 |
+
"grad_norm": 0.490234375,
|
| 681 |
+
"learning_rate": 0.0004636184857423796,
|
| 682 |
+
"loss": 1.3693,
|
| 683 |
+
"mean_token_accuracy": 0.6937206975184381,
|
| 684 |
+
"num_tokens": 129321733.0,
|
| 685 |
+
"step": 740
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.2043979628336371,
|
| 689 |
+
"grad_norm": 0.52734375,
|
| 690 |
+
"learning_rate": 0.00046291613990729035,
|
| 691 |
+
"loss": 1.4267,
|
| 692 |
+
"mean_token_accuracy": 0.6843720972537994,
|
| 693 |
+
"num_tokens": 131068939.0,
|
| 694 |
+
"step": 750
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.20712326900475225,
|
| 698 |
+
"grad_norm": 0.53515625,
|
| 699 |
+
"learning_rate": 0.00046221379407220117,
|
| 700 |
+
"loss": 1.4647,
|
| 701 |
+
"mean_token_accuracy": 0.6786275329068303,
|
| 702 |
+
"num_tokens": 132800192.0,
|
| 703 |
+
"step": 760
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.2098485751758674,
|
| 707 |
+
"grad_norm": 0.5,
|
| 708 |
+
"learning_rate": 0.00046151144823711193,
|
| 709 |
+
"loss": 1.3739,
|
| 710 |
+
"mean_token_accuracy": 0.6946681007742882,
|
| 711 |
+
"num_tokens": 134501880.0,
|
| 712 |
+
"step": 770
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.21257388134698257,
|
| 716 |
+
"grad_norm": 0.60546875,
|
| 717 |
+
"learning_rate": 0.0004608091024020228,
|
| 718 |
+
"loss": 1.3379,
|
| 719 |
+
"mean_token_accuracy": 0.6989552618004382,
|
| 720 |
+
"num_tokens": 136227230.0,
|
| 721 |
+
"step": 780
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.21529918751809773,
|
| 725 |
+
"grad_norm": 0.63671875,
|
| 726 |
+
"learning_rate": 0.00046010675656693356,
|
| 727 |
+
"loss": 1.3646,
|
| 728 |
+
"mean_token_accuracy": 0.6950390106998384,
|
| 729 |
+
"num_tokens": 137938433.0,
|
| 730 |
+
"step": 790
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.2180244936892129,
|
| 734 |
+
"grad_norm": 0.453125,
|
| 735 |
+
"learning_rate": 0.0004594044107318444,
|
| 736 |
+
"loss": 1.3744,
|
| 737 |
+
"mean_token_accuracy": 0.6953079327940941,
|
| 738 |
+
"num_tokens": 139667163.0,
|
| 739 |
+
"step": 800
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.22074979986032806,
|
| 743 |
+
"grad_norm": 0.443359375,
|
| 744 |
+
"learning_rate": 0.00045870206489675514,
|
| 745 |
+
"loss": 1.3347,
|
| 746 |
+
"mean_token_accuracy": 0.7004647579975426,
|
| 747 |
+
"num_tokens": 141481099.0,
|
| 748 |
+
"step": 810
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.22347510603144322,
|
| 752 |
+
"grad_norm": 0.458984375,
|
| 753 |
+
"learning_rate": 0.000457999719061666,
|
| 754 |
+
"loss": 1.4183,
|
| 755 |
+
"mean_token_accuracy": 0.6861088563688099,
|
| 756 |
+
"num_tokens": 143204243.0,
|
| 757 |
+
"step": 820
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.22620041220255838,
|
| 761 |
+
"grad_norm": 0.5078125,
|
| 762 |
+
"learning_rate": 0.00045729737322657677,
|
| 763 |
+
"loss": 1.3501,
|
| 764 |
+
"mean_token_accuracy": 0.6989492080174387,
|
| 765 |
+
"num_tokens": 144995581.0,
|
| 766 |
+
"step": 830
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.22892571837367354,
|
| 770 |
+
"grad_norm": 0.47265625,
|
| 771 |
+
"learning_rate": 0.0004565950273914876,
|
| 772 |
+
"loss": 1.3681,
|
| 773 |
+
"mean_token_accuracy": 0.6930115528404712,
|
| 774 |
+
"num_tokens": 146711076.0,
|
| 775 |
+
"step": 840
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.2316510245447887,
|
| 779 |
+
"grad_norm": 0.44921875,
|
| 780 |
+
"learning_rate": 0.0004558926815563984,
|
| 781 |
+
"loss": 1.335,
|
| 782 |
+
"mean_token_accuracy": 0.7001006077043712,
|
| 783 |
+
"num_tokens": 148463902.0,
|
| 784 |
+
"step": 850
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.23437633071590386,
|
| 788 |
+
"grad_norm": 0.53125,
|
| 789 |
+
"learning_rate": 0.0004551903357213092,
|
| 790 |
+
"loss": 1.3779,
|
| 791 |
+
"mean_token_accuracy": 0.6926328887231648,
|
| 792 |
+
"num_tokens": 150212801.0,
|
| 793 |
+
"step": 860
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.23710163688701902,
|
| 797 |
+
"grad_norm": 0.46484375,
|
| 798 |
+
"learning_rate": 0.00045448798988622,
|
| 799 |
+
"loss": 1.3138,
|
| 800 |
+
"mean_token_accuracy": 0.7013914404436946,
|
| 801 |
+
"num_tokens": 151950016.0,
|
| 802 |
+
"step": 870
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.23982694305813418,
|
| 806 |
+
"grad_norm": 0.46484375,
|
| 807 |
+
"learning_rate": 0.00045378564405113074,
|
| 808 |
+
"loss": 1.3262,
|
| 809 |
+
"mean_token_accuracy": 0.7006035029888154,
|
| 810 |
+
"num_tokens": 153686341.0,
|
| 811 |
+
"step": 880
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.24255224922924934,
|
| 815 |
+
"grad_norm": 0.46875,
|
| 816 |
+
"learning_rate": 0.0004530832982160416,
|
| 817 |
+
"loss": 1.3548,
|
| 818 |
+
"mean_token_accuracy": 0.694561337120831,
|
| 819 |
+
"num_tokens": 155442220.0,
|
| 820 |
+
"step": 890
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.2452775554003645,
|
| 824 |
+
"grad_norm": 0.44140625,
|
| 825 |
+
"learning_rate": 0.00045238095238095237,
|
| 826 |
+
"loss": 1.3115,
|
| 827 |
+
"mean_token_accuracy": 0.703803816344589,
|
| 828 |
+
"num_tokens": 157222278.0,
|
| 829 |
+
"step": 900
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.24800286157147966,
|
| 833 |
+
"grad_norm": 0.4609375,
|
| 834 |
+
"learning_rate": 0.0004516786065458632,
|
| 835 |
+
"loss": 1.311,
|
| 836 |
+
"mean_token_accuracy": 0.7028737253509462,
|
| 837 |
+
"num_tokens": 158989873.0,
|
| 838 |
+
"step": 910
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.2507281677425948,
|
| 842 |
+
"grad_norm": 0.46484375,
|
| 843 |
+
"learning_rate": 0.00045097626071077395,
|
| 844 |
+
"loss": 1.338,
|
| 845 |
+
"mean_token_accuracy": 0.700885118637234,
|
| 846 |
+
"num_tokens": 160740690.0,
|
| 847 |
+
"step": 920
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.25345347391371,
|
| 851 |
+
"grad_norm": 0.466796875,
|
| 852 |
+
"learning_rate": 0.0004502739148756848,
|
| 853 |
+
"loss": 1.3453,
|
| 854 |
+
"mean_token_accuracy": 0.6962541362270713,
|
| 855 |
+
"num_tokens": 162505210.0,
|
| 856 |
+
"step": 930
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.25617878008482514,
|
| 860 |
+
"grad_norm": 0.474609375,
|
| 861 |
+
"learning_rate": 0.0004495715690405956,
|
| 862 |
+
"loss": 1.3439,
|
| 863 |
+
"mean_token_accuracy": 0.6976133125834167,
|
| 864 |
+
"num_tokens": 164184119.0,
|
| 865 |
+
"step": 940
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.2589040862559403,
|
| 869 |
+
"grad_norm": 0.4609375,
|
| 870 |
+
"learning_rate": 0.0004488692232055064,
|
| 871 |
+
"loss": 1.296,
|
| 872 |
+
"mean_token_accuracy": 0.7053397912532091,
|
| 873 |
+
"num_tokens": 165971146.0,
|
| 874 |
+
"step": 950
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.26162939242705546,
|
| 878 |
+
"grad_norm": 0.45703125,
|
| 879 |
+
"learning_rate": 0.0004481668773704172,
|
| 880 |
+
"loss": 1.3388,
|
| 881 |
+
"mean_token_accuracy": 0.7005649470724166,
|
| 882 |
+
"num_tokens": 167701701.0,
|
| 883 |
+
"step": 960
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.2643546985981706,
|
| 887 |
+
"grad_norm": 0.53125,
|
| 888 |
+
"learning_rate": 0.000447464531535328,
|
| 889 |
+
"loss": 1.3452,
|
| 890 |
+
"mean_token_accuracy": 0.6994968581944704,
|
| 891 |
+
"num_tokens": 169443326.0,
|
| 892 |
+
"step": 970
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.2670800047692858,
|
| 896 |
+
"grad_norm": 0.431640625,
|
| 897 |
+
"learning_rate": 0.0004467621857002388,
|
| 898 |
+
"loss": 1.3342,
|
| 899 |
+
"mean_token_accuracy": 0.6998818466439843,
|
| 900 |
+
"num_tokens": 171199385.0,
|
| 901 |
+
"step": 980
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.26980531094040094,
|
| 905 |
+
"grad_norm": 0.45703125,
|
| 906 |
+
"learning_rate": 0.0004460598398651496,
|
| 907 |
+
"loss": 1.2848,
|
| 908 |
+
"mean_token_accuracy": 0.7084928262978792,
|
| 909 |
+
"num_tokens": 172929493.0,
|
| 910 |
+
"step": 990
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.2725306171115161,
|
| 914 |
+
"grad_norm": 0.67578125,
|
| 915 |
+
"learning_rate": 0.0004453574940300604,
|
| 916 |
+
"loss": 1.2857,
|
| 917 |
+
"mean_token_accuracy": 0.7073307786136865,
|
| 918 |
+
"num_tokens": 174672601.0,
|
| 919 |
+
"step": 1000
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.27525592328263127,
|
| 923 |
+
"grad_norm": 0.5234375,
|
| 924 |
+
"learning_rate": 0.00044465514819497123,
|
| 925 |
+
"loss": 1.3244,
|
| 926 |
+
"mean_token_accuracy": 0.7018027381040156,
|
| 927 |
+
"num_tokens": 176441962.0,
|
| 928 |
+
"step": 1010
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.2779812294537464,
|
| 932 |
+
"grad_norm": 0.55859375,
|
| 933 |
+
"learning_rate": 0.000443952802359882,
|
| 934 |
+
"loss": 1.2832,
|
| 935 |
+
"mean_token_accuracy": 0.7082092766650021,
|
| 936 |
+
"num_tokens": 178197361.0,
|
| 937 |
+
"step": 1020
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.2807065356248616,
|
| 941 |
+
"grad_norm": 0.50390625,
|
| 942 |
+
"learning_rate": 0.00044325045652479286,
|
| 943 |
+
"loss": 1.3295,
|
| 944 |
+
"mean_token_accuracy": 0.6989543081261218,
|
| 945 |
+
"num_tokens": 179887580.0,
|
| 946 |
+
"step": 1030
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.28343184179597675,
|
| 950 |
+
"grad_norm": 0.41796875,
|
| 951 |
+
"learning_rate": 0.0004425481106897036,
|
| 952 |
+
"loss": 1.2738,
|
| 953 |
+
"mean_token_accuracy": 0.7097910531796515,
|
| 954 |
+
"num_tokens": 181655865.0,
|
| 955 |
+
"step": 1040
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.2861571479670919,
|
| 959 |
+
"grad_norm": 0.4921875,
|
| 960 |
+
"learning_rate": 0.00044184576485461444,
|
| 961 |
+
"loss": 1.3083,
|
| 962 |
+
"mean_token_accuracy": 0.7053726987913251,
|
| 963 |
+
"num_tokens": 183445880.0,
|
| 964 |
+
"step": 1050
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.28888245413820707,
|
| 968 |
+
"grad_norm": 0.4296875,
|
| 969 |
+
"learning_rate": 0.0004411434190195252,
|
| 970 |
+
"loss": 1.2624,
|
| 971 |
+
"mean_token_accuracy": 0.7115490132942796,
|
| 972 |
+
"num_tokens": 185175706.0,
|
| 973 |
+
"step": 1060
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.29160776030932223,
|
| 977 |
+
"grad_norm": 0.498046875,
|
| 978 |
+
"learning_rate": 0.00044044107318443607,
|
| 979 |
+
"loss": 1.2847,
|
| 980 |
+
"mean_token_accuracy": 0.7070434625260532,
|
| 981 |
+
"num_tokens": 186873396.0,
|
| 982 |
+
"step": 1070
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.2943330664804374,
|
| 986 |
+
"grad_norm": 0.400390625,
|
| 987 |
+
"learning_rate": 0.00043973872734934683,
|
| 988 |
+
"loss": 1.3302,
|
| 989 |
+
"mean_token_accuracy": 0.6996699880808592,
|
| 990 |
+
"num_tokens": 188591288.0,
|
| 991 |
+
"step": 1080
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.29705837265155255,
|
| 995 |
+
"grad_norm": 0.4375,
|
| 996 |
+
"learning_rate": 0.00043903638151425765,
|
| 997 |
+
"loss": 1.318,
|
| 998 |
+
"mean_token_accuracy": 0.7020871014334261,
|
| 999 |
+
"num_tokens": 190375182.0,
|
| 1000 |
+
"step": 1090
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.2997836788226677,
|
| 1004 |
+
"grad_norm": 0.50390625,
|
| 1005 |
+
"learning_rate": 0.0004383340356791684,
|
| 1006 |
+
"loss": 1.2928,
|
| 1007 |
+
"mean_token_accuracy": 0.7056466254405678,
|
| 1008 |
+
"num_tokens": 192104609.0,
|
| 1009 |
+
"step": 1100
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.30250898499378287,
|
| 1013 |
+
"grad_norm": 0.4453125,
|
| 1014 |
+
"learning_rate": 0.0004376316898440792,
|
| 1015 |
+
"loss": 1.202,
|
| 1016 |
+
"mean_token_accuracy": 0.7222756736911833,
|
| 1017 |
+
"num_tokens": 193819768.0,
|
| 1018 |
+
"step": 1110
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.30523429116489803,
|
| 1022 |
+
"grad_norm": 0.439453125,
|
| 1023 |
+
"learning_rate": 0.00043692934400899004,
|
| 1024 |
+
"loss": 1.2824,
|
| 1025 |
+
"mean_token_accuracy": 0.7082328143529594,
|
| 1026 |
+
"num_tokens": 195541705.0,
|
| 1027 |
+
"step": 1120
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.3079595973360132,
|
| 1031 |
+
"grad_norm": 0.443359375,
|
| 1032 |
+
"learning_rate": 0.0004362269981739008,
|
| 1033 |
+
"loss": 1.2729,
|
| 1034 |
+
"mean_token_accuracy": 0.7094620336778462,
|
| 1035 |
+
"num_tokens": 197250976.0,
|
| 1036 |
+
"step": 1130
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.31068490350712835,
|
| 1040 |
+
"grad_norm": 0.388671875,
|
| 1041 |
+
"learning_rate": 0.00043552465233881167,
|
| 1042 |
+
"loss": 1.2343,
|
| 1043 |
+
"mean_token_accuracy": 0.7161834868602455,
|
| 1044 |
+
"num_tokens": 198964087.0,
|
| 1045 |
+
"step": 1140
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.31341020967824357,
|
| 1049 |
+
"grad_norm": 0.408203125,
|
| 1050 |
+
"learning_rate": 0.00043482230650372243,
|
| 1051 |
+
"loss": 1.2853,
|
| 1052 |
+
"mean_token_accuracy": 0.7067827261053026,
|
| 1053 |
+
"num_tokens": 200654341.0,
|
| 1054 |
+
"step": 1150
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.31613551584935873,
|
| 1058 |
+
"grad_norm": 0.470703125,
|
| 1059 |
+
"learning_rate": 0.00043411996066863325,
|
| 1060 |
+
"loss": 1.3217,
|
| 1061 |
+
"mean_token_accuracy": 0.7011503103189171,
|
| 1062 |
+
"num_tokens": 202410389.0,
|
| 1063 |
+
"step": 1160
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.3188608220204739,
|
| 1067 |
+
"grad_norm": 0.43359375,
|
| 1068 |
+
"learning_rate": 0.000433417614833544,
|
| 1069 |
+
"loss": 1.2703,
|
| 1070 |
+
"mean_token_accuracy": 0.710265371389687,
|
| 1071 |
+
"num_tokens": 204176073.0,
|
| 1072 |
+
"step": 1170
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.32158612819158905,
|
| 1076 |
+
"grad_norm": 0.41015625,
|
| 1077 |
+
"learning_rate": 0.0004327152689984549,
|
| 1078 |
+
"loss": 1.257,
|
| 1079 |
+
"mean_token_accuracy": 0.713060013204813,
|
| 1080 |
+
"num_tokens": 206017214.0,
|
| 1081 |
+
"step": 1180
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.3243114343627042,
|
| 1085 |
+
"grad_norm": 0.453125,
|
| 1086 |
+
"learning_rate": 0.00043201292316336564,
|
| 1087 |
+
"loss": 1.2758,
|
| 1088 |
+
"mean_token_accuracy": 0.7083034078590572,
|
| 1089 |
+
"num_tokens": 207832984.0,
|
| 1090 |
+
"step": 1190
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.32703674053381937,
|
| 1094 |
+
"grad_norm": 0.421875,
|
| 1095 |
+
"learning_rate": 0.00043131057732827646,
|
| 1096 |
+
"loss": 1.2757,
|
| 1097 |
+
"mean_token_accuracy": 0.7085663201287389,
|
| 1098 |
+
"num_tokens": 209533427.0,
|
| 1099 |
+
"step": 1200
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.32976204670493453,
|
| 1103 |
+
"grad_norm": 0.443359375,
|
| 1104 |
+
"learning_rate": 0.0004306082314931872,
|
| 1105 |
+
"loss": 1.2609,
|
| 1106 |
+
"mean_token_accuracy": 0.7120108696632087,
|
| 1107 |
+
"num_tokens": 211344332.0,
|
| 1108 |
+
"step": 1210
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.3324873528760497,
|
| 1112 |
+
"grad_norm": 0.474609375,
|
| 1113 |
+
"learning_rate": 0.0004299058856580981,
|
| 1114 |
+
"loss": 1.2847,
|
| 1115 |
+
"mean_token_accuracy": 0.7070382171310484,
|
| 1116 |
+
"num_tokens": 213088746.0,
|
| 1117 |
+
"step": 1220
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.33521265904716485,
|
| 1121 |
+
"grad_norm": 0.4609375,
|
| 1122 |
+
"learning_rate": 0.00042920353982300885,
|
| 1123 |
+
"loss": 1.2914,
|
| 1124 |
+
"mean_token_accuracy": 0.7046342886984348,
|
| 1125 |
+
"num_tokens": 214889528.0,
|
| 1126 |
+
"step": 1230
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.33793796521828,
|
| 1130 |
+
"grad_norm": 0.515625,
|
| 1131 |
+
"learning_rate": 0.00042850119398791966,
|
| 1132 |
+
"loss": 1.318,
|
| 1133 |
+
"mean_token_accuracy": 0.7027574786916375,
|
| 1134 |
+
"num_tokens": 216603081.0,
|
| 1135 |
+
"step": 1240
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.3406632713893952,
|
| 1139 |
+
"grad_norm": 0.400390625,
|
| 1140 |
+
"learning_rate": 0.0004277988481528305,
|
| 1141 |
+
"loss": 1.2342,
|
| 1142 |
+
"mean_token_accuracy": 0.7151992056518793,
|
| 1143 |
+
"num_tokens": 218292845.0,
|
| 1144 |
+
"step": 1250
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.34338857756051033,
|
| 1148 |
+
"grad_norm": 0.466796875,
|
| 1149 |
+
"learning_rate": 0.0004270965023177413,
|
| 1150 |
+
"loss": 1.273,
|
| 1151 |
+
"mean_token_accuracy": 0.7111638378351927,
|
| 1152 |
+
"num_tokens": 220029696.0,
|
| 1153 |
+
"step": 1260
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.3461138837316255,
|
| 1157 |
+
"grad_norm": 0.419921875,
|
| 1158 |
+
"learning_rate": 0.00042639415648265206,
|
| 1159 |
+
"loss": 1.3345,
|
| 1160 |
+
"mean_token_accuracy": 0.699883119482547,
|
| 1161 |
+
"num_tokens": 221810553.0,
|
| 1162 |
+
"step": 1270
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.34883918990274065,
|
| 1166 |
+
"grad_norm": 0.435546875,
|
| 1167 |
+
"learning_rate": 0.00042569181064756287,
|
| 1168 |
+
"loss": 1.2527,
|
| 1169 |
+
"mean_token_accuracy": 0.7150985508225858,
|
| 1170 |
+
"num_tokens": 223552801.0,
|
| 1171 |
+
"step": 1280
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.3515644960738558,
|
| 1175 |
+
"grad_norm": 0.43359375,
|
| 1176 |
+
"learning_rate": 0.0004249894648124737,
|
| 1177 |
+
"loss": 1.2599,
|
| 1178 |
+
"mean_token_accuracy": 0.7120441010221839,
|
| 1179 |
+
"num_tokens": 225254929.0,
|
| 1180 |
+
"step": 1290
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.354289802244971,
|
| 1184 |
+
"grad_norm": 0.49609375,
|
| 1185 |
+
"learning_rate": 0.0004242871189773845,
|
| 1186 |
+
"loss": 1.2961,
|
| 1187 |
+
"mean_token_accuracy": 0.7060732362791896,
|
| 1188 |
+
"num_tokens": 227017304.0,
|
| 1189 |
+
"step": 1300
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.35701510841608614,
|
| 1193 |
+
"grad_norm": 0.50390625,
|
| 1194 |
+
"learning_rate": 0.00042358477314229526,
|
| 1195 |
+
"loss": 1.2191,
|
| 1196 |
+
"mean_token_accuracy": 0.7194700758904219,
|
| 1197 |
+
"num_tokens": 228785771.0,
|
| 1198 |
+
"step": 1310
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.3597404145872013,
|
| 1202 |
+
"grad_norm": 0.3828125,
|
| 1203 |
+
"learning_rate": 0.0004228824273072061,
|
| 1204 |
+
"loss": 1.2231,
|
| 1205 |
+
"mean_token_accuracy": 0.7179213220253586,
|
| 1206 |
+
"num_tokens": 230489667.0,
|
| 1207 |
+
"step": 1320
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.36246572075831646,
|
| 1211 |
+
"grad_norm": 0.408203125,
|
| 1212 |
+
"learning_rate": 0.0004221800814721169,
|
| 1213 |
+
"loss": 1.2519,
|
| 1214 |
+
"mean_token_accuracy": 0.7132132126018405,
|
| 1215 |
+
"num_tokens": 232269581.0,
|
| 1216 |
+
"step": 1330
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.3651910269294316,
|
| 1220 |
+
"grad_norm": 0.42578125,
|
| 1221 |
+
"learning_rate": 0.00042147773563702766,
|
| 1222 |
+
"loss": 1.2605,
|
| 1223 |
+
"mean_token_accuracy": 0.7092904560267925,
|
| 1224 |
+
"num_tokens": 234028126.0,
|
| 1225 |
+
"step": 1340
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.3679163331005468,
|
| 1229 |
+
"grad_norm": 0.53515625,
|
| 1230 |
+
"learning_rate": 0.00042077538980193847,
|
| 1231 |
+
"loss": 1.2882,
|
| 1232 |
+
"mean_token_accuracy": 0.7081171317026019,
|
| 1233 |
+
"num_tokens": 235817129.0,
|
| 1234 |
+
"step": 1350
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.37064163927166194,
|
| 1238 |
+
"grad_norm": 0.40625,
|
| 1239 |
+
"learning_rate": 0.0004200730439668493,
|
| 1240 |
+
"loss": 1.2574,
|
| 1241 |
+
"mean_token_accuracy": 0.7129102074541152,
|
| 1242 |
+
"num_tokens": 237588984.0,
|
| 1243 |
+
"step": 1360
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.3733669454427771,
|
| 1247 |
+
"grad_norm": 0.44921875,
|
| 1248 |
+
"learning_rate": 0.0004193706981317601,
|
| 1249 |
+
"loss": 1.2072,
|
| 1250 |
+
"mean_token_accuracy": 0.7199260313995183,
|
| 1251 |
+
"num_tokens": 239305200.0,
|
| 1252 |
+
"step": 1370
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.37609225161389226,
|
| 1256 |
+
"grad_norm": 0.396484375,
|
| 1257 |
+
"learning_rate": 0.00041866835229667086,
|
| 1258 |
+
"loss": 1.2353,
|
| 1259 |
+
"mean_token_accuracy": 0.7163059611804783,
|
| 1260 |
+
"num_tokens": 241078759.0,
|
| 1261 |
+
"step": 1380
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.3788175577850074,
|
| 1265 |
+
"grad_norm": 0.4453125,
|
| 1266 |
+
"learning_rate": 0.0004179660064615817,
|
| 1267 |
+
"loss": 1.2712,
|
| 1268 |
+
"mean_token_accuracy": 0.7112471625208855,
|
| 1269 |
+
"num_tokens": 242876841.0,
|
| 1270 |
+
"step": 1390
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.3815428639561226,
|
| 1274 |
+
"grad_norm": 0.40234375,
|
| 1275 |
+
"learning_rate": 0.0004172636606264925,
|
| 1276 |
+
"loss": 1.2176,
|
| 1277 |
+
"mean_token_accuracy": 0.7165075090713799,
|
| 1278 |
+
"num_tokens": 244578724.0,
|
| 1279 |
+
"step": 1400
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.38426817012723774,
|
| 1283 |
+
"grad_norm": 0.400390625,
|
| 1284 |
+
"learning_rate": 0.0004165613147914033,
|
| 1285 |
+
"loss": 1.2526,
|
| 1286 |
+
"mean_token_accuracy": 0.7108958872035146,
|
| 1287 |
+
"num_tokens": 246363009.0,
|
| 1288 |
+
"step": 1410
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.3869934762983529,
|
| 1292 |
+
"grad_norm": 0.431640625,
|
| 1293 |
+
"learning_rate": 0.00041585896895631407,
|
| 1294 |
+
"loss": 1.293,
|
| 1295 |
+
"mean_token_accuracy": 0.7064874111674726,
|
| 1296 |
+
"num_tokens": 248120613.0,
|
| 1297 |
+
"step": 1420
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.38971878246946806,
|
| 1301 |
+
"grad_norm": 0.42578125,
|
| 1302 |
+
"learning_rate": 0.0004151566231212249,
|
| 1303 |
+
"loss": 1.2606,
|
| 1304 |
+
"mean_token_accuracy": 0.7118613218888641,
|
| 1305 |
+
"num_tokens": 249941867.0,
|
| 1306 |
+
"step": 1430
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.3924440886405832,
|
| 1310 |
+
"grad_norm": 0.373046875,
|
| 1311 |
+
"learning_rate": 0.0004144542772861357,
|
| 1312 |
+
"loss": 1.2136,
|
| 1313 |
+
"mean_token_accuracy": 0.7203867037780582,
|
| 1314 |
+
"num_tokens": 251695734.0,
|
| 1315 |
+
"step": 1440
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.3951693948116984,
|
| 1319 |
+
"grad_norm": 0.388671875,
|
| 1320 |
+
"learning_rate": 0.0004137519314510465,
|
| 1321 |
+
"loss": 1.2663,
|
| 1322 |
+
"mean_token_accuracy": 0.7106507356278599,
|
| 1323 |
+
"num_tokens": 253503211.0,
|
| 1324 |
+
"step": 1450
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 0.39789470098281354,
|
| 1328 |
+
"grad_norm": 0.4296875,
|
| 1329 |
+
"learning_rate": 0.0004130495856159573,
|
| 1330 |
+
"loss": 1.2482,
|
| 1331 |
+
"mean_token_accuracy": 0.7142273456789553,
|
| 1332 |
+
"num_tokens": 255313734.0,
|
| 1333 |
+
"step": 1460
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.4006200071539287,
|
| 1337 |
+
"grad_norm": 0.3671875,
|
| 1338 |
+
"learning_rate": 0.00041234723978086815,
|
| 1339 |
+
"loss": 1.1809,
|
| 1340 |
+
"mean_token_accuracy": 0.7257948698475957,
|
| 1341 |
+
"num_tokens": 257016513.0,
|
| 1342 |
+
"step": 1470
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.40334531332504386,
|
| 1346 |
+
"grad_norm": 0.412109375,
|
| 1347 |
+
"learning_rate": 0.0004116448939457789,
|
| 1348 |
+
"loss": 1.2676,
|
| 1349 |
+
"mean_token_accuracy": 0.7092947035096586,
|
| 1350 |
+
"num_tokens": 258760362.0,
|
| 1351 |
+
"step": 1480
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 0.406070619496159,
|
| 1355 |
+
"grad_norm": 0.427734375,
|
| 1356 |
+
"learning_rate": 0.0004109425481106897,
|
| 1357 |
+
"loss": 1.2095,
|
| 1358 |
+
"mean_token_accuracy": 0.7201486421748996,
|
| 1359 |
+
"num_tokens": 260546971.0,
|
| 1360 |
+
"step": 1490
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.4087959256672742,
|
| 1364 |
+
"grad_norm": 0.431640625,
|
| 1365 |
+
"learning_rate": 0.0004102402022756005,
|
| 1366 |
+
"loss": 1.2297,
|
| 1367 |
+
"mean_token_accuracy": 0.7155070326291024,
|
| 1368 |
+
"num_tokens": 262307672.0,
|
| 1369 |
+
"step": 1500
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 0.41152123183838935,
|
| 1373 |
+
"grad_norm": 0.427734375,
|
| 1374 |
+
"learning_rate": 0.00040953785644051136,
|
| 1375 |
+
"loss": 1.2367,
|
| 1376 |
+
"mean_token_accuracy": 0.7149525980465115,
|
| 1377 |
+
"num_tokens": 264023889.0,
|
| 1378 |
+
"step": 1510
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.4142465380095045,
|
| 1382 |
+
"grad_norm": 0.4296875,
|
| 1383 |
+
"learning_rate": 0.0004088355106054221,
|
| 1384 |
+
"loss": 1.2325,
|
| 1385 |
+
"mean_token_accuracy": 0.7151728126220405,
|
| 1386 |
+
"num_tokens": 265798519.0,
|
| 1387 |
+
"step": 1520
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.41697184418061967,
|
| 1391 |
+
"grad_norm": 0.396484375,
|
| 1392 |
+
"learning_rate": 0.00040813316477033293,
|
| 1393 |
+
"loss": 1.2632,
|
| 1394 |
+
"mean_token_accuracy": 0.710959506034851,
|
| 1395 |
+
"num_tokens": 267546100.0,
|
| 1396 |
+
"step": 1530
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.4196971503517348,
|
| 1400 |
+
"grad_norm": 0.404296875,
|
| 1401 |
+
"learning_rate": 0.0004074308189352437,
|
| 1402 |
+
"loss": 1.2144,
|
| 1403 |
+
"mean_token_accuracy": 0.7181764165870845,
|
| 1404 |
+
"num_tokens": 269297641.0,
|
| 1405 |
+
"step": 1540
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.42242245652285,
|
| 1409 |
+
"grad_norm": 0.3984375,
|
| 1410 |
+
"learning_rate": 0.00040672847310015456,
|
| 1411 |
+
"loss": 1.261,
|
| 1412 |
+
"mean_token_accuracy": 0.710538933891803,
|
| 1413 |
+
"num_tokens": 271053006.0,
|
| 1414 |
+
"step": 1550
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.42514776269396515,
|
| 1418 |
+
"grad_norm": 0.44140625,
|
| 1419 |
+
"learning_rate": 0.0004060261272650653,
|
| 1420 |
+
"loss": 1.2391,
|
| 1421 |
+
"mean_token_accuracy": 0.7155305192805826,
|
| 1422 |
+
"num_tokens": 272829487.0,
|
| 1423 |
+
"step": 1560
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.4278730688650803,
|
| 1427 |
+
"grad_norm": 0.404296875,
|
| 1428 |
+
"learning_rate": 0.0004053237814299761,
|
| 1429 |
+
"loss": 1.2266,
|
| 1430 |
+
"mean_token_accuracy": 0.7166890133172273,
|
| 1431 |
+
"num_tokens": 274621990.0,
|
| 1432 |
+
"step": 1570
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 0.43059837503619547,
|
| 1436 |
+
"grad_norm": 0.396484375,
|
| 1437 |
+
"learning_rate": 0.00040462143559488696,
|
| 1438 |
+
"loss": 1.2463,
|
| 1439 |
+
"mean_token_accuracy": 0.7121757534332573,
|
| 1440 |
+
"num_tokens": 276398989.0,
|
| 1441 |
+
"step": 1580
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.43332368120731063,
|
| 1445 |
+
"grad_norm": 0.388671875,
|
| 1446 |
+
"learning_rate": 0.0004039190897597977,
|
| 1447 |
+
"loss": 1.2152,
|
| 1448 |
+
"mean_token_accuracy": 0.7180015265010298,
|
| 1449 |
+
"num_tokens": 278192884.0,
|
| 1450 |
+
"step": 1590
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.4360489873784258,
|
| 1454 |
+
"grad_norm": 0.421875,
|
| 1455 |
+
"learning_rate": 0.00040321674392470853,
|
| 1456 |
+
"loss": 1.204,
|
| 1457 |
+
"mean_token_accuracy": 0.7211478114128113,
|
| 1458 |
+
"num_tokens": 279937931.0,
|
| 1459 |
+
"step": 1600
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.43877429354954095,
|
| 1463 |
+
"grad_norm": 0.375,
|
| 1464 |
+
"learning_rate": 0.0004025143980896193,
|
| 1465 |
+
"loss": 1.2067,
|
| 1466 |
+
"mean_token_accuracy": 0.7212561624124646,
|
| 1467 |
+
"num_tokens": 281698143.0,
|
| 1468 |
+
"step": 1610
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 0.4414995997206561,
|
| 1472 |
+
"grad_norm": 0.412109375,
|
| 1473 |
+
"learning_rate": 0.00040181205225453017,
|
| 1474 |
+
"loss": 1.2264,
|
| 1475 |
+
"mean_token_accuracy": 0.7175595877692104,
|
| 1476 |
+
"num_tokens": 283412565.0,
|
| 1477 |
+
"step": 1620
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.44422490589177127,
|
| 1481 |
+
"grad_norm": 0.39453125,
|
| 1482 |
+
"learning_rate": 0.0004011097064194409,
|
| 1483 |
+
"loss": 1.2273,
|
| 1484 |
+
"mean_token_accuracy": 0.7161778485402465,
|
| 1485 |
+
"num_tokens": 285184244.0,
|
| 1486 |
+
"step": 1630
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.44695021206288643,
|
| 1490 |
+
"grad_norm": 0.380859375,
|
| 1491 |
+
"learning_rate": 0.00040040736058435174,
|
| 1492 |
+
"loss": 1.1504,
|
| 1493 |
+
"mean_token_accuracy": 0.7301577464677393,
|
| 1494 |
+
"num_tokens": 286963226.0,
|
| 1495 |
+
"step": 1640
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.4496755182340016,
|
| 1499 |
+
"grad_norm": 0.404296875,
|
| 1500 |
+
"learning_rate": 0.0003997050147492625,
|
| 1501 |
+
"loss": 1.1838,
|
| 1502 |
+
"mean_token_accuracy": 0.7249205836094916,
|
| 1503 |
+
"num_tokens": 288742524.0,
|
| 1504 |
+
"step": 1650
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.45240082440511675,
|
| 1508 |
+
"grad_norm": 0.44921875,
|
| 1509 |
+
"learning_rate": 0.00039900266891417337,
|
| 1510 |
+
"loss": 1.2179,
|
| 1511 |
+
"mean_token_accuracy": 0.71893819719553,
|
| 1512 |
+
"num_tokens": 290486439.0,
|
| 1513 |
+
"step": 1660
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.4551261305762319,
|
| 1517 |
+
"grad_norm": 0.421875,
|
| 1518 |
+
"learning_rate": 0.00039830032307908413,
|
| 1519 |
+
"loss": 1.2206,
|
| 1520 |
+
"mean_token_accuracy": 0.7182010743767023,
|
| 1521 |
+
"num_tokens": 292244616.0,
|
| 1522 |
+
"step": 1670
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.4578514367473471,
|
| 1526 |
+
"grad_norm": 0.376953125,
|
| 1527 |
+
"learning_rate": 0.00039759797724399495,
|
| 1528 |
+
"loss": 1.2252,
|
| 1529 |
+
"mean_token_accuracy": 0.7172848870046437,
|
| 1530 |
+
"num_tokens": 294028863.0,
|
| 1531 |
+
"step": 1680
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.46057674291846223,
|
| 1535 |
+
"grad_norm": 0.408203125,
|
| 1536 |
+
"learning_rate": 0.00039689563140890577,
|
| 1537 |
+
"loss": 1.1818,
|
| 1538 |
+
"mean_token_accuracy": 0.723115173354745,
|
| 1539 |
+
"num_tokens": 295842660.0,
|
| 1540 |
+
"step": 1690
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.4633020490895774,
|
| 1544 |
+
"grad_norm": 0.353515625,
|
| 1545 |
+
"learning_rate": 0.0003961932855738166,
|
| 1546 |
+
"loss": 1.1913,
|
| 1547 |
+
"mean_token_accuracy": 0.7237382984720171,
|
| 1548 |
+
"num_tokens": 297606076.0,
|
| 1549 |
+
"step": 1700
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.46602735526069256,
|
| 1553 |
+
"grad_norm": 0.490234375,
|
| 1554 |
+
"learning_rate": 0.00039549093973872734,
|
| 1555 |
+
"loss": 1.2381,
|
| 1556 |
+
"mean_token_accuracy": 0.714545346237719,
|
| 1557 |
+
"num_tokens": 299367632.0,
|
| 1558 |
+
"step": 1710
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.4687526614318077,
|
| 1562 |
+
"grad_norm": 0.421875,
|
| 1563 |
+
"learning_rate": 0.00039478859390363816,
|
| 1564 |
+
"loss": 1.1702,
|
| 1565 |
+
"mean_token_accuracy": 0.7281134461984038,
|
| 1566 |
+
"num_tokens": 301097990.0,
|
| 1567 |
+
"step": 1720
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.4714779676029229,
|
| 1571 |
+
"grad_norm": 0.431640625,
|
| 1572 |
+
"learning_rate": 0.000394086248068549,
|
| 1573 |
+
"loss": 1.1872,
|
| 1574 |
+
"mean_token_accuracy": 0.7246512384153903,
|
| 1575 |
+
"num_tokens": 302847308.0,
|
| 1576 |
+
"step": 1730
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 0.47420327377403804,
|
| 1580 |
+
"grad_norm": 0.421875,
|
| 1581 |
+
"learning_rate": 0.0003933839022334598,
|
| 1582 |
+
"loss": 1.2085,
|
| 1583 |
+
"mean_token_accuracy": 0.7196571965701878,
|
| 1584 |
+
"num_tokens": 304582625.0,
|
| 1585 |
+
"step": 1740
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4769285799451532,
|
| 1589 |
+
"grad_norm": 0.44140625,
|
| 1590 |
+
"learning_rate": 0.00039268155639837055,
|
| 1591 |
+
"loss": 1.1827,
|
| 1592 |
+
"mean_token_accuracy": 0.7259564273059368,
|
| 1593 |
+
"num_tokens": 306358206.0,
|
| 1594 |
+
"step": 1750
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.47965388611626836,
|
| 1598 |
+
"grad_norm": 0.40234375,
|
| 1599 |
+
"learning_rate": 0.00039197921056328137,
|
| 1600 |
+
"loss": 1.1772,
|
| 1601 |
+
"mean_token_accuracy": 0.7265206996351481,
|
| 1602 |
+
"num_tokens": 308026562.0,
|
| 1603 |
+
"step": 1760
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.4823791922873835,
|
| 1607 |
+
"grad_norm": 0.57421875,
|
| 1608 |
+
"learning_rate": 0.0003912768647281922,
|
| 1609 |
+
"loss": 1.2166,
|
| 1610 |
+
"mean_token_accuracy": 0.7178250108845532,
|
| 1611 |
+
"num_tokens": 309804543.0,
|
| 1612 |
+
"step": 1770
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.4851044984584987,
|
| 1616 |
+
"grad_norm": 0.40625,
|
| 1617 |
+
"learning_rate": 0.000390574518893103,
|
| 1618 |
+
"loss": 1.214,
|
| 1619 |
+
"mean_token_accuracy": 0.7180218786001206,
|
| 1620 |
+
"num_tokens": 311549771.0,
|
| 1621 |
+
"step": 1780
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.48782980462961384,
|
| 1625 |
+
"grad_norm": 0.455078125,
|
| 1626 |
+
"learning_rate": 0.00038987217305801376,
|
| 1627 |
+
"loss": 1.2368,
|
| 1628 |
+
"mean_token_accuracy": 0.7157372819259763,
|
| 1629 |
+
"num_tokens": 313326889.0,
|
| 1630 |
+
"step": 1790
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 0.490555110800729,
|
| 1634 |
+
"grad_norm": 0.384765625,
|
| 1635 |
+
"learning_rate": 0.0003891698272229246,
|
| 1636 |
+
"loss": 1.1708,
|
| 1637 |
+
"mean_token_accuracy": 0.7274354211986065,
|
| 1638 |
+
"num_tokens": 315064715.0,
|
| 1639 |
+
"step": 1800
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.49328041697184416,
|
| 1643 |
+
"grad_norm": 0.376953125,
|
| 1644 |
+
"learning_rate": 0.0003884674813878354,
|
| 1645 |
+
"loss": 1.1907,
|
| 1646 |
+
"mean_token_accuracy": 0.7222747911699117,
|
| 1647 |
+
"num_tokens": 316809509.0,
|
| 1648 |
+
"step": 1810
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4960057231429593,
|
| 1652 |
+
"grad_norm": 0.40234375,
|
| 1653 |
+
"learning_rate": 0.00038776513555274615,
|
| 1654 |
+
"loss": 1.1724,
|
| 1655 |
+
"mean_token_accuracy": 0.7267968454398215,
|
| 1656 |
+
"num_tokens": 318597481.0,
|
| 1657 |
+
"step": 1820
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.4987310293140745,
|
| 1661 |
+
"grad_norm": 0.796875,
|
| 1662 |
+
"learning_rate": 0.00038706278971765697,
|
| 1663 |
+
"loss": 1.1559,
|
| 1664 |
+
"mean_token_accuracy": 0.7283987457863986,
|
| 1665 |
+
"num_tokens": 320382863.0,
|
| 1666 |
+
"step": 1830
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.5014563354851896,
|
| 1670 |
+
"grad_norm": 0.37109375,
|
| 1671 |
+
"learning_rate": 0.0003863604438825678,
|
| 1672 |
+
"loss": 1.1879,
|
| 1673 |
+
"mean_token_accuracy": 0.724396638572216,
|
| 1674 |
+
"num_tokens": 322136431.0,
|
| 1675 |
+
"step": 1840
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5041816416563049,
|
| 1679 |
+
"grad_norm": 0.380859375,
|
| 1680 |
+
"learning_rate": 0.0003856580980474786,
|
| 1681 |
+
"loss": 1.1686,
|
| 1682 |
+
"mean_token_accuracy": 0.7275835652835667,
|
| 1683 |
+
"num_tokens": 323892089.0,
|
| 1684 |
+
"step": 1850
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.50690694782742,
|
| 1688 |
+
"grad_norm": 0.376953125,
|
| 1689 |
+
"learning_rate": 0.00038495575221238936,
|
| 1690 |
+
"loss": 1.1808,
|
| 1691 |
+
"mean_token_accuracy": 0.7243333254009485,
|
| 1692 |
+
"num_tokens": 325693457.0,
|
| 1693 |
+
"step": 1860
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.5096322539985352,
|
| 1697 |
+
"grad_norm": 0.419921875,
|
| 1698 |
+
"learning_rate": 0.0003842534063773002,
|
| 1699 |
+
"loss": 1.1474,
|
| 1700 |
+
"mean_token_accuracy": 0.7292418093420565,
|
| 1701 |
+
"num_tokens": 327397884.0,
|
| 1702 |
+
"step": 1870
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 0.5123575601696503,
|
| 1706 |
+
"grad_norm": 0.4140625,
|
| 1707 |
+
"learning_rate": 0.000383551060542211,
|
| 1708 |
+
"loss": 1.2087,
|
| 1709 |
+
"mean_token_accuracy": 0.7199928862042725,
|
| 1710 |
+
"num_tokens": 329077502.0,
|
| 1711 |
+
"step": 1880
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.5150828663407655,
|
| 1715 |
+
"grad_norm": 0.38671875,
|
| 1716 |
+
"learning_rate": 0.0003828487147071218,
|
| 1717 |
+
"loss": 1.1952,
|
| 1718 |
+
"mean_token_accuracy": 0.7225228334777057,
|
| 1719 |
+
"num_tokens": 330847695.0,
|
| 1720 |
+
"step": 1890
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 0.5178081725118806,
|
| 1724 |
+
"grad_norm": 0.400390625,
|
| 1725 |
+
"learning_rate": 0.00038214636887203257,
|
| 1726 |
+
"loss": 1.1591,
|
| 1727 |
+
"mean_token_accuracy": 0.7250943325459958,
|
| 1728 |
+
"num_tokens": 332578366.0,
|
| 1729 |
+
"step": 1900
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.5205334786829958,
|
| 1733 |
+
"grad_norm": 0.423828125,
|
| 1734 |
+
"learning_rate": 0.00038144402303694344,
|
| 1735 |
+
"loss": 1.1994,
|
| 1736 |
+
"mean_token_accuracy": 0.7206506300717592,
|
| 1737 |
+
"num_tokens": 334293589.0,
|
| 1738 |
+
"step": 1910
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.5232587848541109,
|
| 1742 |
+
"grad_norm": 0.37109375,
|
| 1743 |
+
"learning_rate": 0.0003807416772018542,
|
| 1744 |
+
"loss": 1.1841,
|
| 1745 |
+
"mean_token_accuracy": 0.7210906410589815,
|
| 1746 |
+
"num_tokens": 336016972.0,
|
| 1747 |
+
"step": 1920
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.5259840910252261,
|
| 1751 |
+
"grad_norm": 0.357421875,
|
| 1752 |
+
"learning_rate": 0.000380039331366765,
|
| 1753 |
+
"loss": 1.1503,
|
| 1754 |
+
"mean_token_accuracy": 0.7291983521543444,
|
| 1755 |
+
"num_tokens": 337805977.0,
|
| 1756 |
+
"step": 1930
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.5287093971963412,
|
| 1760 |
+
"grad_norm": 0.3515625,
|
| 1761 |
+
"learning_rate": 0.0003793369855316758,
|
| 1762 |
+
"loss": 1.1218,
|
| 1763 |
+
"mean_token_accuracy": 0.7343028046190738,
|
| 1764 |
+
"num_tokens": 339548221.0,
|
| 1765 |
+
"step": 1940
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.5314347033674565,
|
| 1769 |
+
"grad_norm": 0.38671875,
|
| 1770 |
+
"learning_rate": 0.00037863463969658664,
|
| 1771 |
+
"loss": 1.2138,
|
| 1772 |
+
"mean_token_accuracy": 0.7172385750338435,
|
| 1773 |
+
"num_tokens": 341268344.0,
|
| 1774 |
+
"step": 1950
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.5341600095385716,
|
| 1778 |
+
"grad_norm": 0.396484375,
|
| 1779 |
+
"learning_rate": 0.0003779322938614974,
|
| 1780 |
+
"loss": 1.1792,
|
| 1781 |
+
"mean_token_accuracy": 0.724903620686382,
|
| 1782 |
+
"num_tokens": 343017522.0,
|
| 1783 |
+
"step": 1960
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 0.5368853157096868,
|
| 1787 |
+
"grad_norm": 0.400390625,
|
| 1788 |
+
"learning_rate": 0.0003772299480264082,
|
| 1789 |
+
"loss": 1.1665,
|
| 1790 |
+
"mean_token_accuracy": 0.7268314240500331,
|
| 1791 |
+
"num_tokens": 344699192.0,
|
| 1792 |
+
"step": 1970
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.5396106218808019,
|
| 1796 |
+
"grad_norm": 0.37109375,
|
| 1797 |
+
"learning_rate": 0.00037652760219131904,
|
| 1798 |
+
"loss": 1.143,
|
| 1799 |
+
"mean_token_accuracy": 0.7308998920954763,
|
| 1800 |
+
"num_tokens": 346458527.0,
|
| 1801 |
+
"step": 1980
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.5423359280519171,
|
| 1805 |
+
"grad_norm": 0.396484375,
|
| 1806 |
+
"learning_rate": 0.00037582525635622985,
|
| 1807 |
+
"loss": 1.1795,
|
| 1808 |
+
"mean_token_accuracy": 0.7253339084796607,
|
| 1809 |
+
"num_tokens": 348204585.0,
|
| 1810 |
+
"step": 1990
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.5450612342230322,
|
| 1814 |
+
"grad_norm": 0.388671875,
|
| 1815 |
+
"learning_rate": 0.0003751229105211406,
|
| 1816 |
+
"loss": 1.1936,
|
| 1817 |
+
"mean_token_accuracy": 0.7219026086851954,
|
| 1818 |
+
"num_tokens": 349928259.0,
|
| 1819 |
+
"step": 2000
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 0.5477865403941474,
|
| 1823 |
+
"grad_norm": 0.36328125,
|
| 1824 |
+
"learning_rate": 0.00037442056468605143,
|
| 1825 |
+
"loss": 1.1629,
|
| 1826 |
+
"mean_token_accuracy": 0.7267959822900594,
|
| 1827 |
+
"num_tokens": 351568018.0,
|
| 1828 |
+
"step": 2010
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.5505118465652625,
|
| 1832 |
+
"grad_norm": 0.373046875,
|
| 1833 |
+
"learning_rate": 0.00037371821885096224,
|
| 1834 |
+
"loss": 1.1492,
|
| 1835 |
+
"mean_token_accuracy": 0.7309575733728707,
|
| 1836 |
+
"num_tokens": 353325716.0,
|
| 1837 |
+
"step": 2020
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.5532371527363777,
|
| 1841 |
+
"grad_norm": 0.37890625,
|
| 1842 |
+
"learning_rate": 0.000373015873015873,
|
| 1843 |
+
"loss": 1.1898,
|
| 1844 |
+
"mean_token_accuracy": 0.7220692792907357,
|
| 1845 |
+
"num_tokens": 355099655.0,
|
| 1846 |
+
"step": 2030
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 0.5559624589074929,
|
| 1850 |
+
"grad_norm": 0.373046875,
|
| 1851 |
+
"learning_rate": 0.0003723135271807838,
|
| 1852 |
+
"loss": 1.159,
|
| 1853 |
+
"mean_token_accuracy": 0.7283659107983113,
|
| 1854 |
+
"num_tokens": 356892448.0,
|
| 1855 |
+
"step": 2040
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 0.5586877650786081,
|
| 1859 |
+
"grad_norm": 0.41015625,
|
| 1860 |
+
"learning_rate": 0.0003716111813456946,
|
| 1861 |
+
"loss": 1.1855,
|
| 1862 |
+
"mean_token_accuracy": 0.7233272660523653,
|
| 1863 |
+
"num_tokens": 358599855.0,
|
| 1864 |
+
"step": 2050
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.5614130712497232,
|
| 1868 |
+
"grad_norm": 0.384765625,
|
| 1869 |
+
"learning_rate": 0.00037090883551060545,
|
| 1870 |
+
"loss": 1.2008,
|
| 1871 |
+
"mean_token_accuracy": 0.7202940073795616,
|
| 1872 |
+
"num_tokens": 360366528.0,
|
| 1873 |
+
"step": 2060
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.5641383774208384,
|
| 1877 |
+
"grad_norm": 0.396484375,
|
| 1878 |
+
"learning_rate": 0.0003702064896755162,
|
| 1879 |
+
"loss": 1.1701,
|
| 1880 |
+
"mean_token_accuracy": 0.7270756110548973,
|
| 1881 |
+
"num_tokens": 362123903.0,
|
| 1882 |
+
"step": 2070
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.5668636835919535,
|
| 1886 |
+
"grad_norm": 0.3671875,
|
| 1887 |
+
"learning_rate": 0.00036950414384042703,
|
| 1888 |
+
"loss": 1.145,
|
| 1889 |
+
"mean_token_accuracy": 0.732559056673199,
|
| 1890 |
+
"num_tokens": 363907270.0,
|
| 1891 |
+
"step": 2080
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.5695889897630687,
|
| 1895 |
+
"grad_norm": 0.416015625,
|
| 1896 |
+
"learning_rate": 0.00036880179800533784,
|
| 1897 |
+
"loss": 1.1266,
|
| 1898 |
+
"mean_token_accuracy": 0.7330201560631394,
|
| 1899 |
+
"num_tokens": 365602883.0,
|
| 1900 |
+
"step": 2090
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.5723142959341838,
|
| 1904 |
+
"grad_norm": 0.419921875,
|
| 1905 |
+
"learning_rate": 0.00036809945217024866,
|
| 1906 |
+
"loss": 1.1442,
|
| 1907 |
+
"mean_token_accuracy": 0.7297326970845461,
|
| 1908 |
+
"num_tokens": 367308921.0,
|
| 1909 |
+
"step": 2100
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 0.575039602105299,
|
| 1913 |
+
"grad_norm": 0.392578125,
|
| 1914 |
+
"learning_rate": 0.0003673971063351594,
|
| 1915 |
+
"loss": 1.1582,
|
| 1916 |
+
"mean_token_accuracy": 0.7281600207090377,
|
| 1917 |
+
"num_tokens": 369068618.0,
|
| 1918 |
+
"step": 2110
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.5777649082764141,
|
| 1922 |
+
"grad_norm": 0.37890625,
|
| 1923 |
+
"learning_rate": 0.00036669476050007024,
|
| 1924 |
+
"loss": 1.1683,
|
| 1925 |
+
"mean_token_accuracy": 0.727477038372308,
|
| 1926 |
+
"num_tokens": 370792272.0,
|
| 1927 |
+
"step": 2120
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.5804902144475294,
|
| 1931 |
+
"grad_norm": 0.375,
|
| 1932 |
+
"learning_rate": 0.00036599241466498105,
|
| 1933 |
+
"loss": 1.1724,
|
| 1934 |
+
"mean_token_accuracy": 0.725747492350638,
|
| 1935 |
+
"num_tokens": 372506541.0,
|
| 1936 |
+
"step": 2130
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.5832155206186445,
|
| 1940 |
+
"grad_norm": 0.361328125,
|
| 1941 |
+
"learning_rate": 0.00036529006882989187,
|
| 1942 |
+
"loss": 1.1075,
|
| 1943 |
+
"mean_token_accuracy": 0.7377508584409952,
|
| 1944 |
+
"num_tokens": 374308542.0,
|
| 1945 |
+
"step": 2140
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 0.5859408267897597,
|
| 1949 |
+
"grad_norm": 0.47265625,
|
| 1950 |
+
"learning_rate": 0.00036458772299480263,
|
| 1951 |
+
"loss": 1.1207,
|
| 1952 |
+
"mean_token_accuracy": 0.735583251528442,
|
| 1953 |
+
"num_tokens": 376016266.0,
|
| 1954 |
+
"step": 2150
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.5886661329608748,
|
| 1958 |
+
"grad_norm": 0.36328125,
|
| 1959 |
+
"learning_rate": 0.00036388537715971344,
|
| 1960 |
+
"loss": 1.1742,
|
| 1961 |
+
"mean_token_accuracy": 0.7264269077219069,
|
| 1962 |
+
"num_tokens": 377732713.0,
|
| 1963 |
+
"step": 2160
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.59139143913199,
|
| 1967 |
+
"grad_norm": 0.38671875,
|
| 1968 |
+
"learning_rate": 0.00036318303132462426,
|
| 1969 |
+
"loss": 1.1541,
|
| 1970 |
+
"mean_token_accuracy": 0.7288526111282408,
|
| 1971 |
+
"num_tokens": 379457927.0,
|
| 1972 |
+
"step": 2170
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 0.5941167453031051,
|
| 1976 |
+
"grad_norm": 0.326171875,
|
| 1977 |
+
"learning_rate": 0.0003624806854895351,
|
| 1978 |
+
"loss": 1.2054,
|
| 1979 |
+
"mean_token_accuracy": 0.719714920129627,
|
| 1980 |
+
"num_tokens": 381311531.0,
|
| 1981 |
+
"step": 2180
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 0.5968420514742203,
|
| 1985 |
+
"grad_norm": 0.40625,
|
| 1986 |
+
"learning_rate": 0.00036177833965444584,
|
| 1987 |
+
"loss": 1.1941,
|
| 1988 |
+
"mean_token_accuracy": 0.7239844122901559,
|
| 1989 |
+
"num_tokens": 383076036.0,
|
| 1990 |
+
"step": 2190
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.5995673576453354,
|
| 1994 |
+
"grad_norm": 0.384765625,
|
| 1995 |
+
"learning_rate": 0.0003610759938193567,
|
| 1996 |
+
"loss": 1.181,
|
| 1997 |
+
"mean_token_accuracy": 0.7247908087447286,
|
| 1998 |
+
"num_tokens": 384869981.0,
|
| 1999 |
+
"step": 2200
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 0.6022926638164506,
|
| 2003 |
+
"grad_norm": 0.408203125,
|
| 2004 |
+
"learning_rate": 0.00036037364798426747,
|
| 2005 |
+
"loss": 1.1548,
|
| 2006 |
+
"mean_token_accuracy": 0.727875262312591,
|
| 2007 |
+
"num_tokens": 386654361.0,
|
| 2008 |
+
"step": 2210
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 0.6050179699875657,
|
| 2012 |
+
"grad_norm": 0.38671875,
|
| 2013 |
+
"learning_rate": 0.0003596713021491783,
|
| 2014 |
+
"loss": 1.1284,
|
| 2015 |
+
"mean_token_accuracy": 0.7336899240501225,
|
| 2016 |
+
"num_tokens": 388405388.0,
|
| 2017 |
+
"step": 2220
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.607743276158681,
|
| 2021 |
+
"grad_norm": 0.37109375,
|
| 2022 |
+
"learning_rate": 0.00035896895631408904,
|
| 2023 |
+
"loss": 1.1629,
|
| 2024 |
+
"mean_token_accuracy": 0.72736093737185,
|
| 2025 |
+
"num_tokens": 390160411.0,
|
| 2026 |
+
"step": 2230
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.6104685823297961,
|
| 2030 |
+
"grad_norm": 0.341796875,
|
| 2031 |
+
"learning_rate": 0.0003582666104789999,
|
| 2032 |
+
"loss": 1.1718,
|
| 2033 |
+
"mean_token_accuracy": 0.724588902015239,
|
| 2034 |
+
"num_tokens": 391963393.0,
|
| 2035 |
+
"step": 2240
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 0.6131938885009113,
|
| 2039 |
+
"grad_norm": 0.361328125,
|
| 2040 |
+
"learning_rate": 0.0003575642646439107,
|
| 2041 |
+
"loss": 1.1686,
|
| 2042 |
+
"mean_token_accuracy": 0.7265552974306047,
|
| 2043 |
+
"num_tokens": 393719494.0,
|
| 2044 |
+
"step": 2250
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 0.6159191946720264,
|
| 2048 |
+
"grad_norm": 0.3203125,
|
| 2049 |
+
"learning_rate": 0.00035686191880882144,
|
| 2050 |
+
"loss": 1.1597,
|
| 2051 |
+
"mean_token_accuracy": 0.7278934679925442,
|
| 2052 |
+
"num_tokens": 395419867.0,
|
| 2053 |
+
"step": 2260
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.6186445008431416,
|
| 2057 |
+
"grad_norm": 0.3515625,
|
| 2058 |
+
"learning_rate": 0.00035615957297373225,
|
| 2059 |
+
"loss": 1.14,
|
| 2060 |
+
"mean_token_accuracy": 0.7317047557793558,
|
| 2061 |
+
"num_tokens": 397164636.0,
|
| 2062 |
+
"step": 2270
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.6213698070142567,
|
| 2066 |
+
"grad_norm": 0.384765625,
|
| 2067 |
+
"learning_rate": 0.00035545722713864307,
|
| 2068 |
+
"loss": 1.1711,
|
| 2069 |
+
"mean_token_accuracy": 0.7251532531343401,
|
| 2070 |
+
"num_tokens": 398897880.0,
|
| 2071 |
+
"step": 2280
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 0.6240951131853719,
|
| 2075 |
+
"grad_norm": 0.37109375,
|
| 2076 |
+
"learning_rate": 0.0003547548813035539,
|
| 2077 |
+
"loss": 1.1499,
|
| 2078 |
+
"mean_token_accuracy": 0.72917456375435,
|
| 2079 |
+
"num_tokens": 400668616.0,
|
| 2080 |
+
"step": 2290
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.6268204193564871,
|
| 2084 |
+
"grad_norm": 0.375,
|
| 2085 |
+
"learning_rate": 0.00035405253546846464,
|
| 2086 |
+
"loss": 1.1378,
|
| 2087 |
+
"mean_token_accuracy": 0.7313735852017998,
|
| 2088 |
+
"num_tokens": 402379710.0,
|
| 2089 |
+
"step": 2300
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.6295457255276022,
|
| 2093 |
+
"grad_norm": 0.3515625,
|
| 2094 |
+
"learning_rate": 0.0003533501896333755,
|
| 2095 |
+
"loss": 1.1381,
|
| 2096 |
+
"mean_token_accuracy": 0.7306974153965712,
|
| 2097 |
+
"num_tokens": 404084345.0,
|
| 2098 |
+
"step": 2310
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.6322710316987175,
|
| 2102 |
+
"grad_norm": 0.3828125,
|
| 2103 |
+
"learning_rate": 0.0003526478437982863,
|
| 2104 |
+
"loss": 1.0999,
|
| 2105 |
+
"mean_token_accuracy": 0.7397502162493765,
|
| 2106 |
+
"num_tokens": 405770321.0,
|
| 2107 |
+
"step": 2320
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 0.6349963378698326,
|
| 2111 |
+
"grad_norm": 0.3359375,
|
| 2112 |
+
"learning_rate": 0.0003519454979631971,
|
| 2113 |
+
"loss": 1.1241,
|
| 2114 |
+
"mean_token_accuracy": 0.733117110747844,
|
| 2115 |
+
"num_tokens": 407492020.0,
|
| 2116 |
+
"step": 2330
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6377216440409478,
|
| 2120 |
+
"grad_norm": 0.345703125,
|
| 2121 |
+
"learning_rate": 0.00035124315212810785,
|
| 2122 |
+
"loss": 1.1205,
|
| 2123 |
+
"mean_token_accuracy": 0.7354815387167036,
|
| 2124 |
+
"num_tokens": 409257115.0,
|
| 2125 |
+
"step": 2340
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 0.6404469502120629,
|
| 2129 |
+
"grad_norm": 0.33984375,
|
| 2130 |
+
"learning_rate": 0.0003505408062930187,
|
| 2131 |
+
"loss": 1.1524,
|
| 2132 |
+
"mean_token_accuracy": 0.7284994964487851,
|
| 2133 |
+
"num_tokens": 410986071.0,
|
| 2134 |
+
"step": 2350
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 0.6431722563831781,
|
| 2138 |
+
"grad_norm": 0.361328125,
|
| 2139 |
+
"learning_rate": 0.0003498384604579295,
|
| 2140 |
+
"loss": 1.1326,
|
| 2141 |
+
"mean_token_accuracy": 0.73249177262187,
|
| 2142 |
+
"num_tokens": 412763897.0,
|
| 2143 |
+
"step": 2360
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 0.6458975625542932,
|
| 2147 |
+
"grad_norm": 0.35546875,
|
| 2148 |
+
"learning_rate": 0.0003491361146228403,
|
| 2149 |
+
"loss": 1.0881,
|
| 2150 |
+
"mean_token_accuracy": 0.7415378532372415,
|
| 2151 |
+
"num_tokens": 414503168.0,
|
| 2152 |
+
"step": 2370
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.6486228687254084,
|
| 2156 |
+
"grad_norm": 0.353515625,
|
| 2157 |
+
"learning_rate": 0.00034843376878775106,
|
| 2158 |
+
"loss": 1.1189,
|
| 2159 |
+
"mean_token_accuracy": 0.7360304208472371,
|
| 2160 |
+
"num_tokens": 416227145.0,
|
| 2161 |
+
"step": 2380
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 0.6513481748965235,
|
| 2165 |
+
"grad_norm": 0.33203125,
|
| 2166 |
+
"learning_rate": 0.00034773142295266193,
|
| 2167 |
+
"loss": 1.1114,
|
| 2168 |
+
"mean_token_accuracy": 0.7346363394521177,
|
| 2169 |
+
"num_tokens": 417973040.0,
|
| 2170 |
+
"step": 2390
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.6540734810676387,
|
| 2174 |
+
"grad_norm": 0.365234375,
|
| 2175 |
+
"learning_rate": 0.0003470290771175727,
|
| 2176 |
+
"loss": 1.1291,
|
| 2177 |
+
"mean_token_accuracy": 0.7329517565667629,
|
| 2178 |
+
"num_tokens": 419736780.0,
|
| 2179 |
+
"step": 2400
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.6567987872387538,
|
| 2183 |
+
"grad_norm": 0.32421875,
|
| 2184 |
+
"learning_rate": 0.0003463267312824835,
|
| 2185 |
+
"loss": 1.12,
|
| 2186 |
+
"mean_token_accuracy": 0.7355642972514034,
|
| 2187 |
+
"num_tokens": 421516023.0,
|
| 2188 |
+
"step": 2410
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 0.6595240934098691,
|
| 2192 |
+
"grad_norm": 0.3984375,
|
| 2193 |
+
"learning_rate": 0.0003456243854473943,
|
| 2194 |
+
"loss": 1.1714,
|
| 2195 |
+
"mean_token_accuracy": 0.7273551743477583,
|
| 2196 |
+
"num_tokens": 423324296.0,
|
| 2197 |
+
"step": 2420
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 0.6622493995809842,
|
| 2201 |
+
"grad_norm": 0.42578125,
|
| 2202 |
+
"learning_rate": 0.00034492203961230514,
|
| 2203 |
+
"loss": 1.1472,
|
| 2204 |
+
"mean_token_accuracy": 0.7267329922877253,
|
| 2205 |
+
"num_tokens": 425114987.0,
|
| 2206 |
+
"step": 2430
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 0.6649747057520994,
|
| 2210 |
+
"grad_norm": 0.373046875,
|
| 2211 |
+
"learning_rate": 0.0003442196937772159,
|
| 2212 |
+
"loss": 1.114,
|
| 2213 |
+
"mean_token_accuracy": 0.7362177189439535,
|
| 2214 |
+
"num_tokens": 426875751.0,
|
| 2215 |
+
"step": 2440
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.6677000119232145,
|
| 2219 |
+
"grad_norm": 0.330078125,
|
| 2220 |
+
"learning_rate": 0.0003435173479421267,
|
| 2221 |
+
"loss": 1.1187,
|
| 2222 |
+
"mean_token_accuracy": 0.7348853600211441,
|
| 2223 |
+
"num_tokens": 428715433.0,
|
| 2224 |
+
"step": 2450
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 0.6704253180943297,
|
| 2228 |
+
"grad_norm": 0.400390625,
|
| 2229 |
+
"learning_rate": 0.00034281500210703753,
|
| 2230 |
+
"loss": 1.1587,
|
| 2231 |
+
"mean_token_accuracy": 0.7272924329154193,
|
| 2232 |
+
"num_tokens": 430443301.0,
|
| 2233 |
+
"step": 2460
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 0.6731506242654448,
|
| 2237 |
+
"grad_norm": 0.34375,
|
| 2238 |
+
"learning_rate": 0.00034211265627194835,
|
| 2239 |
+
"loss": 1.0693,
|
| 2240 |
+
"mean_token_accuracy": 0.7440984978340566,
|
| 2241 |
+
"num_tokens": 432149898.0,
|
| 2242 |
+
"step": 2470
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.67587593043656,
|
| 2246 |
+
"grad_norm": 0.388671875,
|
| 2247 |
+
"learning_rate": 0.0003414103104368591,
|
| 2248 |
+
"loss": 1.0951,
|
| 2249 |
+
"mean_token_accuracy": 0.7401705386117101,
|
| 2250 |
+
"num_tokens": 433904775.0,
|
| 2251 |
+
"step": 2480
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 0.6786012366076751,
|
| 2255 |
+
"grad_norm": 0.3828125,
|
| 2256 |
+
"learning_rate": 0.00034070796460176987,
|
| 2257 |
+
"loss": 1.0992,
|
| 2258 |
+
"mean_token_accuracy": 0.7375994463451206,
|
| 2259 |
+
"num_tokens": 435648944.0,
|
| 2260 |
+
"step": 2490
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 0.6813265427787903,
|
| 2264 |
+
"grad_norm": 0.34375,
|
| 2265 |
+
"learning_rate": 0.00034000561876668074,
|
| 2266 |
+
"loss": 1.1405,
|
| 2267 |
+
"mean_token_accuracy": 0.7315420118160546,
|
| 2268 |
+
"num_tokens": 437390122.0,
|
| 2269 |
+
"step": 2500
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.6840518489499054,
|
| 2273 |
+
"grad_norm": 0.3515625,
|
| 2274 |
+
"learning_rate": 0.0003393032729315915,
|
| 2275 |
+
"loss": 1.1311,
|
| 2276 |
+
"mean_token_accuracy": 0.733266216237098,
|
| 2277 |
+
"num_tokens": 439126311.0,
|
| 2278 |
+
"step": 2510
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.6867771551210207,
|
| 2282 |
+
"grad_norm": 0.3671875,
|
| 2283 |
+
"learning_rate": 0.0003386009270965023,
|
| 2284 |
+
"loss": 1.1102,
|
| 2285 |
+
"mean_token_accuracy": 0.7364032724872231,
|
| 2286 |
+
"num_tokens": 440890933.0,
|
| 2287 |
+
"step": 2520
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 0.6895024612921358,
|
| 2291 |
+
"grad_norm": 0.392578125,
|
| 2292 |
+
"learning_rate": 0.00033789858126141313,
|
| 2293 |
+
"loss": 1.101,
|
| 2294 |
+
"mean_token_accuracy": 0.7384627360850573,
|
| 2295 |
+
"num_tokens": 442611770.0,
|
| 2296 |
+
"step": 2530
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 0.692227767463251,
|
| 2300 |
+
"grad_norm": 0.369140625,
|
| 2301 |
+
"learning_rate": 0.00033719623542632395,
|
| 2302 |
+
"loss": 1.1059,
|
| 2303 |
+
"mean_token_accuracy": 0.7377724641934037,
|
| 2304 |
+
"num_tokens": 444358166.0,
|
| 2305 |
+
"step": 2540
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.6949530736343661,
|
| 2309 |
+
"grad_norm": 0.35546875,
|
| 2310 |
+
"learning_rate": 0.0003364938895912347,
|
| 2311 |
+
"loss": 1.145,
|
| 2312 |
+
"mean_token_accuracy": 0.7298734590411187,
|
| 2313 |
+
"num_tokens": 446078790.0,
|
| 2314 |
+
"step": 2550
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.6976783798054813,
|
| 2318 |
+
"grad_norm": 0.392578125,
|
| 2319 |
+
"learning_rate": 0.0003357915437561455,
|
| 2320 |
+
"loss": 1.1079,
|
| 2321 |
+
"mean_token_accuracy": 0.7355253180488944,
|
| 2322 |
+
"num_tokens": 447811186.0,
|
| 2323 |
+
"step": 2560
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 0.7004036859765964,
|
| 2327 |
+
"grad_norm": 0.337890625,
|
| 2328 |
+
"learning_rate": 0.00033508919792105634,
|
| 2329 |
+
"loss": 1.124,
|
| 2330 |
+
"mean_token_accuracy": 0.7344003698788584,
|
| 2331 |
+
"num_tokens": 449537962.0,
|
| 2332 |
+
"step": 2570
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.7031289921477116,
|
| 2336 |
+
"grad_norm": 0.34375,
|
| 2337 |
+
"learning_rate": 0.00033438685208596715,
|
| 2338 |
+
"loss": 1.0841,
|
| 2339 |
+
"mean_token_accuracy": 0.7412578398361802,
|
| 2340 |
+
"num_tokens": 451259469.0,
|
| 2341 |
+
"step": 2580
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.7058542983188267,
|
| 2345 |
+
"grad_norm": 0.3515625,
|
| 2346 |
+
"learning_rate": 0.0003336845062508779,
|
| 2347 |
+
"loss": 1.1074,
|
| 2348 |
+
"mean_token_accuracy": 0.7388199215754867,
|
| 2349 |
+
"num_tokens": 453041146.0,
|
| 2350 |
+
"step": 2590
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.708579604489942,
|
| 2354 |
+
"grad_norm": 0.35546875,
|
| 2355 |
+
"learning_rate": 0.00033298216041578873,
|
| 2356 |
+
"loss": 1.132,
|
| 2357 |
+
"mean_token_accuracy": 0.7321982179768384,
|
| 2358 |
+
"num_tokens": 454753651.0,
|
| 2359 |
+
"step": 2600
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 0.711304910661057,
|
| 2363 |
+
"grad_norm": 0.35546875,
|
| 2364 |
+
"learning_rate": 0.00033227981458069955,
|
| 2365 |
+
"loss": 1.0938,
|
| 2366 |
+
"mean_token_accuracy": 0.7390209911391139,
|
| 2367 |
+
"num_tokens": 456537057.0,
|
| 2368 |
+
"step": 2610
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.7140302168321723,
|
| 2372 |
+
"grad_norm": 0.36328125,
|
| 2373 |
+
"learning_rate": 0.00033157746874561036,
|
| 2374 |
+
"loss": 1.1417,
|
| 2375 |
+
"mean_token_accuracy": 0.7310832546092569,
|
| 2376 |
+
"num_tokens": 458271296.0,
|
| 2377 |
+
"step": 2620
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 0.7167555230032874,
|
| 2381 |
+
"grad_norm": 0.34375,
|
| 2382 |
+
"learning_rate": 0.0003308751229105211,
|
| 2383 |
+
"loss": 1.1118,
|
| 2384 |
+
"mean_token_accuracy": 0.7353935448452831,
|
| 2385 |
+
"num_tokens": 460014932.0,
|
| 2386 |
+
"step": 2630
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.7194808291744026,
|
| 2390 |
+
"grad_norm": 0.345703125,
|
| 2391 |
+
"learning_rate": 0.000330172777075432,
|
| 2392 |
+
"loss": 1.1228,
|
| 2393 |
+
"mean_token_accuracy": 0.7343842899426818,
|
| 2394 |
+
"num_tokens": 461818480.0,
|
| 2395 |
+
"step": 2640
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.7222061353455177,
|
| 2399 |
+
"grad_norm": 0.359375,
|
| 2400 |
+
"learning_rate": 0.00032947043124034275,
|
| 2401 |
+
"loss": 1.1535,
|
| 2402 |
+
"mean_token_accuracy": 0.7270912263542414,
|
| 2403 |
+
"num_tokens": 463519993.0,
|
| 2404 |
+
"step": 2650
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.7249314415166329,
|
| 2408 |
+
"grad_norm": 0.349609375,
|
| 2409 |
+
"learning_rate": 0.00032876808540525357,
|
| 2410 |
+
"loss": 1.1122,
|
| 2411 |
+
"mean_token_accuracy": 0.7352983796037733,
|
| 2412 |
+
"num_tokens": 465333101.0,
|
| 2413 |
+
"step": 2660
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.727656747687748,
|
| 2417 |
+
"grad_norm": 0.349609375,
|
| 2418 |
+
"learning_rate": 0.00032806573957016433,
|
| 2419 |
+
"loss": 1.1081,
|
| 2420 |
+
"mean_token_accuracy": 0.7361832971684634,
|
| 2421 |
+
"num_tokens": 467047198.0,
|
| 2422 |
+
"step": 2670
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 0.7303820538588632,
|
| 2426 |
+
"grad_norm": 0.345703125,
|
| 2427 |
+
"learning_rate": 0.0003273633937350752,
|
| 2428 |
+
"loss": 1.1227,
|
| 2429 |
+
"mean_token_accuracy": 0.7353186239488423,
|
| 2430 |
+
"num_tokens": 468806711.0,
|
| 2431 |
+
"step": 2680
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7331073600299783,
|
| 2435 |
+
"grad_norm": 0.330078125,
|
| 2436 |
+
"learning_rate": 0.00032666104789998596,
|
| 2437 |
+
"loss": 1.0706,
|
| 2438 |
+
"mean_token_accuracy": 0.7438032808713615,
|
| 2439 |
+
"num_tokens": 470600782.0,
|
| 2440 |
+
"step": 2690
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 0.7358326662010936,
|
| 2444 |
+
"grad_norm": 0.3515625,
|
| 2445 |
+
"learning_rate": 0.0003259587020648968,
|
| 2446 |
+
"loss": 1.1209,
|
| 2447 |
+
"mean_token_accuracy": 0.734395441506058,
|
| 2448 |
+
"num_tokens": 472349330.0,
|
| 2449 |
+
"step": 2700
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.7385579723722087,
|
| 2453 |
+
"grad_norm": 0.322265625,
|
| 2454 |
+
"learning_rate": 0.00032525635622980754,
|
| 2455 |
+
"loss": 1.0917,
|
| 2456 |
+
"mean_token_accuracy": 0.7406582017429173,
|
| 2457 |
+
"num_tokens": 474106983.0,
|
| 2458 |
+
"step": 2710
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 0.7412832785433239,
|
| 2462 |
+
"grad_norm": 0.373046875,
|
| 2463 |
+
"learning_rate": 0.00032455401039471835,
|
| 2464 |
+
"loss": 1.146,
|
| 2465 |
+
"mean_token_accuracy": 0.7296730799600482,
|
| 2466 |
+
"num_tokens": 475902407.0,
|
| 2467 |
+
"step": 2720
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.744008584714439,
|
| 2471 |
+
"grad_norm": 0.345703125,
|
| 2472 |
+
"learning_rate": 0.00032385166455962917,
|
| 2473 |
+
"loss": 1.0453,
|
| 2474 |
+
"mean_token_accuracy": 0.7479070770554245,
|
| 2475 |
+
"num_tokens": 477654644.0,
|
| 2476 |
+
"step": 2730
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.7467338908855542,
|
| 2480 |
+
"grad_norm": 0.359375,
|
| 2481 |
+
"learning_rate": 0.00032314931872453993,
|
| 2482 |
+
"loss": 1.1249,
|
| 2483 |
+
"mean_token_accuracy": 0.7325184845365584,
|
| 2484 |
+
"num_tokens": 479409078.0,
|
| 2485 |
+
"step": 2740
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 0.7494591970566693,
|
| 2489 |
+
"grad_norm": 0.35546875,
|
| 2490 |
+
"learning_rate": 0.0003224469728894508,
|
| 2491 |
+
"loss": 1.1047,
|
| 2492 |
+
"mean_token_accuracy": 0.7368000699207187,
|
| 2493 |
+
"num_tokens": 481154972.0,
|
| 2494 |
+
"step": 2750
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.7521845032277845,
|
| 2498 |
+
"grad_norm": 0.37890625,
|
| 2499 |
+
"learning_rate": 0.00032174462705436156,
|
| 2500 |
+
"loss": 1.1314,
|
| 2501 |
+
"mean_token_accuracy": 0.7322432189248502,
|
| 2502 |
+
"num_tokens": 482957554.0,
|
| 2503 |
+
"step": 2760
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 0.7549098093988996,
|
| 2507 |
+
"grad_norm": 0.345703125,
|
| 2508 |
+
"learning_rate": 0.0003210422812192724,
|
| 2509 |
+
"loss": 1.106,
|
| 2510 |
+
"mean_token_accuracy": 0.7369892225600779,
|
| 2511 |
+
"num_tokens": 484730289.0,
|
| 2512 |
+
"step": 2770
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 0.7576351155700148,
|
| 2516 |
+
"grad_norm": 0.38671875,
|
| 2517 |
+
"learning_rate": 0.00032033993538418314,
|
| 2518 |
+
"loss": 1.1143,
|
| 2519 |
+
"mean_token_accuracy": 0.7335695104673505,
|
| 2520 |
+
"num_tokens": 486390658.0,
|
| 2521 |
+
"step": 2780
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.7603604217411299,
|
| 2525 |
+
"grad_norm": 0.357421875,
|
| 2526 |
+
"learning_rate": 0.000319637589549094,
|
| 2527 |
+
"loss": 1.0688,
|
| 2528 |
+
"mean_token_accuracy": 0.7441553009673954,
|
| 2529 |
+
"num_tokens": 488084357.0,
|
| 2530 |
+
"step": 2790
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.7630857279122452,
|
| 2534 |
+
"grad_norm": 0.36328125,
|
| 2535 |
+
"learning_rate": 0.00031893524371400477,
|
| 2536 |
+
"loss": 1.1611,
|
| 2537 |
+
"mean_token_accuracy": 0.7271939906291663,
|
| 2538 |
+
"num_tokens": 489867504.0,
|
| 2539 |
+
"step": 2800
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 0.7658110340833603,
|
| 2543 |
+
"grad_norm": 0.328125,
|
| 2544 |
+
"learning_rate": 0.0003182328978789156,
|
| 2545 |
+
"loss": 1.1254,
|
| 2546 |
+
"mean_token_accuracy": 0.7324933409690857,
|
| 2547 |
+
"num_tokens": 491614120.0,
|
| 2548 |
+
"step": 2810
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 0.7685363402544755,
|
| 2552 |
+
"grad_norm": 0.34765625,
|
| 2553 |
+
"learning_rate": 0.00031753055204382635,
|
| 2554 |
+
"loss": 1.1173,
|
| 2555 |
+
"mean_token_accuracy": 0.7357215932570398,
|
| 2556 |
+
"num_tokens": 493360108.0,
|
| 2557 |
+
"step": 2820
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.7712616464255906,
|
| 2561 |
+
"grad_norm": 0.33984375,
|
| 2562 |
+
"learning_rate": 0.0003168282062087372,
|
| 2563 |
+
"loss": 1.0859,
|
| 2564 |
+
"mean_token_accuracy": 0.742600809969008,
|
| 2565 |
+
"num_tokens": 495060867.0,
|
| 2566 |
+
"step": 2830
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 0.7739869525967058,
|
| 2570 |
+
"grad_norm": 0.357421875,
|
| 2571 |
+
"learning_rate": 0.000316125860373648,
|
| 2572 |
+
"loss": 1.1152,
|
| 2573 |
+
"mean_token_accuracy": 0.7333301523700356,
|
| 2574 |
+
"num_tokens": 496731129.0,
|
| 2575 |
+
"step": 2840
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 0.7767122587678209,
|
| 2579 |
+
"grad_norm": 0.322265625,
|
| 2580 |
+
"learning_rate": 0.0003154235145385588,
|
| 2581 |
+
"loss": 1.0788,
|
| 2582 |
+
"mean_token_accuracy": 0.7434908222407103,
|
| 2583 |
+
"num_tokens": 498416929.0,
|
| 2584 |
+
"step": 2850
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 0.7794375649389361,
|
| 2588 |
+
"grad_norm": 0.34375,
|
| 2589 |
+
"learning_rate": 0.0003147211687034696,
|
| 2590 |
+
"loss": 1.065,
|
| 2591 |
+
"mean_token_accuracy": 0.7451503177173435,
|
| 2592 |
+
"num_tokens": 500131030.0,
|
| 2593 |
+
"step": 2860
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.7821628711100512,
|
| 2597 |
+
"grad_norm": 0.328125,
|
| 2598 |
+
"learning_rate": 0.0003140188228683804,
|
| 2599 |
+
"loss": 1.0668,
|
| 2600 |
+
"mean_token_accuracy": 0.7436349290423095,
|
| 2601 |
+
"num_tokens": 501860254.0,
|
| 2602 |
+
"step": 2870
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 0.7848881772811664,
|
| 2606 |
+
"grad_norm": 0.376953125,
|
| 2607 |
+
"learning_rate": 0.0003133164770332912,
|
| 2608 |
+
"loss": 1.1311,
|
| 2609 |
+
"mean_token_accuracy": 0.7318741642870009,
|
| 2610 |
+
"num_tokens": 503599791.0,
|
| 2611 |
+
"step": 2880
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 0.7876134834522815,
|
| 2615 |
+
"grad_norm": 0.345703125,
|
| 2616 |
+
"learning_rate": 0.000312614131198202,
|
| 2617 |
+
"loss": 1.1602,
|
| 2618 |
+
"mean_token_accuracy": 0.7279526983387768,
|
| 2619 |
+
"num_tokens": 505277304.0,
|
| 2620 |
+
"step": 2890
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.7903387896233968,
|
| 2624 |
+
"grad_norm": 0.35546875,
|
| 2625 |
+
"learning_rate": 0.0003119117853631128,
|
| 2626 |
+
"loss": 1.1026,
|
| 2627 |
+
"mean_token_accuracy": 0.7374209313653409,
|
| 2628 |
+
"num_tokens": 507010506.0,
|
| 2629 |
+
"step": 2900
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 0.7930640957945119,
|
| 2633 |
+
"grad_norm": 0.33203125,
|
| 2634 |
+
"learning_rate": 0.00031120943952802363,
|
| 2635 |
+
"loss": 1.0825,
|
| 2636 |
+
"mean_token_accuracy": 0.7415086347609758,
|
| 2637 |
+
"num_tokens": 508717678.0,
|
| 2638 |
+
"step": 2910
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 0.7957894019656271,
|
| 2642 |
+
"grad_norm": 0.326171875,
|
| 2643 |
+
"learning_rate": 0.0003105070936929344,
|
| 2644 |
+
"loss": 1.0521,
|
| 2645 |
+
"mean_token_accuracy": 0.7478948015719652,
|
| 2646 |
+
"num_tokens": 510478982.0,
|
| 2647 |
+
"step": 2920
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 0.7985147081367422,
|
| 2651 |
+
"grad_norm": 0.361328125,
|
| 2652 |
+
"learning_rate": 0.00030980474785784526,
|
| 2653 |
+
"loss": 1.059,
|
| 2654 |
+
"mean_token_accuracy": 0.7448375985957683,
|
| 2655 |
+
"num_tokens": 512223492.0,
|
| 2656 |
+
"step": 2930
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.8012400143078574,
|
| 2660 |
+
"grad_norm": 0.3515625,
|
| 2661 |
+
"learning_rate": 0.000309102402022756,
|
| 2662 |
+
"loss": 1.0837,
|
| 2663 |
+
"mean_token_accuracy": 0.7406654883176088,
|
| 2664 |
+
"num_tokens": 513950826.0,
|
| 2665 |
+
"step": 2940
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 0.8039653204789725,
|
| 2669 |
+
"grad_norm": 0.337890625,
|
| 2670 |
+
"learning_rate": 0.0003084000561876668,
|
| 2671 |
+
"loss": 1.1186,
|
| 2672 |
+
"mean_token_accuracy": 0.7354094261303544,
|
| 2673 |
+
"num_tokens": 515747512.0,
|
| 2674 |
+
"step": 2950
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 0.8066906266500877,
|
| 2678 |
+
"grad_norm": 0.318359375,
|
| 2679 |
+
"learning_rate": 0.0003076977103525776,
|
| 2680 |
+
"loss": 1.0841,
|
| 2681 |
+
"mean_token_accuracy": 0.7409739443100989,
|
| 2682 |
+
"num_tokens": 517564408.0,
|
| 2683 |
+
"step": 2960
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.8094159328212028,
|
| 2687 |
+
"grad_norm": 0.328125,
|
| 2688 |
+
"learning_rate": 0.0003069953645174884,
|
| 2689 |
+
"loss": 1.0163,
|
| 2690 |
+
"mean_token_accuracy": 0.753525473922491,
|
| 2691 |
+
"num_tokens": 519335113.0,
|
| 2692 |
+
"step": 2970
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 0.812141238992318,
|
| 2696 |
+
"grad_norm": 0.341796875,
|
| 2697 |
+
"learning_rate": 0.00030629301868239923,
|
| 2698 |
+
"loss": 1.0592,
|
| 2699 |
+
"mean_token_accuracy": 0.7457088253460824,
|
| 2700 |
+
"num_tokens": 521052694.0,
|
| 2701 |
+
"step": 2980
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 0.8148665451634332,
|
| 2705 |
+
"grad_norm": 0.33984375,
|
| 2706 |
+
"learning_rate": 0.00030559067284731,
|
| 2707 |
+
"loss": 1.1095,
|
| 2708 |
+
"mean_token_accuracy": 0.7366851487196981,
|
| 2709 |
+
"num_tokens": 522838886.0,
|
| 2710 |
+
"step": 2990
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 0.8175918513345484,
|
| 2714 |
+
"grad_norm": 0.333984375,
|
| 2715 |
+
"learning_rate": 0.0003048883270122208,
|
| 2716 |
+
"loss": 1.0807,
|
| 2717 |
+
"mean_token_accuracy": 0.7409872910007834,
|
| 2718 |
+
"num_tokens": 524659688.0,
|
| 2719 |
+
"step": 3000
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.8203171575056635,
|
| 2723 |
+
"grad_norm": 0.333984375,
|
| 2724 |
+
"learning_rate": 0.0003041859811771316,
|
| 2725 |
+
"loss": 1.0652,
|
| 2726 |
+
"mean_token_accuracy": 0.7444087780080736,
|
| 2727 |
+
"num_tokens": 526428828.0,
|
| 2728 |
+
"step": 3010
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 0.8230424636767787,
|
| 2732 |
+
"grad_norm": 0.349609375,
|
| 2733 |
+
"learning_rate": 0.00030348363534204244,
|
| 2734 |
+
"loss": 1.0946,
|
| 2735 |
+
"mean_token_accuracy": 0.737694866489619,
|
| 2736 |
+
"num_tokens": 528178357.0,
|
| 2737 |
+
"step": 3020
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 0.8257677698478938,
|
| 2741 |
+
"grad_norm": 0.33984375,
|
| 2742 |
+
"learning_rate": 0.0003027812895069532,
|
| 2743 |
+
"loss": 1.0771,
|
| 2744 |
+
"mean_token_accuracy": 0.7418748954311013,
|
| 2745 |
+
"num_tokens": 529968661.0,
|
| 2746 |
+
"step": 3030
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.828493076019009,
|
| 2750 |
+
"grad_norm": 0.359375,
|
| 2751 |
+
"learning_rate": 0.00030207894367186407,
|
| 2752 |
+
"loss": 1.0785,
|
| 2753 |
+
"mean_token_accuracy": 0.7434822773560882,
|
| 2754 |
+
"num_tokens": 531735846.0,
|
| 2755 |
+
"step": 3040
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 0.8312183821901241,
|
| 2759 |
+
"grad_norm": 0.33203125,
|
| 2760 |
+
"learning_rate": 0.00030137659783677483,
|
| 2761 |
+
"loss": 1.1008,
|
| 2762 |
+
"mean_token_accuracy": 0.7383057860657573,
|
| 2763 |
+
"num_tokens": 533482605.0,
|
| 2764 |
+
"step": 3050
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 0.8339436883612393,
|
| 2768 |
+
"grad_norm": 0.33203125,
|
| 2769 |
+
"learning_rate": 0.00030067425200168565,
|
| 2770 |
+
"loss": 1.0853,
|
| 2771 |
+
"mean_token_accuracy": 0.7413273256272077,
|
| 2772 |
+
"num_tokens": 535172117.0,
|
| 2773 |
+
"step": 3060
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 0.8366689945323545,
|
| 2777 |
+
"grad_norm": 0.388671875,
|
| 2778 |
+
"learning_rate": 0.0002999719061665964,
|
| 2779 |
+
"loss": 1.0709,
|
| 2780 |
+
"mean_token_accuracy": 0.7434915580786765,
|
| 2781 |
+
"num_tokens": 536922982.0,
|
| 2782 |
+
"step": 3070
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8393943007034697,
|
| 2786 |
+
"grad_norm": 0.359375,
|
| 2787 |
+
"learning_rate": 0.0002992695603315073,
|
| 2788 |
+
"loss": 1.0856,
|
| 2789 |
+
"mean_token_accuracy": 0.740437910053879,
|
| 2790 |
+
"num_tokens": 538697561.0,
|
| 2791 |
+
"step": 3080
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 0.8421196068745849,
|
| 2795 |
+
"grad_norm": 0.34765625,
|
| 2796 |
+
"learning_rate": 0.00029856721449641804,
|
| 2797 |
+
"loss": 1.0881,
|
| 2798 |
+
"mean_token_accuracy": 0.7398839842528104,
|
| 2799 |
+
"num_tokens": 540498809.0,
|
| 2800 |
+
"step": 3090
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 0.8448449130457,
|
| 2804 |
+
"grad_norm": 0.333984375,
|
| 2805 |
+
"learning_rate": 0.00029786486866132886,
|
| 2806 |
+
"loss": 1.0505,
|
| 2807 |
+
"mean_token_accuracy": 0.74623784115538,
|
| 2808 |
+
"num_tokens": 542220573.0,
|
| 2809 |
+
"step": 3100
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.8475702192168152,
|
| 2813 |
+
"grad_norm": 0.37109375,
|
| 2814 |
+
"learning_rate": 0.0002971625228262396,
|
| 2815 |
+
"loss": 1.0689,
|
| 2816 |
+
"mean_token_accuracy": 0.7432276338338852,
|
| 2817 |
+
"num_tokens": 543995979.0,
|
| 2818 |
+
"step": 3110
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.8502955253879303,
|
| 2822 |
+
"grad_norm": 0.328125,
|
| 2823 |
+
"learning_rate": 0.0002964601769911505,
|
| 2824 |
+
"loss": 1.1001,
|
| 2825 |
+
"mean_token_accuracy": 0.7364274661056698,
|
| 2826 |
+
"num_tokens": 545762046.0,
|
| 2827 |
+
"step": 3120
|
| 2828 |
+
},
|
| 2829 |
+
{
|
| 2830 |
+
"epoch": 0.8530208315590455,
|
| 2831 |
+
"grad_norm": 0.306640625,
|
| 2832 |
+
"learning_rate": 0.00029575783115606125,
|
| 2833 |
+
"loss": 1.0657,
|
| 2834 |
+
"mean_token_accuracy": 0.7446419023908675,
|
| 2835 |
+
"num_tokens": 547563120.0,
|
| 2836 |
+
"step": 3130
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 0.8557461377301606,
|
| 2840 |
+
"grad_norm": 0.33203125,
|
| 2841 |
+
"learning_rate": 0.00029505548532097206,
|
| 2842 |
+
"loss": 1.0868,
|
| 2843 |
+
"mean_token_accuracy": 0.7397670422680676,
|
| 2844 |
+
"num_tokens": 549276605.0,
|
| 2845 |
+
"step": 3140
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.8584714439012758,
|
| 2849 |
+
"grad_norm": 0.365234375,
|
| 2850 |
+
"learning_rate": 0.0002943531394858829,
|
| 2851 |
+
"loss": 1.0652,
|
| 2852 |
+
"mean_token_accuracy": 0.7441672122105956,
|
| 2853 |
+
"num_tokens": 550991479.0,
|
| 2854 |
+
"step": 3150
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 0.8611967500723909,
|
| 2858 |
+
"grad_norm": 0.33203125,
|
| 2859 |
+
"learning_rate": 0.0002936507936507937,
|
| 2860 |
+
"loss": 1.0578,
|
| 2861 |
+
"mean_token_accuracy": 0.746835071220994,
|
| 2862 |
+
"num_tokens": 552777662.0,
|
| 2863 |
+
"step": 3160
|
| 2864 |
+
},
|
| 2865 |
+
{
|
| 2866 |
+
"epoch": 0.8639220562435062,
|
| 2867 |
+
"grad_norm": 0.357421875,
|
| 2868 |
+
"learning_rate": 0.00029294844781570446,
|
| 2869 |
+
"loss": 1.0466,
|
| 2870 |
+
"mean_token_accuracy": 0.7476489477790892,
|
| 2871 |
+
"num_tokens": 554539356.0,
|
| 2872 |
+
"step": 3170
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 0.8666473624146213,
|
| 2876 |
+
"grad_norm": 0.353515625,
|
| 2877 |
+
"learning_rate": 0.0002922461019806152,
|
| 2878 |
+
"loss": 1.1222,
|
| 2879 |
+
"mean_token_accuracy": 0.733480770047754,
|
| 2880 |
+
"num_tokens": 556212548.0,
|
| 2881 |
+
"step": 3180
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.8693726685857365,
|
| 2885 |
+
"grad_norm": 0.361328125,
|
| 2886 |
+
"learning_rate": 0.0002915437561455261,
|
| 2887 |
+
"loss": 1.0835,
|
| 2888 |
+
"mean_token_accuracy": 0.7399150485172867,
|
| 2889 |
+
"num_tokens": 557950461.0,
|
| 2890 |
+
"step": 3190
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 0.8720979747568516,
|
| 2894 |
+
"grad_norm": 0.36328125,
|
| 2895 |
+
"learning_rate": 0.00029084141031043685,
|
| 2896 |
+
"loss": 1.0566,
|
| 2897 |
+
"mean_token_accuracy": 0.7452725498005748,
|
| 2898 |
+
"num_tokens": 559715926.0,
|
| 2899 |
+
"step": 3200
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 0.8748232809279668,
|
| 2903 |
+
"grad_norm": 0.33984375,
|
| 2904 |
+
"learning_rate": 0.00029013906447534766,
|
| 2905 |
+
"loss": 1.0807,
|
| 2906 |
+
"mean_token_accuracy": 0.7420402772724628,
|
| 2907 |
+
"num_tokens": 561479394.0,
|
| 2908 |
+
"step": 3210
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.8775485870990819,
|
| 2912 |
+
"grad_norm": 0.3359375,
|
| 2913 |
+
"learning_rate": 0.0002894367186402584,
|
| 2914 |
+
"loss": 1.0717,
|
| 2915 |
+
"mean_token_accuracy": 0.7428519351407885,
|
| 2916 |
+
"num_tokens": 563271872.0,
|
| 2917 |
+
"step": 3220
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.8802738932701971,
|
| 2921 |
+
"grad_norm": 0.33203125,
|
| 2922 |
+
"learning_rate": 0.0002887343728051693,
|
| 2923 |
+
"loss": 1.0623,
|
| 2924 |
+
"mean_token_accuracy": 0.745782736968249,
|
| 2925 |
+
"num_tokens": 565002210.0,
|
| 2926 |
+
"step": 3230
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 0.8829991994413122,
|
| 2930 |
+
"grad_norm": 0.34375,
|
| 2931 |
+
"learning_rate": 0.00028803202697008006,
|
| 2932 |
+
"loss": 0.9654,
|
| 2933 |
+
"mean_token_accuracy": 0.7632681075483561,
|
| 2934 |
+
"num_tokens": 566740287.0,
|
| 2935 |
+
"step": 3240
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.8857245056124274,
|
| 2939 |
+
"grad_norm": 0.30859375,
|
| 2940 |
+
"learning_rate": 0.00028732968113499087,
|
| 2941 |
+
"loss": 1.0976,
|
| 2942 |
+
"mean_token_accuracy": 0.7386646059341728,
|
| 2943 |
+
"num_tokens": 568560935.0,
|
| 2944 |
+
"step": 3250
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 0.8884498117835425,
|
| 2948 |
+
"grad_norm": 0.384765625,
|
| 2949 |
+
"learning_rate": 0.0002866273352999017,
|
| 2950 |
+
"loss": 1.0843,
|
| 2951 |
+
"mean_token_accuracy": 0.7406178612262011,
|
| 2952 |
+
"num_tokens": 570290159.0,
|
| 2953 |
+
"step": 3260
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 0.8911751179546578,
|
| 2957 |
+
"grad_norm": 0.3515625,
|
| 2958 |
+
"learning_rate": 0.0002859249894648125,
|
| 2959 |
+
"loss": 1.0829,
|
| 2960 |
+
"mean_token_accuracy": 0.740851585380733,
|
| 2961 |
+
"num_tokens": 572076704.0,
|
| 2962 |
+
"step": 3270
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 0.8939004241257729,
|
| 2966 |
+
"grad_norm": 0.3203125,
|
| 2967 |
+
"learning_rate": 0.00028522264362972326,
|
| 2968 |
+
"loss": 1.1033,
|
| 2969 |
+
"mean_token_accuracy": 0.7380231520161032,
|
| 2970 |
+
"num_tokens": 573841975.0,
|
| 2971 |
+
"step": 3280
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.8966257302968881,
|
| 2975 |
+
"grad_norm": 0.3515625,
|
| 2976 |
+
"learning_rate": 0.0002845202977946341,
|
| 2977 |
+
"loss": 1.0641,
|
| 2978 |
+
"mean_token_accuracy": 0.7450438223779201,
|
| 2979 |
+
"num_tokens": 575587035.0,
|
| 2980 |
+
"step": 3290
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 0.8993510364680032,
|
| 2984 |
+
"grad_norm": 0.318359375,
|
| 2985 |
+
"learning_rate": 0.0002838179519595449,
|
| 2986 |
+
"loss": 1.0663,
|
| 2987 |
+
"mean_token_accuracy": 0.7433103552088142,
|
| 2988 |
+
"num_tokens": 577285852.0,
|
| 2989 |
+
"step": 3300
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 0.9020763426391184,
|
| 2993 |
+
"grad_norm": 0.349609375,
|
| 2994 |
+
"learning_rate": 0.0002831156061244557,
|
| 2995 |
+
"loss": 1.0831,
|
| 2996 |
+
"mean_token_accuracy": 0.7410020404495299,
|
| 2997 |
+
"num_tokens": 579085053.0,
|
| 2998 |
+
"step": 3310
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.9048016488102335,
|
| 3002 |
+
"grad_norm": 0.33203125,
|
| 3003 |
+
"learning_rate": 0.00028241326028936647,
|
| 3004 |
+
"loss": 1.0401,
|
| 3005 |
+
"mean_token_accuracy": 0.7481556948274374,
|
| 3006 |
+
"num_tokens": 580874041.0,
|
| 3007 |
+
"step": 3320
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 0.9075269549813487,
|
| 3011 |
+
"grad_norm": 0.328125,
|
| 3012 |
+
"learning_rate": 0.0002817109144542773,
|
| 3013 |
+
"loss": 1.052,
|
| 3014 |
+
"mean_token_accuracy": 0.7451382425613702,
|
| 3015 |
+
"num_tokens": 582616757.0,
|
| 3016 |
+
"step": 3330
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.9102522611524638,
|
| 3020 |
+
"grad_norm": 0.37109375,
|
| 3021 |
+
"learning_rate": 0.0002810085686191881,
|
| 3022 |
+
"loss": 1.0498,
|
| 3023 |
+
"mean_token_accuracy": 0.7470538474619388,
|
| 3024 |
+
"num_tokens": 584370810.0,
|
| 3025 |
+
"step": 3340
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 0.912977567323579,
|
| 3029 |
+
"grad_norm": 0.337890625,
|
| 3030 |
+
"learning_rate": 0.0002803062227840989,
|
| 3031 |
+
"loss": 1.0599,
|
| 3032 |
+
"mean_token_accuracy": 0.7450041811913252,
|
| 3033 |
+
"num_tokens": 586143330.0,
|
| 3034 |
+
"step": 3350
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.9157028734946941,
|
| 3038 |
+
"grad_norm": 0.345703125,
|
| 3039 |
+
"learning_rate": 0.0002796038769490097,
|
| 3040 |
+
"loss": 1.0129,
|
| 3041 |
+
"mean_token_accuracy": 0.753754030354321,
|
| 3042 |
+
"num_tokens": 587851884.0,
|
| 3043 |
+
"step": 3360
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 0.9184281796658094,
|
| 3047 |
+
"grad_norm": 0.3203125,
|
| 3048 |
+
"learning_rate": 0.00027890153111392055,
|
| 3049 |
+
"loss": 1.0408,
|
| 3050 |
+
"mean_token_accuracy": 0.7472209732979536,
|
| 3051 |
+
"num_tokens": 589601267.0,
|
| 3052 |
+
"step": 3370
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 0.9211534858369245,
|
| 3056 |
+
"grad_norm": 0.388671875,
|
| 3057 |
+
"learning_rate": 0.0002781991852788313,
|
| 3058 |
+
"loss": 1.0909,
|
| 3059 |
+
"mean_token_accuracy": 0.7383921964094042,
|
| 3060 |
+
"num_tokens": 591321205.0,
|
| 3061 |
+
"step": 3380
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.9238787920080397,
|
| 3065 |
+
"grad_norm": 0.291015625,
|
| 3066 |
+
"learning_rate": 0.0002774968394437421,
|
| 3067 |
+
"loss": 1.0126,
|
| 3068 |
+
"mean_token_accuracy": 0.7546688699163496,
|
| 3069 |
+
"num_tokens": 593110103.0,
|
| 3070 |
+
"step": 3390
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 0.9266040981791548,
|
| 3074 |
+
"grad_norm": 0.35546875,
|
| 3075 |
+
"learning_rate": 0.0002767944936086529,
|
| 3076 |
+
"loss": 1.0781,
|
| 3077 |
+
"mean_token_accuracy": 0.7418509462848306,
|
| 3078 |
+
"num_tokens": 594823039.0,
|
| 3079 |
+
"step": 3400
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 0.92932940435027,
|
| 3083 |
+
"grad_norm": 0.33203125,
|
| 3084 |
+
"learning_rate": 0.0002760921477735637,
|
| 3085 |
+
"loss": 1.0656,
|
| 3086 |
+
"mean_token_accuracy": 0.7450129883363843,
|
| 3087 |
+
"num_tokens": 596625643.0,
|
| 3088 |
+
"step": 3410
|
| 3089 |
+
},
|
| 3090 |
+
{
|
| 3091 |
+
"epoch": 0.9320547105213851,
|
| 3092 |
+
"grad_norm": 0.3671875,
|
| 3093 |
+
"learning_rate": 0.0002753898019384745,
|
| 3094 |
+
"loss": 1.0814,
|
| 3095 |
+
"mean_token_accuracy": 0.7387082081288099,
|
| 3096 |
+
"num_tokens": 598409404.0,
|
| 3097 |
+
"step": 3420
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.9347800166925003,
|
| 3101 |
+
"grad_norm": 0.40625,
|
| 3102 |
+
"learning_rate": 0.0002746874561033853,
|
| 3103 |
+
"loss": 1.0619,
|
| 3104 |
+
"mean_token_accuracy": 0.7441019948571921,
|
| 3105 |
+
"num_tokens": 600131817.0,
|
| 3106 |
+
"step": 3430
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.9375053228636154,
|
| 3110 |
+
"grad_norm": 0.310546875,
|
| 3111 |
+
"learning_rate": 0.0002739851102682961,
|
| 3112 |
+
"loss": 1.0625,
|
| 3113 |
+
"mean_token_accuracy": 0.7441184409894049,
|
| 3114 |
+
"num_tokens": 601867823.0,
|
| 3115 |
+
"step": 3440
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 0.9402306290347306,
|
| 3119 |
+
"grad_norm": 0.328125,
|
| 3120 |
+
"learning_rate": 0.0002732827644332069,
|
| 3121 |
+
"loss": 1.0346,
|
| 3122 |
+
"mean_token_accuracy": 0.7519477549009025,
|
| 3123 |
+
"num_tokens": 603591263.0,
|
| 3124 |
+
"step": 3450
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.9429559352058458,
|
| 3128 |
+
"grad_norm": 0.33203125,
|
| 3129 |
+
"learning_rate": 0.0002725804185981177,
|
| 3130 |
+
"loss": 1.0756,
|
| 3131 |
+
"mean_token_accuracy": 0.7429594827815891,
|
| 3132 |
+
"num_tokens": 605400422.0,
|
| 3133 |
+
"step": 3460
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 0.945681241376961,
|
| 3137 |
+
"grad_norm": 0.32421875,
|
| 3138 |
+
"learning_rate": 0.0002718780727630285,
|
| 3139 |
+
"loss": 1.0677,
|
| 3140 |
+
"mean_token_accuracy": 0.7448620780371129,
|
| 3141 |
+
"num_tokens": 607180330.0,
|
| 3142 |
+
"step": 3470
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 0.9484065475480761,
|
| 3146 |
+
"grad_norm": 0.322265625,
|
| 3147 |
+
"learning_rate": 0.00027117572692793936,
|
| 3148 |
+
"loss": 1.0215,
|
| 3149 |
+
"mean_token_accuracy": 0.7525013948790729,
|
| 3150 |
+
"num_tokens": 608937194.0,
|
| 3151 |
+
"step": 3480
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.9511318537191913,
|
| 3155 |
+
"grad_norm": 0.54296875,
|
| 3156 |
+
"learning_rate": 0.0002704733810928501,
|
| 3157 |
+
"loss": 1.0707,
|
| 3158 |
+
"mean_token_accuracy": 0.7420834172517061,
|
| 3159 |
+
"num_tokens": 610676168.0,
|
| 3160 |
+
"step": 3490
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 0.9538571598903064,
|
| 3164 |
+
"grad_norm": 0.30859375,
|
| 3165 |
+
"learning_rate": 0.00026977103525776093,
|
| 3166 |
+
"loss": 1.0088,
|
| 3167 |
+
"mean_token_accuracy": 0.7546906681731343,
|
| 3168 |
+
"num_tokens": 612491555.0,
|
| 3169 |
+
"step": 3500
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 0.9565824660614216,
|
| 3173 |
+
"grad_norm": 0.36328125,
|
| 3174 |
+
"learning_rate": 0.0002690686894226717,
|
| 3175 |
+
"loss": 1.0682,
|
| 3176 |
+
"mean_token_accuracy": 0.7417504930868745,
|
| 3177 |
+
"num_tokens": 614310820.0,
|
| 3178 |
+
"step": 3510
|
| 3179 |
+
},
|
| 3180 |
+
{
|
| 3181 |
+
"epoch": 0.9593077722325367,
|
| 3182 |
+
"grad_norm": 0.353515625,
|
| 3183 |
+
"learning_rate": 0.00026836634358758256,
|
| 3184 |
+
"loss": 1.0792,
|
| 3185 |
+
"mean_token_accuracy": 0.7415831151418388,
|
| 3186 |
+
"num_tokens": 616071087.0,
|
| 3187 |
+
"step": 3520
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.9620330784036519,
|
| 3191 |
+
"grad_norm": 0.34375,
|
| 3192 |
+
"learning_rate": 0.0002676639977524933,
|
| 3193 |
+
"loss": 1.0179,
|
| 3194 |
+
"mean_token_accuracy": 0.7520351181738079,
|
| 3195 |
+
"num_tokens": 617769166.0,
|
| 3196 |
+
"step": 3530
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 0.964758384574767,
|
| 3200 |
+
"grad_norm": 0.34375,
|
| 3201 |
+
"learning_rate": 0.00026696165191740414,
|
| 3202 |
+
"loss": 1.0445,
|
| 3203 |
+
"mean_token_accuracy": 0.7471835752017796,
|
| 3204 |
+
"num_tokens": 619538232.0,
|
| 3205 |
+
"step": 3540
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 0.9674836907458823,
|
| 3209 |
+
"grad_norm": 0.29296875,
|
| 3210 |
+
"learning_rate": 0.0002662593060823149,
|
| 3211 |
+
"loss": 1.0407,
|
| 3212 |
+
"mean_token_accuracy": 0.74965282054618,
|
| 3213 |
+
"num_tokens": 621303314.0,
|
| 3214 |
+
"step": 3550
|
| 3215 |
+
},
|
| 3216 |
+
{
|
| 3217 |
+
"epoch": 0.9702089969169974,
|
| 3218 |
+
"grad_norm": 0.298828125,
|
| 3219 |
+
"learning_rate": 0.00026555696024722577,
|
| 3220 |
+
"loss": 1.027,
|
| 3221 |
+
"mean_token_accuracy": 0.751960375905037,
|
| 3222 |
+
"num_tokens": 623100776.0,
|
| 3223 |
+
"step": 3560
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 0.9729343030881126,
|
| 3227 |
+
"grad_norm": 0.3125,
|
| 3228 |
+
"learning_rate": 0.00026485461441213653,
|
| 3229 |
+
"loss": 1.096,
|
| 3230 |
+
"mean_token_accuracy": 0.736579249240458,
|
| 3231 |
+
"num_tokens": 624821413.0,
|
| 3232 |
+
"step": 3570
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 0.9756596092592277,
|
| 3236 |
+
"grad_norm": 0.341796875,
|
| 3237 |
+
"learning_rate": 0.00026415226857704735,
|
| 3238 |
+
"loss": 1.0511,
|
| 3239 |
+
"mean_token_accuracy": 0.7452825047075748,
|
| 3240 |
+
"num_tokens": 626628545.0,
|
| 3241 |
+
"step": 3580
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 0.9783849154303429,
|
| 3245 |
+
"grad_norm": 0.318359375,
|
| 3246 |
+
"learning_rate": 0.00026344992274195816,
|
| 3247 |
+
"loss": 1.0388,
|
| 3248 |
+
"mean_token_accuracy": 0.749433082062751,
|
| 3249 |
+
"num_tokens": 628425036.0,
|
| 3250 |
+
"step": 3590
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.981110221601458,
|
| 3254 |
+
"grad_norm": 0.30859375,
|
| 3255 |
+
"learning_rate": 0.000262747576906869,
|
| 3256 |
+
"loss": 1.0046,
|
| 3257 |
+
"mean_token_accuracy": 0.7535642351955175,
|
| 3258 |
+
"num_tokens": 630092739.0,
|
| 3259 |
+
"step": 3600
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 0.9838355277725732,
|
| 3263 |
+
"grad_norm": 0.375,
|
| 3264 |
+
"learning_rate": 0.00026204523107177974,
|
| 3265 |
+
"loss": 1.0579,
|
| 3266 |
+
"mean_token_accuracy": 0.7460371427237987,
|
| 3267 |
+
"num_tokens": 631791605.0,
|
| 3268 |
+
"step": 3610
|
| 3269 |
+
},
|
| 3270 |
+
{
|
| 3271 |
+
"epoch": 0.9865608339436883,
|
| 3272 |
+
"grad_norm": 0.73046875,
|
| 3273 |
+
"learning_rate": 0.00026134288523669056,
|
| 3274 |
+
"loss": 1.0452,
|
| 3275 |
+
"mean_token_accuracy": 0.7458532767370343,
|
| 3276 |
+
"num_tokens": 633554055.0,
|
| 3277 |
+
"step": 3620
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 0.9892861401148035,
|
| 3281 |
+
"grad_norm": 0.328125,
|
| 3282 |
+
"learning_rate": 0.00026064053940160137,
|
| 3283 |
+
"loss": 1.0193,
|
| 3284 |
+
"mean_token_accuracy": 0.7518707301467658,
|
| 3285 |
+
"num_tokens": 635269789.0,
|
| 3286 |
+
"step": 3630
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.9920114462859186,
|
| 3290 |
+
"grad_norm": 0.31640625,
|
| 3291 |
+
"learning_rate": 0.00025993819356651213,
|
| 3292 |
+
"loss": 1.0367,
|
| 3293 |
+
"mean_token_accuracy": 0.7495086012408138,
|
| 3294 |
+
"num_tokens": 637078092.0,
|
| 3295 |
+
"step": 3640
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 0.9947367524570339,
|
| 3299 |
+
"grad_norm": 0.337890625,
|
| 3300 |
+
"learning_rate": 0.00025923584773142295,
|
| 3301 |
+
"loss": 1.0075,
|
| 3302 |
+
"mean_token_accuracy": 0.7556772115640342,
|
| 3303 |
+
"num_tokens": 638813927.0,
|
| 3304 |
+
"step": 3650
|
| 3305 |
+
},
|
| 3306 |
+
{
|
| 3307 |
+
"epoch": 0.997462058628149,
|
| 3308 |
+
"grad_norm": 0.34765625,
|
| 3309 |
+
"learning_rate": 0.0002585335018963337,
|
| 3310 |
+
"loss": 1.0366,
|
| 3311 |
+
"mean_token_accuracy": 0.7495333584956825,
|
| 3312 |
+
"num_tokens": 640594007.0,
|
| 3313 |
+
"step": 3660
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 1.0,
|
| 3317 |
+
"grad_norm": 0.1640625,
|
| 3318 |
+
"learning_rate": 0.0002578311560612446,
|
| 3319 |
+
"loss": 0.9358,
|
| 3320 |
+
"mean_token_accuracy": 0.7545788142105077,
|
| 3321 |
+
"num_tokens": 642209396.0,
|
| 3322 |
+
"step": 3670
|
| 3323 |
+
}
|
| 3324 |
+
],
|
| 3325 |
+
"logging_steps": 10,
|
| 3326 |
+
"max_steps": 7340,
|
| 3327 |
+
"num_input_tokens_seen": 0,
|
| 3328 |
+
"num_train_epochs": 2,
|
| 3329 |
+
"save_steps": 500.0,
|
| 3330 |
+
"stateful_callbacks": {
|
| 3331 |
+
"TrainerControl": {
|
| 3332 |
+
"args": {
|
| 3333 |
+
"should_epoch_stop": false,
|
| 3334 |
+
"should_evaluate": false,
|
| 3335 |
+
"should_log": false,
|
| 3336 |
+
"should_save": true,
|
| 3337 |
+
"should_training_stop": false
|
| 3338 |
+
},
|
| 3339 |
+
"attributes": {}
|
| 3340 |
+
}
|
| 3341 |
+
},
|
| 3342 |
+
"total_flos": 1.068172081287866e+19,
|
| 3343 |
+
"train_batch_size": 8,
|
| 3344 |
+
"trial_name": null,
|
| 3345 |
+
"trial_params": null
|
| 3346 |
+
}
|
checkpoint-3670/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f00d55cafeda09e6936676fbcbeac40ed9bcedc85bbbc85cdf29a53e944f42c
|
| 3 |
+
size 6072
|
checkpoint-7340/chat_template.jinja
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
{{- bos_token }}
|
| 3 |
+
{%- for message in messages %}
|
| 4 |
+
{%- if message['role'] == 'assistant' %}
|
| 5 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 6 |
+
' }}
|
| 7 |
+
{%- generation %}
|
| 8 |
+
{{- message['content'] + '<|eot_id|>' }}
|
| 9 |
+
{%- endgeneration %}
|
| 10 |
+
{{- '
|
| 11 |
+
' }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>' + '
|
| 14 |
+
' + message['content'] + '<|eot_id|>' + '
|
| 15 |
+
' }}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- endfor %}
|
| 18 |
+
{%- if add_generation_prompt %}
|
| 19 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>
|
| 20 |
+
' }}
|
| 21 |
+
{%- endif %}
|
checkpoint-7340/config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HymbaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"attn_factor": 0.5,
|
| 7 |
+
"attn_hidden_size": -1,
|
| 8 |
+
"attn_implementation": "flash_attention_2",
|
| 9 |
+
"attn_implementation_new": "flash_attention_2",
|
| 10 |
+
"attn_only_wo_proj": true,
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoConfig": "configuration_hymba.HymbaConfig",
|
| 13 |
+
"AutoModelForCausalLM": "modeling_hymba.HymbaForCausalLM"
|
| 14 |
+
},
|
| 15 |
+
"bos_token_id": 128000,
|
| 16 |
+
"calc_logits_for_entire_prompt": false,
|
| 17 |
+
"conv_dim": {
|
| 18 |
+
"0": 3200,
|
| 19 |
+
"1": 3200,
|
| 20 |
+
"10": 3200,
|
| 21 |
+
"11": 3200,
|
| 22 |
+
"12": 3200,
|
| 23 |
+
"13": 3200,
|
| 24 |
+
"14": 3200,
|
| 25 |
+
"15": 3200,
|
| 26 |
+
"16": 3200,
|
| 27 |
+
"17": 3200,
|
| 28 |
+
"18": 3200,
|
| 29 |
+
"19": 3200,
|
| 30 |
+
"2": 3200,
|
| 31 |
+
"20": 3200,
|
| 32 |
+
"21": 3200,
|
| 33 |
+
"22": 3200,
|
| 34 |
+
"23": 3200,
|
| 35 |
+
"24": 3200,
|
| 36 |
+
"25": 3200,
|
| 37 |
+
"26": 3200,
|
| 38 |
+
"27": 3200,
|
| 39 |
+
"28": 3200,
|
| 40 |
+
"29": 3200,
|
| 41 |
+
"3": 3200,
|
| 42 |
+
"30": 3200,
|
| 43 |
+
"31": 3200,
|
| 44 |
+
"4": 3200,
|
| 45 |
+
"5": 3200,
|
| 46 |
+
"6": 3200,
|
| 47 |
+
"7": 3200,
|
| 48 |
+
"8": 3200,
|
| 49 |
+
"9": 3200
|
| 50 |
+
},
|
| 51 |
+
"eos_token_id": [
|
| 52 |
+
128001,
|
| 53 |
+
128008,
|
| 54 |
+
128009
|
| 55 |
+
],
|
| 56 |
+
"global_attn_idx": [
|
| 57 |
+
0,
|
| 58 |
+
8,
|
| 59 |
+
15
|
| 60 |
+
],
|
| 61 |
+
"head_dim": 128,
|
| 62 |
+
"hidden_act": "silu",
|
| 63 |
+
"hidden_size": 2048,
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"intermediate_size": 8192,
|
| 66 |
+
"kq_head_dim": -1,
|
| 67 |
+
"kq_norm": "none",
|
| 68 |
+
"kv_reuse_every_i_layer": -1,
|
| 69 |
+
"kv_reuse_group": null,
|
| 70 |
+
"kv_weight_reuse": false,
|
| 71 |
+
"layer_type": [
|
| 72 |
+
"h",
|
| 73 |
+
"h",
|
| 74 |
+
"h",
|
| 75 |
+
"h",
|
| 76 |
+
"h",
|
| 77 |
+
"h",
|
| 78 |
+
"h",
|
| 79 |
+
"h",
|
| 80 |
+
"h",
|
| 81 |
+
"h",
|
| 82 |
+
"h",
|
| 83 |
+
"h",
|
| 84 |
+
"h",
|
| 85 |
+
"h",
|
| 86 |
+
"h",
|
| 87 |
+
"h"
|
| 88 |
+
],
|
| 89 |
+
"mamba_conv_bias": true,
|
| 90 |
+
"mamba_d_conv": 4,
|
| 91 |
+
"mamba_d_state": 16,
|
| 92 |
+
"mamba_dt_rank": 100,
|
| 93 |
+
"mamba_expand": 1,
|
| 94 |
+
"mamba_inner_layernorms": false,
|
| 95 |
+
"mamba_proj_bias": false,
|
| 96 |
+
"max_position_embeddings": 131072,
|
| 97 |
+
"memory_tokens_interspersed_every": 0,
|
| 98 |
+
"mlp_hidden_act": "silu",
|
| 99 |
+
"model_type": "hymba",
|
| 100 |
+
"num_attention_heads": 16,
|
| 101 |
+
"num_experts": 1,
|
| 102 |
+
"num_experts_per_tok": 1,
|
| 103 |
+
"num_hidden_layers": 16,
|
| 104 |
+
"num_key_value_heads": 4,
|
| 105 |
+
"num_mamba": 1,
|
| 106 |
+
"num_memory_tokens": 0,
|
| 107 |
+
"orig_max_position_embeddings": 2048,
|
| 108 |
+
"output_router_logits": false,
|
| 109 |
+
"pad_token_id": null,
|
| 110 |
+
"pure_attn": true,
|
| 111 |
+
"rms_norm_eps": 1e-05,
|
| 112 |
+
"rope": true,
|
| 113 |
+
"rope_scaling": {
|
| 114 |
+
"factor": 32.0,
|
| 115 |
+
"high_freq_factor": 4.0,
|
| 116 |
+
"low_freq_factor": 1.0,
|
| 117 |
+
"original_max_position_embeddings": 8192,
|
| 118 |
+
"rope_type": "llama3"
|
| 119 |
+
},
|
| 120 |
+
"rope_theta": 500000.0,
|
| 121 |
+
"rope_type": "ntk",
|
| 122 |
+
"router_aux_loss_coef": 0.001,
|
| 123 |
+
"seq_length": 8192,
|
| 124 |
+
"sliding_window": 256,
|
| 125 |
+
"tie_word_embeddings": true,
|
| 126 |
+
"torch_dtype": "bfloat16",
|
| 127 |
+
"transformers_version": "4.53.0",
|
| 128 |
+
"use_cache": false,
|
| 129 |
+
"use_mamba_kernels": true,
|
| 130 |
+
"v_head_dim": 128,
|
| 131 |
+
"vocab_size": 128256
|
| 132 |
+
}
|
checkpoint-7340/configuration_hymba.py
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
class HymbaConfig(PretrainedConfig):
|
| 6 |
+
|
| 7 |
+
model_type = "hymba"
|
| 8 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 9 |
+
|
| 10 |
+
def __init__(
|
| 11 |
+
self,
|
| 12 |
+
vocab_size=65536,
|
| 13 |
+
tie_word_embeddings=False,
|
| 14 |
+
hidden_size=4096,
|
| 15 |
+
intermediate_size=14336,
|
| 16 |
+
num_hidden_layers=32,
|
| 17 |
+
num_attention_heads=32,
|
| 18 |
+
num_key_value_heads=8,
|
| 19 |
+
hidden_act="silu",
|
| 20 |
+
initializer_range=0.02,
|
| 21 |
+
rms_norm_eps=1e-6,
|
| 22 |
+
attn_only_wo_proj=False,
|
| 23 |
+
use_cache=True,
|
| 24 |
+
calc_logits_for_entire_prompt=False,
|
| 25 |
+
output_router_logits=False,
|
| 26 |
+
router_aux_loss_coef=0.001,
|
| 27 |
+
pad_token_id=0,
|
| 28 |
+
bos_token_id=1,
|
| 29 |
+
eos_token_id=2,
|
| 30 |
+
sliding_window=None,
|
| 31 |
+
max_position_embeddings=262144,
|
| 32 |
+
orig_max_position_embeddings=None,
|
| 33 |
+
attention_dropout=0.0,
|
| 34 |
+
num_experts_per_tok=2,
|
| 35 |
+
num_experts=16,
|
| 36 |
+
use_mamba_kernels=True,
|
| 37 |
+
mamba_d_state=16,
|
| 38 |
+
mamba_d_conv=4,
|
| 39 |
+
mamba_expand=2,
|
| 40 |
+
mamba_dt_rank="auto",
|
| 41 |
+
mamba_conv_bias=True,
|
| 42 |
+
mamba_proj_bias=False,
|
| 43 |
+
mamba_inner_layernorms=True,
|
| 44 |
+
kv_reuse_every_i_layer=-1,
|
| 45 |
+
kv_reuse_group=None,
|
| 46 |
+
kv_weight_reuse=False,
|
| 47 |
+
global_attn_idx=None,
|
| 48 |
+
num_mamba=1,
|
| 49 |
+
pure_attn=False,
|
| 50 |
+
attn_implementation_new='sdpa',
|
| 51 |
+
rope_type=None,
|
| 52 |
+
attn_factor=0.5,
|
| 53 |
+
**kwargs,
|
| 54 |
+
):
|
| 55 |
+
self.vocab_size = vocab_size
|
| 56 |
+
self.tie_word_embeddings = tie_word_embeddings
|
| 57 |
+
self.hidden_size = hidden_size
|
| 58 |
+
self.intermediate_size = intermediate_size
|
| 59 |
+
self.num_hidden_layers = num_hidden_layers
|
| 60 |
+
self.num_attention_heads = num_attention_heads
|
| 61 |
+
self.sliding_window = sliding_window
|
| 62 |
+
self.max_position_embeddings = max_position_embeddings
|
| 63 |
+
self.orig_max_position_embeddings = orig_max_position_embeddings
|
| 64 |
+
self.attention_dropout = attention_dropout
|
| 65 |
+
self.attn_only_wo_proj = attn_only_wo_proj
|
| 66 |
+
|
| 67 |
+
if num_key_value_heads is None:
|
| 68 |
+
num_key_value_heads = num_attention_heads
|
| 69 |
+
|
| 70 |
+
self.num_key_value_heads = num_key_value_heads
|
| 71 |
+
self.hidden_act = hidden_act
|
| 72 |
+
self.initializer_range = initializer_range
|
| 73 |
+
self.rms_norm_eps = rms_norm_eps
|
| 74 |
+
|
| 75 |
+
self.use_cache = use_cache
|
| 76 |
+
self.calc_logits_for_entire_prompt = calc_logits_for_entire_prompt
|
| 77 |
+
self.output_router_logits = output_router_logits
|
| 78 |
+
self.router_aux_loss_coef = router_aux_loss_coef
|
| 79 |
+
|
| 80 |
+
self.num_experts_per_tok = num_experts_per_tok
|
| 81 |
+
self.num_experts = num_experts
|
| 82 |
+
|
| 83 |
+
self.use_mamba_kernels = use_mamba_kernels
|
| 84 |
+
self.mamba_d_state = mamba_d_state
|
| 85 |
+
self.mamba_d_conv = mamba_d_conv
|
| 86 |
+
self.mamba_expand = mamba_expand
|
| 87 |
+
self.mamba_dt_rank = math.ceil(self.hidden_size / 16) if mamba_dt_rank == "auto" else mamba_dt_rank
|
| 88 |
+
self.mamba_conv_bias = mamba_conv_bias
|
| 89 |
+
self.mamba_proj_bias = mamba_proj_bias
|
| 90 |
+
self.mamba_inner_layernorms = mamba_inner_layernorms
|
| 91 |
+
|
| 92 |
+
self.attn_hidden_size = kwargs.pop("attn_hidden_size", -1)
|
| 93 |
+
self.attn_factor = attn_factor
|
| 94 |
+
self.kq_head_dim = kwargs.pop("kq_head_dim", -1)
|
| 95 |
+
self.v_head_dim = kwargs.pop("v_head_dim", -1)
|
| 96 |
+
self.kq_norm = kwargs.pop("kq_norm", None)
|
| 97 |
+
self.rope = kwargs.pop("rope", False)
|
| 98 |
+
self.rope_theta = kwargs.pop("rope_theta", 10000.0)
|
| 99 |
+
self.num_memory_tokens = kwargs.pop("num_memory_tokens", 0)
|
| 100 |
+
self.memory_tokens_interspersed_every = kwargs.pop("memory_tokens_interspersed_every", 0)
|
| 101 |
+
|
| 102 |
+
self.kv_reuse_every_i_layer = kv_reuse_every_i_layer
|
| 103 |
+
self.kv_reuse_group = kv_reuse_group
|
| 104 |
+
self.kv_weight_reuse = kv_weight_reuse
|
| 105 |
+
|
| 106 |
+
self.global_attn_idx = global_attn_idx
|
| 107 |
+
|
| 108 |
+
self.num_mamba = num_mamba
|
| 109 |
+
|
| 110 |
+
self.attn_implementation_new = attn_implementation_new
|
| 111 |
+
|
| 112 |
+
self.rope_type = rope_type
|
| 113 |
+
|
| 114 |
+
self.pure_attn = pure_attn
|
| 115 |
+
|
| 116 |
+
super().__init__(
|
| 117 |
+
pad_token_id=pad_token_id,
|
| 118 |
+
bos_token_id=bos_token_id,
|
| 119 |
+
eos_token_id=eos_token_id,
|
| 120 |
+
tie_word_embeddings=tie_word_embeddings,
|
| 121 |
+
**kwargs,
|
| 122 |
+
)
|
checkpoint-7340/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"transformers_version": "4.53.0"
|
| 10 |
+
}
|
checkpoint-7340/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:538afd1aad45266f8557c2a29f8496a376e6cfc1f4a9e0d2c44519448b78e678
|
| 3 |
+
size 2471642200
|
checkpoint-7340/modeling_hymba.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7340/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e68a14e261ba2c7432b5cdc578e0e6750c8fc57e43598ff50ebb3d04447e417d
|
| 3 |
+
size 4943354422
|
checkpoint-7340/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
checkpoint-7340/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:332d348ed4d6c605735836627555000674392b75beb40082a7a320d4f9f70304
|
| 3 |
+
size 1064
|
checkpoint-7340/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
checkpoint-7340/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
checkpoint-7340/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|eot_id|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
checkpoint-7340/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7340/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f00d55cafeda09e6936676fbcbeac40ed9bcedc85bbbc85cdf29a53e944f42c
|
| 3 |
+
size 6072
|
config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HymbaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"attn_factor": 0.5,
|
| 7 |
+
"attn_hidden_size": -1,
|
| 8 |
+
"attn_implementation": "flash_attention_2",
|
| 9 |
+
"attn_implementation_new": "flash_attention_2",
|
| 10 |
+
"attn_only_wo_proj": true,
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoConfig": "configuration_hymba.HymbaConfig",
|
| 13 |
+
"AutoModelForCausalLM": "modeling_hymba.HymbaForCausalLM"
|
| 14 |
+
},
|
| 15 |
+
"bos_token_id": 128000,
|
| 16 |
+
"calc_logits_for_entire_prompt": false,
|
| 17 |
+
"conv_dim": {
|
| 18 |
+
"0": 3200,
|
| 19 |
+
"1": 3200,
|
| 20 |
+
"10": 3200,
|
| 21 |
+
"11": 3200,
|
| 22 |
+
"12": 3200,
|
| 23 |
+
"13": 3200,
|
| 24 |
+
"14": 3200,
|
| 25 |
+
"15": 3200,
|
| 26 |
+
"16": 3200,
|
| 27 |
+
"17": 3200,
|
| 28 |
+
"18": 3200,
|
| 29 |
+
"19": 3200,
|
| 30 |
+
"2": 3200,
|
| 31 |
+
"20": 3200,
|
| 32 |
+
"21": 3200,
|
| 33 |
+
"22": 3200,
|
| 34 |
+
"23": 3200,
|
| 35 |
+
"24": 3200,
|
| 36 |
+
"25": 3200,
|
| 37 |
+
"26": 3200,
|
| 38 |
+
"27": 3200,
|
| 39 |
+
"28": 3200,
|
| 40 |
+
"29": 3200,
|
| 41 |
+
"3": 3200,
|
| 42 |
+
"30": 3200,
|
| 43 |
+
"31": 3200,
|
| 44 |
+
"4": 3200,
|
| 45 |
+
"5": 3200,
|
| 46 |
+
"6": 3200,
|
| 47 |
+
"7": 3200,
|
| 48 |
+
"8": 3200,
|
| 49 |
+
"9": 3200
|
| 50 |
+
},
|
| 51 |
+
"eos_token_id": [
|
| 52 |
+
128001,
|
| 53 |
+
128008,
|
| 54 |
+
128009
|
| 55 |
+
],
|
| 56 |
+
"global_attn_idx": [
|
| 57 |
+
0,
|
| 58 |
+
8,
|
| 59 |
+
15
|
| 60 |
+
],
|
| 61 |
+
"head_dim": 128,
|
| 62 |
+
"hidden_act": "silu",
|
| 63 |
+
"hidden_size": 2048,
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"intermediate_size": 8192,
|
| 66 |
+
"kq_head_dim": -1,
|
| 67 |
+
"kq_norm": "none",
|
| 68 |
+
"kv_reuse_every_i_layer": -1,
|
| 69 |
+
"kv_reuse_group": null,
|
| 70 |
+
"kv_weight_reuse": false,
|
| 71 |
+
"layer_type": [
|
| 72 |
+
"h",
|
| 73 |
+
"h",
|
| 74 |
+
"h",
|
| 75 |
+
"h",
|
| 76 |
+
"h",
|
| 77 |
+
"h",
|
| 78 |
+
"h",
|
| 79 |
+
"h",
|
| 80 |
+
"h",
|
| 81 |
+
"h",
|
| 82 |
+
"h",
|
| 83 |
+
"h",
|
| 84 |
+
"h",
|
| 85 |
+
"h",
|
| 86 |
+
"h",
|
| 87 |
+
"h"
|
| 88 |
+
],
|
| 89 |
+
"mamba_conv_bias": true,
|
| 90 |
+
"mamba_d_conv": 4,
|
| 91 |
+
"mamba_d_state": 16,
|
| 92 |
+
"mamba_dt_rank": 100,
|
| 93 |
+
"mamba_expand": 1,
|
| 94 |
+
"mamba_inner_layernorms": false,
|
| 95 |
+
"mamba_proj_bias": false,
|
| 96 |
+
"max_position_embeddings": 131072,
|
| 97 |
+
"memory_tokens_interspersed_every": 0,
|
| 98 |
+
"mlp_hidden_act": "silu",
|
| 99 |
+
"model_type": "hymba",
|
| 100 |
+
"num_attention_heads": 16,
|
| 101 |
+
"num_experts": 1,
|
| 102 |
+
"num_experts_per_tok": 1,
|
| 103 |
+
"num_hidden_layers": 16,
|
| 104 |
+
"num_key_value_heads": 4,
|
| 105 |
+
"num_mamba": 1,
|
| 106 |
+
"num_memory_tokens": 0,
|
| 107 |
+
"orig_max_position_embeddings": 2048,
|
| 108 |
+
"output_router_logits": false,
|
| 109 |
+
"pad_token_id": null,
|
| 110 |
+
"pure_attn": true,
|
| 111 |
+
"rms_norm_eps": 1e-05,
|
| 112 |
+
"rope": true,
|
| 113 |
+
"rope_scaling": {
|
| 114 |
+
"factor": 32.0,
|
| 115 |
+
"high_freq_factor": 4.0,
|
| 116 |
+
"low_freq_factor": 1.0,
|
| 117 |
+
"original_max_position_embeddings": 8192,
|
| 118 |
+
"rope_type": "llama3"
|
| 119 |
+
},
|
| 120 |
+
"rope_theta": 500000.0,
|
| 121 |
+
"rope_type": "ntk",
|
| 122 |
+
"router_aux_loss_coef": 0.001,
|
| 123 |
+
"seq_length": 8192,
|
| 124 |
+
"sliding_window": 256,
|
| 125 |
+
"tie_word_embeddings": true,
|
| 126 |
+
"torch_dtype": "bfloat16",
|
| 127 |
+
"transformers_version": "4.53.0",
|
| 128 |
+
"use_cache": false,
|
| 129 |
+
"use_mamba_kernels": true,
|
| 130 |
+
"v_head_dim": 128,
|
| 131 |
+
"vocab_size": 128256
|
| 132 |
+
}
|
configuration_hymba.py
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
class HymbaConfig(PretrainedConfig):
|
| 6 |
+
|
| 7 |
+
model_type = "hymba"
|
| 8 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 9 |
+
|
| 10 |
+
def __init__(
|
| 11 |
+
self,
|
| 12 |
+
vocab_size=65536,
|
| 13 |
+
tie_word_embeddings=False,
|
| 14 |
+
hidden_size=4096,
|
| 15 |
+
intermediate_size=14336,
|
| 16 |
+
num_hidden_layers=32,
|
| 17 |
+
num_attention_heads=32,
|
| 18 |
+
num_key_value_heads=8,
|
| 19 |
+
hidden_act="silu",
|
| 20 |
+
initializer_range=0.02,
|
| 21 |
+
rms_norm_eps=1e-6,
|
| 22 |
+
attn_only_wo_proj=False,
|
| 23 |
+
use_cache=True,
|
| 24 |
+
calc_logits_for_entire_prompt=False,
|
| 25 |
+
output_router_logits=False,
|
| 26 |
+
router_aux_loss_coef=0.001,
|
| 27 |
+
pad_token_id=0,
|
| 28 |
+
bos_token_id=1,
|
| 29 |
+
eos_token_id=2,
|
| 30 |
+
sliding_window=None,
|
| 31 |
+
max_position_embeddings=262144,
|
| 32 |
+
orig_max_position_embeddings=None,
|
| 33 |
+
attention_dropout=0.0,
|
| 34 |
+
num_experts_per_tok=2,
|
| 35 |
+
num_experts=16,
|
| 36 |
+
use_mamba_kernels=True,
|
| 37 |
+
mamba_d_state=16,
|
| 38 |
+
mamba_d_conv=4,
|
| 39 |
+
mamba_expand=2,
|
| 40 |
+
mamba_dt_rank="auto",
|
| 41 |
+
mamba_conv_bias=True,
|
| 42 |
+
mamba_proj_bias=False,
|
| 43 |
+
mamba_inner_layernorms=True,
|
| 44 |
+
kv_reuse_every_i_layer=-1,
|
| 45 |
+
kv_reuse_group=None,
|
| 46 |
+
kv_weight_reuse=False,
|
| 47 |
+
global_attn_idx=None,
|
| 48 |
+
num_mamba=1,
|
| 49 |
+
pure_attn=False,
|
| 50 |
+
attn_implementation_new='sdpa',
|
| 51 |
+
rope_type=None,
|
| 52 |
+
attn_factor=0.5,
|
| 53 |
+
**kwargs,
|
| 54 |
+
):
|
| 55 |
+
self.vocab_size = vocab_size
|
| 56 |
+
self.tie_word_embeddings = tie_word_embeddings
|
| 57 |
+
self.hidden_size = hidden_size
|
| 58 |
+
self.intermediate_size = intermediate_size
|
| 59 |
+
self.num_hidden_layers = num_hidden_layers
|
| 60 |
+
self.num_attention_heads = num_attention_heads
|
| 61 |
+
self.sliding_window = sliding_window
|
| 62 |
+
self.max_position_embeddings = max_position_embeddings
|
| 63 |
+
self.orig_max_position_embeddings = orig_max_position_embeddings
|
| 64 |
+
self.attention_dropout = attention_dropout
|
| 65 |
+
self.attn_only_wo_proj = attn_only_wo_proj
|
| 66 |
+
|
| 67 |
+
if num_key_value_heads is None:
|
| 68 |
+
num_key_value_heads = num_attention_heads
|
| 69 |
+
|
| 70 |
+
self.num_key_value_heads = num_key_value_heads
|
| 71 |
+
self.hidden_act = hidden_act
|
| 72 |
+
self.initializer_range = initializer_range
|
| 73 |
+
self.rms_norm_eps = rms_norm_eps
|
| 74 |
+
|
| 75 |
+
self.use_cache = use_cache
|
| 76 |
+
self.calc_logits_for_entire_prompt = calc_logits_for_entire_prompt
|
| 77 |
+
self.output_router_logits = output_router_logits
|
| 78 |
+
self.router_aux_loss_coef = router_aux_loss_coef
|
| 79 |
+
|
| 80 |
+
self.num_experts_per_tok = num_experts_per_tok
|
| 81 |
+
self.num_experts = num_experts
|
| 82 |
+
|
| 83 |
+
self.use_mamba_kernels = use_mamba_kernels
|
| 84 |
+
self.mamba_d_state = mamba_d_state
|
| 85 |
+
self.mamba_d_conv = mamba_d_conv
|
| 86 |
+
self.mamba_expand = mamba_expand
|
| 87 |
+
self.mamba_dt_rank = math.ceil(self.hidden_size / 16) if mamba_dt_rank == "auto" else mamba_dt_rank
|
| 88 |
+
self.mamba_conv_bias = mamba_conv_bias
|
| 89 |
+
self.mamba_proj_bias = mamba_proj_bias
|
| 90 |
+
self.mamba_inner_layernorms = mamba_inner_layernorms
|
| 91 |
+
|
| 92 |
+
self.attn_hidden_size = kwargs.pop("attn_hidden_size", -1)
|
| 93 |
+
self.attn_factor = attn_factor
|
| 94 |
+
self.kq_head_dim = kwargs.pop("kq_head_dim", -1)
|
| 95 |
+
self.v_head_dim = kwargs.pop("v_head_dim", -1)
|
| 96 |
+
self.kq_norm = kwargs.pop("kq_norm", None)
|
| 97 |
+
self.rope = kwargs.pop("rope", False)
|
| 98 |
+
self.rope_theta = kwargs.pop("rope_theta", 10000.0)
|
| 99 |
+
self.num_memory_tokens = kwargs.pop("num_memory_tokens", 0)
|
| 100 |
+
self.memory_tokens_interspersed_every = kwargs.pop("memory_tokens_interspersed_every", 0)
|
| 101 |
+
|
| 102 |
+
self.kv_reuse_every_i_layer = kv_reuse_every_i_layer
|
| 103 |
+
self.kv_reuse_group = kv_reuse_group
|
| 104 |
+
self.kv_weight_reuse = kv_weight_reuse
|
| 105 |
+
|
| 106 |
+
self.global_attn_idx = global_attn_idx
|
| 107 |
+
|
| 108 |
+
self.num_mamba = num_mamba
|
| 109 |
+
|
| 110 |
+
self.attn_implementation_new = attn_implementation_new
|
| 111 |
+
|
| 112 |
+
self.rope_type = rope_type
|
| 113 |
+
|
| 114 |
+
self.pure_attn = pure_attn
|
| 115 |
+
|
| 116 |
+
super().__init__(
|
| 117 |
+
pad_token_id=pad_token_id,
|
| 118 |
+
bos_token_id=bos_token_id,
|
| 119 |
+
eos_token_id=eos_token_id,
|
| 120 |
+
tie_word_embeddings=tie_word_embeddings,
|
| 121 |
+
**kwargs,
|
| 122 |
+
)
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"transformers_version": "4.53.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:538afd1aad45266f8557c2a29f8496a376e6cfc1f4a9e0d2c44519448b78e678
|
| 3 |
+
size 2471642200
|
modeling_hymba.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|eot_id|>",
|
| 2055 |
+
"extra_special_tokens": {},
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f00d55cafeda09e6936676fbcbeac40ed9bcedc85bbbc85cdf29a53e944f42c
|
| 3 |
+
size 6072
|