Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-102/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,162 @@
+---
+library_name: peft
+tags:
+- axolotl
+- base_model:adapter:model
+- lora
+- transformers
+datasets:
+- hardlyworking/HardlyRPv2-10k
+base_model: model
+pipeline_tag: text-generation
+model-index:
+- name: outputs/out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.12.0.dev0`
+```yaml
+base_model: model
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: false
+cut_cross_entropy: true
+
+load_in_8bit: false
+load_in_4bit: true
+
+# for use with fft to only train on language model layers
+# unfrozen_parameters:
+  # - model.language_model.*
+  # - lm_head
+  # - embed_tokens
+
+
+chat_template: mistral_v7_tekken
+datasets:
+  - path: hardlyworking/HardlyRPv2-10k
+    type: chat_template
+    split: train
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+      user: human
+      assistant: gpt
+
+val_set_size: 0.0
+output_dir: ./outputs/out
+
+adapter: qlora
+lora_r: 32
+lora_alpha: 64
+lora_dropout: 0.05
+# lora_target_linear: # Does not work with gemma3n currently
+lora_target_modules:
+  - self_attn.q_proj
+  - self_attn.k_proj
+  - self_attn.v_proj
+  - self_attn.o_proj
+  - mlp.gate_proj
+  - mlp.up_proj
+  - mlp.down_proj
+
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 16
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+  unsloth: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch:
+saves_per_epoch: 4
+weight_decay: 0.0
+special_tokens:
+
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model was trained from scratch on the hardlyworking/HardlyRPv2-10k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 13
+- training_steps: 135
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.0
+- Transformers 4.55.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.21.4

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.up_proj",
+    "self_attn.q_proj",
+    "self_attn.o_proj",
+    "self_attn.k_proj",
+    "mlp.down_proj",
+    "mlp.gate_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292f11ea917be88d6cdf82d94a01c2fe0cff748f22bfff68556966618cae8920
+size 739321784

chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-102/README.md

@@ -0,0 +1,208 @@
+---
+base_model: model
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:model
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-102/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.up_proj",
+    "self_attn.q_proj",
+    "self_attn.o_proj",
+    "self_attn.k_proj",
+    "mlp.down_proj",
+    "mlp.gate_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-102/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66d8f7119e58ec01367fb85a6abaa1eb47c6e119edeb9a8dd1e5b3393444add
+size 739321784

checkpoint-102/chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-102/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593d7f5fcf6e4e421762793d533bd3f8719055ce3efd3be1208ec10b91546d78
+size 376056741

checkpoint-102/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8290a10374e21d73cfe0938ec8975684ad4f00a2201486ecbb737e779b98b5f6
+size 14645

checkpoint-102/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fc9a04baf6c238edd542dfc9e204d9c241397ad5906691d3d1b4f268f110a6
+size 1465

checkpoint-102/special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-102/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

checkpoint-102/trainer_state.json

@@ -0,0 +1,1054 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7531149053991694,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007383479464697739,
+      "grad_norm": 1.9591929912567139,
+      "learning_rate": 0.0,
+      "loss": 1.6228,
+      "memory/device_mem_reserved(gib)": 21.61,
+      "memory/max_mem_active(gib)": 21.2,
+      "memory/max_mem_allocated(gib)": 21.2,
+      "step": 1
+    },
+    {
+      "epoch": 0.014766958929395477,
+      "grad_norm": 1.4523507356643677,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.5769,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 2
+    },
+    {
+      "epoch": 0.022150438394093218,
+      "grad_norm": 1.1918187141418457,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.5435,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 3
+    },
+    {
+      "epoch": 0.029533917858790955,
+      "grad_norm": 0.8260876536369324,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 1.6523,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 4
+    },
+    {
+      "epoch": 0.03691739732348869,
+      "grad_norm": 0.8584926128387451,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.5745,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 5
+    },
+    {
+      "epoch": 0.044300876788186436,
+      "grad_norm": 0.6466429829597473,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.4759,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 6
+    },
+    {
+      "epoch": 0.05168435625288417,
+      "grad_norm": 0.5014482140541077,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 1.602,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 7
+    },
+    {
+      "epoch": 0.05906783571758191,
+      "grad_norm": 0.6017433404922485,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 1.4176,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 8
+    },
+    {
+      "epoch": 0.06645131518227965,
+      "grad_norm": 0.4612258970737457,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 1.5819,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 9
+    },
+    {
+      "epoch": 0.07383479464697738,
+      "grad_norm": 0.4430214464664459,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.561,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 10
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 0.3746771216392517,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 1.6744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 11
+    },
+    {
+      "epoch": 0.08860175357637287,
+      "grad_norm": 0.38248857855796814,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 1.5629,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 12
+    },
+    {
+      "epoch": 0.09598523304107061,
+      "grad_norm": 0.515844464302063,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 1.5264,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 13
+    },
+    {
+      "epoch": 0.10336871250576835,
+      "grad_norm": 0.3964424431324005,
+      "learning_rate": 0.0002,
+      "loss": 1.5398,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 14
+    },
+    {
+      "epoch": 0.11075219197046608,
+      "grad_norm": 0.4010593891143799,
+      "learning_rate": 0.0001999668467514313,
+      "loss": 1.4618,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 15
+    },
+    {
+      "epoch": 0.11813567143516382,
+      "grad_norm": 0.3192802965641022,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 1.6994,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 16
+    },
+    {
+      "epoch": 0.12551915089986157,
+      "grad_norm": 0.410099059343338,
+      "learning_rate": 0.00019970175264485266,
+      "loss": 1.5913,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 17
+    },
+    {
+      "epoch": 0.1329026303645593,
+      "grad_norm": 0.312429815530777,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 1.5701,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 18
+    },
+    {
+      "epoch": 0.14028610982925704,
+      "grad_norm": 0.2831230163574219,
+      "learning_rate": 0.00019917226741361015,
+      "loss": 1.5744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 19
+    },
+    {
+      "epoch": 0.14766958929395477,
+      "grad_norm": 0.3618868291378021,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 1.5185,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 20
+    },
+    {
+      "epoch": 0.15505306875865252,
+      "grad_norm": 0.3151628077030182,
+      "learning_rate": 0.00019837979515735166,
+      "loss": 1.5086,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 21
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 0.31955838203430176,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 1.6329,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 22
+    },
+    {
+      "epoch": 0.169820027688048,
+      "grad_norm": 0.3030437231063843,
+      "learning_rate": 0.00019732643737003827,
+      "loss": 1.6697,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 23
+    },
+    {
+      "epoch": 0.17720350715274574,
+      "grad_norm": 0.41288134455680847,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 1.7094,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 24
+    },
+    {
+      "epoch": 0.18458698661744347,
+      "grad_norm": 0.2887294888496399,
+      "learning_rate": 0.00019601498736716017,
+      "loss": 1.5554,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 25
+    },
+    {
+      "epoch": 0.19197046608214122,
+      "grad_norm": 0.3173791170120239,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 1.4404,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 26
+    },
+    {
+      "epoch": 0.19935394554683894,
+      "grad_norm": 0.2877439558506012,
+      "learning_rate": 0.00019444892287836613,
+      "loss": 1.4766,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 27
+    },
+    {
+      "epoch": 0.2067374250115367,
+      "grad_norm": 0.29286038875579834,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 1.5156,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 28
+    },
+    {
+      "epoch": 0.2141209044762344,
+      "grad_norm": 0.27713659405708313,
+      "learning_rate": 0.00019263239682514952,
+      "loss": 1.5153,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 29
+    },
+    {
+      "epoch": 0.22150438394093216,
+      "grad_norm": 0.29187655448913574,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 1.6036,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 30
+    },
+    {
+      "epoch": 0.22888786340562992,
+      "grad_norm": 0.2671583890914917,
+      "learning_rate": 0.00019057022630804716,
+      "loss": 1.4675,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 31
+    },
+    {
+      "epoch": 0.23627134287032764,
+      "grad_norm": 0.2679831087589264,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 1.581,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 32
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 0.26359617710113525,
+      "learning_rate": 0.00018826787983255473,
+      "loss": 1.4674,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 33
+    },
+    {
+      "epoch": 0.25103830179972314,
+      "grad_norm": 0.30446046590805054,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 1.5038,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 34
+    },
+    {
+      "epoch": 0.25842178126442084,
+      "grad_norm": 0.3004315197467804,
+      "learning_rate": 0.00018573146280763324,
+      "loss": 1.4024,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 35
+    },
+    {
+      "epoch": 0.2658052607291186,
+      "grad_norm": 0.27353399991989136,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 1.3652,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 36
+    },
+    {
+      "epoch": 0.27318874019381634,
+      "grad_norm": 0.2659265995025635,
+      "learning_rate": 0.0001829677013552619,
+      "loss": 1.4905,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 37
+    },
+    {
+      "epoch": 0.2805722196585141,
+      "grad_norm": 0.2703750431537628,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 1.3298,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 38
+    },
+    {
+      "epoch": 0.28795569912321184,
+      "grad_norm": 0.29322877526283264,
+      "learning_rate": 0.00017998392447397197,
+      "loss": 1.3639,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 39
+    },
+    {
+      "epoch": 0.29533917858790953,
+      "grad_norm": 0.26927265524864197,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 1.4849,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 40
+    },
+    {
+      "epoch": 0.3027226580526073,
+      "grad_norm": 0.26683205366134644,
+      "learning_rate": 0.00017678804460366,
+      "loss": 1.4523,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 41
+    },
+    {
+      "epoch": 0.31010613751730504,
+      "grad_norm": 0.26909339427948,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 1.6047,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 42
+    },
+    {
+      "epoch": 0.3174896169820028,
+      "grad_norm": 0.2938016355037689,
+      "learning_rate": 0.00017338853664321992,
+      "loss": 1.3858,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 43
+    },
+    {
+      "epoch": 0.3248730964467005,
+      "grad_norm": 0.28290048241615295,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 1.3671,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 44
+    },
+    {
+      "epoch": 0.33225657591139823,
+      "grad_norm": 0.2870519161224365,
+      "learning_rate": 0.00016979441547663435,
+      "loss": 1.5334,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 45
+    },
+    {
+      "epoch": 0.339640055376096,
+      "grad_norm": 0.26375913619995117,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 1.5627,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 46
+    },
+    {
+      "epoch": 0.34702353484079373,
+      "grad_norm": 0.26975446939468384,
+      "learning_rate": 0.00016601521206712318,
+      "loss": 1.4987,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 47
+    },
+    {
+      "epoch": 0.3544070143054915,
+      "grad_norm": 0.30166226625442505,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 1.5128,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 48
+    },
+    {
+      "epoch": 0.3617904937701892,
+      "grad_norm": 0.29190436005592346,
+      "learning_rate": 0.00016206094818274229,
+      "loss": 1.4914,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 49
+    },
+    {
+      "epoch": 0.36917397323488693,
+      "grad_norm": 0.2847207486629486,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 1.4755,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 50
+    },
+    {
+      "epoch": 0.3765574526995847,
+      "grad_norm": 0.2877140939235687,
+      "learning_rate": 0.00015794210982045636,
+      "loss": 1.422,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 51
+    },
+    {
+      "epoch": 0.38394093216428243,
+      "grad_norm": 0.2705255150794983,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 1.4822,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 52
+    },
+    {
+      "epoch": 0.3913244116289802,
+      "grad_norm": 0.2597866654396057,
+      "learning_rate": 0.00015366961939916008,
+      "loss": 1.5088,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 53
+    },
+    {
+      "epoch": 0.3987078910936779,
+      "grad_norm": 0.2965547740459442,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 1.5346,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 54
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 0.2670862078666687,
+      "learning_rate": 0.00014925480679538647,
+      "loss": 1.5695,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 55
+    },
+    {
+      "epoch": 0.4134748500230734,
+      "grad_norm": 0.30679062008857727,
+      "learning_rate": 0.000146997674302732,
+      "loss": 1.6911,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 56
+    },
+    {
+      "epoch": 0.42085832948777113,
+      "grad_norm": 0.2812528908252716,
+      "learning_rate": 0.0001447093792985114,
+      "loss": 1.664,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 57
+    },
+    {
+      "epoch": 0.4282418089524688,
+      "grad_norm": 0.26079821586608887,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 1.3911,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 58
+    },
+    {
+      "epoch": 0.4356252884171666,
+      "grad_norm": 0.3026648461818695,
+      "learning_rate": 0.00014004539056512667,
+      "loss": 1.5685,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 59
+    },
+    {
+      "epoch": 0.44300876788186433,
+      "grad_norm": 0.28435277938842773,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 1.3599,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 60
+    },
+    {
+      "epoch": 0.4503922473465621,
+      "grad_norm": 0.29877325892448425,
+      "learning_rate": 0.0001352752086549095,
+      "loss": 1.5173,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 61
+    },
+    {
+      "epoch": 0.45777572681125983,
+      "grad_norm": 0.29666033387184143,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 1.5017,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 62
+    },
+    {
+      "epoch": 0.4651592062759575,
+      "grad_norm": 0.26934438943862915,
+      "learning_rate": 0.0001304114832327518,
+      "loss": 1.4674,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 63
+    },
+    {
+      "epoch": 0.4725426857406553,
+      "grad_norm": 0.30038923025131226,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 1.5306,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 64
+    },
+    {
+      "epoch": 0.47992616520535303,
+      "grad_norm": 0.2799171805381775,
+      "learning_rate": 0.00012546711202412287,
+      "loss": 1.4696,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 65
+    },
+    {
+      "epoch": 0.4873096446700508,
+      "grad_norm": 0.313919335603714,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 1.5927,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 66
+    },
+    {
+      "epoch": 0.4946931241347485,
+      "grad_norm": 0.27579808235168457,
+      "learning_rate": 0.0001204552066126201,
+      "loss": 1.4654,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 67
+    },
+    {
+      "epoch": 0.5020766035994463,
+      "grad_norm": 0.28434908390045166,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 1.5039,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 68
+    },
+    {
+      "epoch": 0.509460083064144,
+      "grad_norm": 0.2828267514705658,
+      "learning_rate": 0.0001153890576704062,
+      "loss": 1.6203,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 69
+    },
+    {
+      "epoch": 0.5168435625288417,
+      "grad_norm": 0.30293530225753784,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 1.5628,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 70
+    },
+    {
+      "epoch": 0.5242270419935394,
+      "grad_norm": 0.2633240520954132,
+      "learning_rate": 0.00011028209971373605,
+      "loss": 1.5666,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 71
+    },
+    {
+      "epoch": 0.5316105214582372,
+      "grad_norm": 0.24525777995586395,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 1.592,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 72
+    },
+    {
+      "epoch": 0.5389940009229349,
+      "grad_norm": 0.27619901299476624,
+      "learning_rate": 0.00010514787547703466,
+      "loss": 1.6212,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 73
+    },
+    {
+      "epoch": 0.5463774803876327,
+      "grad_norm": 0.2783447504043579,
+      "learning_rate": 0.00010257479136549889,
+      "loss": 1.457,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 74
+    },
+    {
+      "epoch": 0.5537609598523304,
+      "grad_norm": 0.2755623459815979,
+      "learning_rate": 0.0001,
+      "loss": 1.3652,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 75
+    },
+    {
+      "epoch": 0.5611444393170282,
+      "grad_norm": 0.28049108386039734,
+      "learning_rate": 9.742520863450115e-05,
+      "loss": 1.4187,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 76
+    },
+    {
+      "epoch": 0.5685279187817259,
+      "grad_norm": 0.27499496936798096,
+      "learning_rate": 9.485212452296535e-05,
+      "loss": 1.5488,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 77
+    },
+    {
+      "epoch": 0.5759113982464237,
+      "grad_norm": 0.288296639919281,
+      "learning_rate": 9.228245378733537e-05,
+      "loss": 1.412,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 78
+    },
+    {
+      "epoch": 0.5832948777111213,
+      "grad_norm": 0.35849323868751526,
+      "learning_rate": 8.971790028626395e-05,
+      "loss": 1.5214,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 79
+    },
+    {
+      "epoch": 0.5906783571758191,
+      "grad_norm": 0.2951800525188446,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 1.4837,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 80
+    },
+    {
+      "epoch": 0.5980618366405168,
+      "grad_norm": 0.2763918340206146,
+      "learning_rate": 8.461094232959381e-05,
+      "loss": 1.5419,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 81
+    },
+    {
+      "epoch": 0.6054453161052146,
+      "grad_norm": 0.2745305895805359,
+      "learning_rate": 8.207192411892646e-05,
+      "loss": 1.4921,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 82
+    },
+    {
+      "epoch": 0.6128287955699123,
+      "grad_norm": 0.30081912875175476,
+      "learning_rate": 7.954479338737995e-05,
+      "loss": 1.4745,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 83
+    },
+    {
+      "epoch": 0.6202122750346101,
+      "grad_norm": 0.27640482783317566,
+      "learning_rate": 7.703122578682046e-05,
+      "loss": 1.4461,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 84
+    },
+    {
+      "epoch": 0.6275957544993078,
+      "grad_norm": 0.3407949209213257,
+      "learning_rate": 7.453288797587714e-05,
+      "loss": 1.617,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 85
+    },
+    {
+      "epoch": 0.6349792339640056,
+      "grad_norm": 0.2856479287147522,
+      "learning_rate": 7.205143651483906e-05,
+      "loss": 1.6538,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 86
+    },
+    {
+      "epoch": 0.6423627134287033,
+      "grad_norm": 0.39668434858322144,
+      "learning_rate": 6.958851676724823e-05,
+      "loss": 1.5753,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 87
+    },
+    {
+      "epoch": 0.649746192893401,
+      "grad_norm": 0.28521108627319336,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 1.3448,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 88
+    },
+    {
+      "epoch": 0.6571296723580987,
+      "grad_norm": 0.2806543707847595,
+      "learning_rate": 6.472479134509052e-05,
+      "loss": 1.6431,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 89
+    },
+    {
+      "epoch": 0.6645131518227965,
+      "grad_norm": 0.28897204995155334,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 1.5744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 90
+    },
+    {
+      "epoch": 0.6718966312874942,
+      "grad_norm": 0.25295817852020264,
+      "learning_rate": 5.9954609434873344e-05,
+      "loss": 1.4552,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 91
+    },
+    {
+      "epoch": 0.679280110752192,
+      "grad_norm": 0.2824646234512329,
+      "learning_rate": 5.7608560929013946e-05,
+      "loss": 1.4193,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 92
+    },
+    {
+      "epoch": 0.6866635902168897,
+      "grad_norm": 0.27227288484573364,
+      "learning_rate": 5.5290620701488594e-05,
+      "loss": 1.4602,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 93
+    },
+    {
+      "epoch": 0.6940470696815875,
+      "grad_norm": 0.26284658908843994,
+      "learning_rate": 5.300232569726804e-05,
+      "loss": 1.5947,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 94
+    },
+    {
+      "epoch": 0.7014305491462852,
+      "grad_norm": 0.26174792647361755,
+      "learning_rate": 5.074519320461357e-05,
+      "loss": 1.4122,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 95
+    },
+    {
+      "epoch": 0.708814028610983,
+      "grad_norm": 0.3069747984409332,
+      "learning_rate": 4.852071984901696e-05,
+      "loss": 1.4805,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 96
+    },
+    {
+      "epoch": 0.7161975080756806,
+      "grad_norm": 0.32007896900177,
+      "learning_rate": 4.633038060083996e-05,
+      "loss": 1.3798,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 97
+    },
+    {
+      "epoch": 0.7235809875403784,
+      "grad_norm": 0.26006585359573364,
+      "learning_rate": 4.417562779731355e-05,
+      "loss": 1.4974,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 98
+    },
+    {
+      "epoch": 0.7309644670050761,
+      "grad_norm": 0.2552710473537445,
+      "learning_rate": 4.205789017954364e-05,
+      "loss": 1.4851,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 99
+    },
+    {
+      "epoch": 0.7383479464697739,
+      "grad_norm": 0.23933957517147064,
+      "learning_rate": 3.997857194516319e-05,
+      "loss": 1.5046,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 100
+    },
+    {
+      "epoch": 0.7457314259344716,
+      "grad_norm": 0.2627595067024231,
+      "learning_rate": 3.793905181725772e-05,
+      "loss": 1.4958,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 101
+    },
+    {
+      "epoch": 0.7531149053991694,
+      "grad_norm": 0.3138872981071472,
+      "learning_rate": 3.594068213018249e-05,
+      "loss": 1.4714,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 102
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 34,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.851878167145349e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-102/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fcfaa0586b6a2ecea53c5d5918e29b57140459bd84f8ccd10b223317f2666e
+size 10001

checkpoint-135/README.md

@@ -0,0 +1,208 @@
+---
+base_model: model
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:model
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-135/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.up_proj",
+    "self_attn.q_proj",
+    "self_attn.o_proj",
+    "self_attn.k_proj",
+    "mlp.down_proj",
+    "mlp.gate_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-135/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292f11ea917be88d6cdf82d94a01c2fe0cff748f22bfff68556966618cae8920
+size 739321784

checkpoint-135/chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-135/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5b44d40fdb0aa2f0eca1fa0242651ceeb819170657cb2a24da6b5fb2bbfb14
+size 376056741

checkpoint-135/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf0f29a7ba7038a6c0c83f621da840ae793b1a307ea466896e2934173348c8e
+size 14645

checkpoint-135/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfa4c2e04867bb2d10c95a968a961b1ea1c52b991cddcab18342d22891578b9
+size 1465

checkpoint-135/special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-135/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

checkpoint-135/trainer_state.json

@@ -0,0 +1,1384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9967697277341947,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007383479464697739,
+      "grad_norm": 1.9591929912567139,
+      "learning_rate": 0.0,
+      "loss": 1.6228,
+      "memory/device_mem_reserved(gib)": 21.61,
+      "memory/max_mem_active(gib)": 21.2,
+      "memory/max_mem_allocated(gib)": 21.2,
+      "step": 1
+    },
+    {
+      "epoch": 0.014766958929395477,
+      "grad_norm": 1.4523507356643677,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.5769,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 2
+    },
+    {
+      "epoch": 0.022150438394093218,
+      "grad_norm": 1.1918187141418457,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.5435,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 3
+    },
+    {
+      "epoch": 0.029533917858790955,
+      "grad_norm": 0.8260876536369324,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 1.6523,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 4
+    },
+    {
+      "epoch": 0.03691739732348869,
+      "grad_norm": 0.8584926128387451,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.5745,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 5
+    },
+    {
+      "epoch": 0.044300876788186436,
+      "grad_norm": 0.6466429829597473,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.4759,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 6
+    },
+    {
+      "epoch": 0.05168435625288417,
+      "grad_norm": 0.5014482140541077,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 1.602,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 7
+    },
+    {
+      "epoch": 0.05906783571758191,
+      "grad_norm": 0.6017433404922485,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 1.4176,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 8
+    },
+    {
+      "epoch": 0.06645131518227965,
+      "grad_norm": 0.4612258970737457,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 1.5819,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 9
+    },
+    {
+      "epoch": 0.07383479464697738,
+      "grad_norm": 0.4430214464664459,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.561,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 10
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 0.3746771216392517,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 1.6744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 11
+    },
+    {
+      "epoch": 0.08860175357637287,
+      "grad_norm": 0.38248857855796814,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 1.5629,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 12
+    },
+    {
+      "epoch": 0.09598523304107061,
+      "grad_norm": 0.515844464302063,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 1.5264,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 13
+    },
+    {
+      "epoch": 0.10336871250576835,
+      "grad_norm": 0.3964424431324005,
+      "learning_rate": 0.0002,
+      "loss": 1.5398,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 14
+    },
+    {
+      "epoch": 0.11075219197046608,
+      "grad_norm": 0.4010593891143799,
+      "learning_rate": 0.0001999668467514313,
+      "loss": 1.4618,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 15
+    },
+    {
+      "epoch": 0.11813567143516382,
+      "grad_norm": 0.3192802965641022,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 1.6994,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 16
+    },
+    {
+      "epoch": 0.12551915089986157,
+      "grad_norm": 0.410099059343338,
+      "learning_rate": 0.00019970175264485266,
+      "loss": 1.5913,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 17
+    },
+    {
+      "epoch": 0.1329026303645593,
+      "grad_norm": 0.312429815530777,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 1.5701,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 18
+    },
+    {
+      "epoch": 0.14028610982925704,
+      "grad_norm": 0.2831230163574219,
+      "learning_rate": 0.00019917226741361015,
+      "loss": 1.5744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 19
+    },
+    {
+      "epoch": 0.14766958929395477,
+      "grad_norm": 0.3618868291378021,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 1.5185,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 20
+    },
+    {
+      "epoch": 0.15505306875865252,
+      "grad_norm": 0.3151628077030182,
+      "learning_rate": 0.00019837979515735166,
+      "loss": 1.5086,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 21
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 0.31955838203430176,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 1.6329,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 22
+    },
+    {
+      "epoch": 0.169820027688048,
+      "grad_norm": 0.3030437231063843,
+      "learning_rate": 0.00019732643737003827,
+      "loss": 1.6697,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 23
+    },
+    {
+      "epoch": 0.17720350715274574,
+      "grad_norm": 0.41288134455680847,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 1.7094,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 24
+    },
+    {
+      "epoch": 0.18458698661744347,
+      "grad_norm": 0.2887294888496399,
+      "learning_rate": 0.00019601498736716017,
+      "loss": 1.5554,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 25
+    },
+    {
+      "epoch": 0.19197046608214122,
+      "grad_norm": 0.3173791170120239,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 1.4404,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 26
+    },
+    {
+      "epoch": 0.19935394554683894,
+      "grad_norm": 0.2877439558506012,
+      "learning_rate": 0.00019444892287836613,
+      "loss": 1.4766,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 27
+    },
+    {
+      "epoch": 0.2067374250115367,
+      "grad_norm": 0.29286038875579834,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 1.5156,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 28
+    },
+    {
+      "epoch": 0.2141209044762344,
+      "grad_norm": 0.27713659405708313,
+      "learning_rate": 0.00019263239682514952,
+      "loss": 1.5153,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 29
+    },
+    {
+      "epoch": 0.22150438394093216,
+      "grad_norm": 0.29187655448913574,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 1.6036,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 30
+    },
+    {
+      "epoch": 0.22888786340562992,
+      "grad_norm": 0.2671583890914917,
+      "learning_rate": 0.00019057022630804716,
+      "loss": 1.4675,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 31
+    },
+    {
+      "epoch": 0.23627134287032764,
+      "grad_norm": 0.2679831087589264,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 1.581,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 32
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 0.26359617710113525,
+      "learning_rate": 0.00018826787983255473,
+      "loss": 1.4674,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 33
+    },
+    {
+      "epoch": 0.25103830179972314,
+      "grad_norm": 0.30446046590805054,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 1.5038,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 34
+    },
+    {
+      "epoch": 0.25842178126442084,
+      "grad_norm": 0.3004315197467804,
+      "learning_rate": 0.00018573146280763324,
+      "loss": 1.4024,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 35
+    },
+    {
+      "epoch": 0.2658052607291186,
+      "grad_norm": 0.27353399991989136,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 1.3652,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 36
+    },
+    {
+      "epoch": 0.27318874019381634,
+      "grad_norm": 0.2659265995025635,
+      "learning_rate": 0.0001829677013552619,
+      "loss": 1.4905,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 37
+    },
+    {
+      "epoch": 0.2805722196585141,
+      "grad_norm": 0.2703750431537628,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 1.3298,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 38
+    },
+    {
+      "epoch": 0.28795569912321184,
+      "grad_norm": 0.29322877526283264,
+      "learning_rate": 0.00017998392447397197,
+      "loss": 1.3639,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 39
+    },
+    {
+      "epoch": 0.29533917858790953,
+      "grad_norm": 0.26927265524864197,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 1.4849,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 40
+    },
+    {
+      "epoch": 0.3027226580526073,
+      "grad_norm": 0.26683205366134644,
+      "learning_rate": 0.00017678804460366,
+      "loss": 1.4523,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 41
+    },
+    {
+      "epoch": 0.31010613751730504,
+      "grad_norm": 0.26909339427948,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 1.6047,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 42
+    },
+    {
+      "epoch": 0.3174896169820028,
+      "grad_norm": 0.2938016355037689,
+      "learning_rate": 0.00017338853664321992,
+      "loss": 1.3858,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 43
+    },
+    {
+      "epoch": 0.3248730964467005,
+      "grad_norm": 0.28290048241615295,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 1.3671,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 44
+    },
+    {
+      "epoch": 0.33225657591139823,
+      "grad_norm": 0.2870519161224365,
+      "learning_rate": 0.00016979441547663435,
+      "loss": 1.5334,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 45
+    },
+    {
+      "epoch": 0.339640055376096,
+      "grad_norm": 0.26375913619995117,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 1.5627,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 46
+    },
+    {
+      "epoch": 0.34702353484079373,
+      "grad_norm": 0.26975446939468384,
+      "learning_rate": 0.00016601521206712318,
+      "loss": 1.4987,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 47
+    },
+    {
+      "epoch": 0.3544070143054915,
+      "grad_norm": 0.30166226625442505,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 1.5128,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 48
+    },
+    {
+      "epoch": 0.3617904937701892,
+      "grad_norm": 0.29190436005592346,
+      "learning_rate": 0.00016206094818274229,
+      "loss": 1.4914,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 49
+    },
+    {
+      "epoch": 0.36917397323488693,
+      "grad_norm": 0.2847207486629486,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 1.4755,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 50
+    },
+    {
+      "epoch": 0.3765574526995847,
+      "grad_norm": 0.2877140939235687,
+      "learning_rate": 0.00015794210982045636,
+      "loss": 1.422,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 51
+    },
+    {
+      "epoch": 0.38394093216428243,
+      "grad_norm": 0.2705255150794983,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 1.4822,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 52
+    },
+    {
+      "epoch": 0.3913244116289802,
+      "grad_norm": 0.2597866654396057,
+      "learning_rate": 0.00015366961939916008,
+      "loss": 1.5088,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 53
+    },
+    {
+      "epoch": 0.3987078910936779,
+      "grad_norm": 0.2965547740459442,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 1.5346,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 54
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 0.2670862078666687,
+      "learning_rate": 0.00014925480679538647,
+      "loss": 1.5695,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 55
+    },
+    {
+      "epoch": 0.4134748500230734,
+      "grad_norm": 0.30679062008857727,
+      "learning_rate": 0.000146997674302732,
+      "loss": 1.6911,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 56
+    },
+    {
+      "epoch": 0.42085832948777113,
+      "grad_norm": 0.2812528908252716,
+      "learning_rate": 0.0001447093792985114,
+      "loss": 1.664,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 57
+    },
+    {
+      "epoch": 0.4282418089524688,
+      "grad_norm": 0.26079821586608887,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 1.3911,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 58
+    },
+    {
+      "epoch": 0.4356252884171666,
+      "grad_norm": 0.3026648461818695,
+      "learning_rate": 0.00014004539056512667,
+      "loss": 1.5685,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 59
+    },
+    {
+      "epoch": 0.44300876788186433,
+      "grad_norm": 0.28435277938842773,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 1.3599,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 60
+    },
+    {
+      "epoch": 0.4503922473465621,
+      "grad_norm": 0.29877325892448425,
+      "learning_rate": 0.0001352752086549095,
+      "loss": 1.5173,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 61
+    },
+    {
+      "epoch": 0.45777572681125983,
+      "grad_norm": 0.29666033387184143,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 1.5017,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 62
+    },
+    {
+      "epoch": 0.4651592062759575,
+      "grad_norm": 0.26934438943862915,
+      "learning_rate": 0.0001304114832327518,
+      "loss": 1.4674,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 63
+    },
+    {
+      "epoch": 0.4725426857406553,
+      "grad_norm": 0.30038923025131226,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 1.5306,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 64
+    },
+    {
+      "epoch": 0.47992616520535303,
+      "grad_norm": 0.2799171805381775,
+      "learning_rate": 0.00012546711202412287,
+      "loss": 1.4696,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 65
+    },
+    {
+      "epoch": 0.4873096446700508,
+      "grad_norm": 0.313919335603714,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 1.5927,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 66
+    },
+    {
+      "epoch": 0.4946931241347485,
+      "grad_norm": 0.27579808235168457,
+      "learning_rate": 0.0001204552066126201,
+      "loss": 1.4654,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 67
+    },
+    {
+      "epoch": 0.5020766035994463,
+      "grad_norm": 0.28434908390045166,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 1.5039,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 68
+    },
+    {
+      "epoch": 0.509460083064144,
+      "grad_norm": 0.2828267514705658,
+      "learning_rate": 0.0001153890576704062,
+      "loss": 1.6203,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 69
+    },
+    {
+      "epoch": 0.5168435625288417,
+      "grad_norm": 0.30293530225753784,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 1.5628,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 70
+    },
+    {
+      "epoch": 0.5242270419935394,
+      "grad_norm": 0.2633240520954132,
+      "learning_rate": 0.00011028209971373605,
+      "loss": 1.5666,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 71
+    },
+    {
+      "epoch": 0.5316105214582372,
+      "grad_norm": 0.24525777995586395,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 1.592,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 72
+    },
+    {
+      "epoch": 0.5389940009229349,
+      "grad_norm": 0.27619901299476624,
+      "learning_rate": 0.00010514787547703466,
+      "loss": 1.6212,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 73
+    },
+    {
+      "epoch": 0.5463774803876327,
+      "grad_norm": 0.2783447504043579,
+      "learning_rate": 0.00010257479136549889,
+      "loss": 1.457,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 74
+    },
+    {
+      "epoch": 0.5537609598523304,
+      "grad_norm": 0.2755623459815979,
+      "learning_rate": 0.0001,
+      "loss": 1.3652,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 75
+    },
+    {
+      "epoch": 0.5611444393170282,
+      "grad_norm": 0.28049108386039734,
+      "learning_rate": 9.742520863450115e-05,
+      "loss": 1.4187,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 76
+    },
+    {
+      "epoch": 0.5685279187817259,
+      "grad_norm": 0.27499496936798096,
+      "learning_rate": 9.485212452296535e-05,
+      "loss": 1.5488,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 77
+    },
+    {
+      "epoch": 0.5759113982464237,
+      "grad_norm": 0.288296639919281,
+      "learning_rate": 9.228245378733537e-05,
+      "loss": 1.412,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 78
+    },
+    {
+      "epoch": 0.5832948777111213,
+      "grad_norm": 0.35849323868751526,
+      "learning_rate": 8.971790028626395e-05,
+      "loss": 1.5214,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 79
+    },
+    {
+      "epoch": 0.5906783571758191,
+      "grad_norm": 0.2951800525188446,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 1.4837,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 80
+    },
+    {
+      "epoch": 0.5980618366405168,
+      "grad_norm": 0.2763918340206146,
+      "learning_rate": 8.461094232959381e-05,
+      "loss": 1.5419,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 81
+    },
+    {
+      "epoch": 0.6054453161052146,
+      "grad_norm": 0.2745305895805359,
+      "learning_rate": 8.207192411892646e-05,
+      "loss": 1.4921,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 82
+    },
+    {
+      "epoch": 0.6128287955699123,
+      "grad_norm": 0.30081912875175476,
+      "learning_rate": 7.954479338737995e-05,
+      "loss": 1.4745,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 83
+    },
+    {
+      "epoch": 0.6202122750346101,
+      "grad_norm": 0.27640482783317566,
+      "learning_rate": 7.703122578682046e-05,
+      "loss": 1.4461,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 84
+    },
+    {
+      "epoch": 0.6275957544993078,
+      "grad_norm": 0.3407949209213257,
+      "learning_rate": 7.453288797587714e-05,
+      "loss": 1.617,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 85
+    },
+    {
+      "epoch": 0.6349792339640056,
+      "grad_norm": 0.2856479287147522,
+      "learning_rate": 7.205143651483906e-05,
+      "loss": 1.6538,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 86
+    },
+    {
+      "epoch": 0.6423627134287033,
+      "grad_norm": 0.39668434858322144,
+      "learning_rate": 6.958851676724823e-05,
+      "loss": 1.5753,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 87
+    },
+    {
+      "epoch": 0.649746192893401,
+      "grad_norm": 0.28521108627319336,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 1.3448,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 88
+    },
+    {
+      "epoch": 0.6571296723580987,
+      "grad_norm": 0.2806543707847595,
+      "learning_rate": 6.472479134509052e-05,
+      "loss": 1.6431,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 89
+    },
+    {
+      "epoch": 0.6645131518227965,
+      "grad_norm": 0.28897204995155334,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 1.5744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 90
+    },
+    {
+      "epoch": 0.6718966312874942,
+      "grad_norm": 0.25295817852020264,
+      "learning_rate": 5.9954609434873344e-05,
+      "loss": 1.4552,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 91
+    },
+    {
+      "epoch": 0.679280110752192,
+      "grad_norm": 0.2824646234512329,
+      "learning_rate": 5.7608560929013946e-05,
+      "loss": 1.4193,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 92
+    },
+    {
+      "epoch": 0.6866635902168897,
+      "grad_norm": 0.27227288484573364,
+      "learning_rate": 5.5290620701488594e-05,
+      "loss": 1.4602,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 93
+    },
+    {
+      "epoch": 0.6940470696815875,
+      "grad_norm": 0.26284658908843994,
+      "learning_rate": 5.300232569726804e-05,
+      "loss": 1.5947,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 94
+    },
+    {
+      "epoch": 0.7014305491462852,
+      "grad_norm": 0.26174792647361755,
+      "learning_rate": 5.074519320461357e-05,
+      "loss": 1.4122,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 95
+    },
+    {
+      "epoch": 0.708814028610983,
+      "grad_norm": 0.3069747984409332,
+      "learning_rate": 4.852071984901696e-05,
+      "loss": 1.4805,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 96
+    },
+    {
+      "epoch": 0.7161975080756806,
+      "grad_norm": 0.32007896900177,
+      "learning_rate": 4.633038060083996e-05,
+      "loss": 1.3798,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 97
+    },
+    {
+      "epoch": 0.7235809875403784,
+      "grad_norm": 0.26006585359573364,
+      "learning_rate": 4.417562779731355e-05,
+      "loss": 1.4974,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 98
+    },
+    {
+      "epoch": 0.7309644670050761,
+      "grad_norm": 0.2552710473537445,
+      "learning_rate": 4.205789017954364e-05,
+      "loss": 1.4851,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 99
+    },
+    {
+      "epoch": 0.7383479464697739,
+      "grad_norm": 0.23933957517147064,
+      "learning_rate": 3.997857194516319e-05,
+      "loss": 1.5046,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 100
+    },
+    {
+      "epoch": 0.7457314259344716,
+      "grad_norm": 0.2627595067024231,
+      "learning_rate": 3.793905181725772e-05,
+      "loss": 1.4958,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 101
+    },
+    {
+      "epoch": 0.7531149053991694,
+      "grad_norm": 0.3138872981071472,
+      "learning_rate": 3.594068213018249e-05,
+      "loss": 1.4714,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 102
+    },
+    {
+      "epoch": 0.7604983848638671,
+      "grad_norm": 0.2678472697734833,
+      "learning_rate": 3.3984787932876814e-05,
+      "loss": 1.5767,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 103
+    },
+    {
+      "epoch": 0.7678818643285649,
+      "grad_norm": 0.29931122064590454,
+      "learning_rate": 3.207266611027069e-05,
+      "loss": 1.5006,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 104
+    },
+    {
+      "epoch": 0.7752653437932626,
+      "grad_norm": 0.27635884284973145,
+      "learning_rate": 3.0205584523365626e-05,
+      "loss": 1.4236,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 105
+    },
+    {
+      "epoch": 0.7826488232579604,
+      "grad_norm": 0.2608022093772888,
+      "learning_rate": 2.8384781168560693e-05,
+      "loss": 1.3451,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 106
+    },
+    {
+      "epoch": 0.790032302722658,
+      "grad_norm": 0.271505743265152,
+      "learning_rate": 2.6611463356780096e-05,
+      "loss": 1.5161,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 107
+    },
+    {
+      "epoch": 0.7974157821873558,
+      "grad_norm": 0.26420703530311584,
+      "learning_rate": 2.4886806912948035e-05,
+      "loss": 1.5567,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 108
+    },
+    {
+      "epoch": 0.8047992616520535,
+      "grad_norm": 0.2610979974269867,
+      "learning_rate": 2.3211955396340002e-05,
+      "loss": 1.6357,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 109
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 0.25315845012664795,
+      "learning_rate": 2.1588019342328968e-05,
+      "loss": 1.4353,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 110
+    },
+    {
+      "epoch": 0.819566220581449,
+      "grad_norm": 0.27436307072639465,
+      "learning_rate": 2.0016075526028065e-05,
+      "loss": 1.4613,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 111
+    },
+    {
+      "epoch": 0.8269497000461468,
+      "grad_norm": 0.2581930458545685,
+      "learning_rate": 1.8497166248318876e-05,
+      "loss": 1.4317,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 112
+    },
+    {
+      "epoch": 0.8343331795108445,
+      "grad_norm": 0.3470868170261383,
+      "learning_rate": 1.703229864473811e-05,
+      "loss": 1.5637,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 113
+    },
+    {
+      "epoch": 0.8417166589755423,
+      "grad_norm": 0.2554042339324951,
+      "learning_rate": 1.562244401768144e-05,
+      "loss": 1.597,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 114
+    },
+    {
+      "epoch": 0.84910013844024,
+      "grad_norm": 0.26158565282821655,
+      "learning_rate": 1.426853719236676e-05,
+      "loss": 1.3765,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 115
+    },
+    {
+      "epoch": 0.8564836179049377,
+      "grad_norm": 0.27990010380744934,
+      "learning_rate": 1.2971475896984475e-05,
+      "loss": 1.2698,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 116
+    },
+    {
+      "epoch": 0.8638670973696354,
+      "grad_norm": 0.2723514139652252,
+      "learning_rate": 1.1732120167445248e-05,
+      "loss": 1.5009,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 117
+    },
+    {
+      "epoch": 0.8712505768343332,
+      "grad_norm": 0.2686865031719208,
+      "learning_rate": 1.0551291777120464e-05,
+      "loss": 1.4692,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 118
+    },
+    {
+      "epoch": 0.8786340562990309,
+      "grad_norm": 0.2559969127178192,
+      "learning_rate": 9.429773691952858e-06,
+      "loss": 1.4417,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 119
+    },
+    {
+      "epoch": 0.8860175357637287,
+      "grad_norm": 0.3991638123989105,
+      "learning_rate": 8.368309551299536e-06,
+      "loss": 1.5384,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 120
+    },
+    {
+      "epoch": 0.8934010152284264,
+      "grad_norm": 0.2762066125869751,
+      "learning_rate": 7.367603174850502e-06,
+      "loss": 1.4997,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 121
+    },
+    {
+      "epoch": 0.9007844946931242,
+      "grad_norm": 0.2837660014629364,
+      "learning_rate": 6.428318095950647e-06,
+      "loss": 1.448,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 122
+    },
+    {
+      "epoch": 0.9081679741578219,
+      "grad_norm": 0.2550673484802246,
+      "learning_rate": 5.551077121633874e-06,
+      "loss": 1.4488,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 123
+    },
+    {
+      "epoch": 0.9155514536225197,
+      "grad_norm": 0.2584616541862488,
+      "learning_rate": 4.7364619196617495e-06,
+      "loss": 1.3641,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 124
+    },
+    {
+      "epoch": 0.9229349330872173,
+      "grad_norm": 0.2741107940673828,
+      "learning_rate": 3.985012632839824e-06,
+      "loss": 1.4923,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 125
+    },
+    {
+      "epoch": 0.930318412551915,
+      "grad_norm": 0.252888023853302,
+      "learning_rate": 3.2972275208679625e-06,
+      "loss": 1.4971,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 126
+    },
+    {
+      "epoch": 0.9377018920166128,
+      "grad_norm": 0.25903505086898804,
+      "learning_rate": 2.6735626299617457e-06,
+      "loss": 1.3392,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 127
+    },
+    {
+      "epoch": 0.9450853714813106,
+      "grad_norm": 0.2537846267223358,
+      "learning_rate": 2.1144314904642195e-06,
+      "loss": 1.3883,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 128
+    },
+    {
+      "epoch": 0.9524688509460083,
+      "grad_norm": 0.2762198746204376,
+      "learning_rate": 1.6202048426483651e-06,
+      "loss": 1.4447,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 129
+    },
+    {
+      "epoch": 0.9598523304107061,
+      "grad_norm": 0.25517532229423523,
+      "learning_rate": 1.1912103908922945e-06,
+      "loss": 1.455,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 130
+    },
+    {
+      "epoch": 0.9672358098754038,
+      "grad_norm": 0.2435961812734604,
+      "learning_rate": 8.277325863898511e-07,
+      "loss": 1.4236,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 131
+    },
+    {
+      "epoch": 0.9746192893401016,
+      "grad_norm": 0.28410804271698,
+      "learning_rate": 5.300124385410943e-07,
+      "loss": 1.4976,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 132
+    },
+    {
+      "epoch": 0.9820027688047993,
+      "grad_norm": 0.2661467492580414,
+      "learning_rate": 2.9824735514732974e-07,
+      "loss": 1.3701,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 133
+    },
+    {
+      "epoch": 0.989386248269497,
+      "grad_norm": 0.2969636023044586,
+      "learning_rate": 1.3259101151694708e-07,
+      "loss": 1.6409,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 134
+    },
+    {
+      "epoch": 0.9967697277341947,
+      "grad_norm": 0.26862043142318726,
+      "learning_rate": 3.3153248568695835e-08,
+      "loss": 1.5537,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 135
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 34,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4510152212217856e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-135/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fcfaa0586b6a2ecea53c5d5918e29b57140459bd84f8ccd10b223317f2666e
+size 10001

checkpoint-34/README.md

@@ -0,0 +1,208 @@
+---
+base_model: model
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:model
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-34/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.up_proj",
+    "self_attn.q_proj",
+    "self_attn.o_proj",
+    "self_attn.k_proj",
+    "mlp.down_proj",
+    "mlp.gate_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-34/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee0cfbc02cf11ba8a3d0517b4ad062da5b5d21fd57cd1e3c46e42b72bd37148
+size 739321784

checkpoint-34/chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-34/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595b62a4e5d5759d07d761026796bc6cdc64853d0fdd77779bf5eb2636d73ba2
+size 376056741

checkpoint-34/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752df206744310768190894600622fb72d119c128eb069316564028933e553a9
+size 14645

checkpoint-34/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608a7d43c7da47f12ba539b1648dfe152960db238228a3078753109d10f1bfc4
+size 1465

checkpoint-34/special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-34/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

checkpoint-34/trainer_state.json

@@ -0,0 +1,374 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25103830179972314,
+  "eval_steps": 500,
+  "global_step": 34,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007383479464697739,
+      "grad_norm": 1.9591929912567139,
+      "learning_rate": 0.0,
+      "loss": 1.6228,
+      "memory/device_mem_reserved(gib)": 21.61,
+      "memory/max_mem_active(gib)": 21.2,
+      "memory/max_mem_allocated(gib)": 21.2,
+      "step": 1
+    },
+    {
+      "epoch": 0.014766958929395477,
+      "grad_norm": 1.4523507356643677,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.5769,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 2
+    },
+    {
+      "epoch": 0.022150438394093218,
+      "grad_norm": 1.1918187141418457,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.5435,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 3
+    },
+    {
+      "epoch": 0.029533917858790955,
+      "grad_norm": 0.8260876536369324,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 1.6523,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 4
+    },
+    {
+      "epoch": 0.03691739732348869,
+      "grad_norm": 0.8584926128387451,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.5745,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 5
+    },
+    {
+      "epoch": 0.044300876788186436,
+      "grad_norm": 0.6466429829597473,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.4759,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 6
+    },
+    {
+      "epoch": 0.05168435625288417,
+      "grad_norm": 0.5014482140541077,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 1.602,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 7
+    },
+    {
+      "epoch": 0.05906783571758191,
+      "grad_norm": 0.6017433404922485,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 1.4176,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 8
+    },
+    {
+      "epoch": 0.06645131518227965,
+      "grad_norm": 0.4612258970737457,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 1.5819,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 9
+    },
+    {
+      "epoch": 0.07383479464697738,
+      "grad_norm": 0.4430214464664459,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.561,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 10
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 0.3746771216392517,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 1.6744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 11
+    },
+    {
+      "epoch": 0.08860175357637287,
+      "grad_norm": 0.38248857855796814,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 1.5629,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 12
+    },
+    {
+      "epoch": 0.09598523304107061,
+      "grad_norm": 0.515844464302063,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 1.5264,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 13
+    },
+    {
+      "epoch": 0.10336871250576835,
+      "grad_norm": 0.3964424431324005,
+      "learning_rate": 0.0002,
+      "loss": 1.5398,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 14
+    },
+    {
+      "epoch": 0.11075219197046608,
+      "grad_norm": 0.4010593891143799,
+      "learning_rate": 0.0001999668467514313,
+      "loss": 1.4618,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 15
+    },
+    {
+      "epoch": 0.11813567143516382,
+      "grad_norm": 0.3192802965641022,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 1.6994,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 16
+    },
+    {
+      "epoch": 0.12551915089986157,
+      "grad_norm": 0.410099059343338,
+      "learning_rate": 0.00019970175264485266,
+      "loss": 1.5913,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 17
+    },
+    {
+      "epoch": 0.1329026303645593,
+      "grad_norm": 0.312429815530777,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 1.5701,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 18
+    },
+    {
+      "epoch": 0.14028610982925704,
+      "grad_norm": 0.2831230163574219,
+      "learning_rate": 0.00019917226741361015,
+      "loss": 1.5744,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 19
+    },
+    {
+      "epoch": 0.14766958929395477,
+      "grad_norm": 0.3618868291378021,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 1.5185,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 20
+    },
+    {
+      "epoch": 0.15505306875865252,
+      "grad_norm": 0.3151628077030182,
+      "learning_rate": 0.00019837979515735166,
+      "loss": 1.5086,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 21
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 0.31955838203430176,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 1.6329,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 22
+    },
+    {
+      "epoch": 0.169820027688048,
+      "grad_norm": 0.3030437231063843,
+      "learning_rate": 0.00019732643737003827,
+      "loss": 1.6697,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 23
+    },
+    {
+      "epoch": 0.17720350715274574,
+      "grad_norm": 0.41288134455680847,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 1.7094,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 24
+    },
+    {
+      "epoch": 0.18458698661744347,
+      "grad_norm": 0.2887294888496399,
+      "learning_rate": 0.00019601498736716017,
+      "loss": 1.5554,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 25
+    },
+    {
+      "epoch": 0.19197046608214122,
+      "grad_norm": 0.3173791170120239,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 1.4404,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 26
+    },
+    {
+      "epoch": 0.19935394554683894,
+      "grad_norm": 0.2877439558506012,
+      "learning_rate": 0.00019444892287836613,
+      "loss": 1.4766,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 27
+    },
+    {
+      "epoch": 0.2067374250115367,
+      "grad_norm": 0.29286038875579834,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 1.5156,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 28
+    },
+    {
+      "epoch": 0.2141209044762344,
+      "grad_norm": 0.27713659405708313,
+      "learning_rate": 0.00019263239682514952,
+      "loss": 1.5153,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 29
+    },
+    {
+      "epoch": 0.22150438394093216,
+      "grad_norm": 0.29187655448913574,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 1.6036,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 30
+    },
+    {
+      "epoch": 0.22888786340562992,
+      "grad_norm": 0.2671583890914917,
+      "learning_rate": 0.00019057022630804716,
+      "loss": 1.4675,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 31
+    },
+    {
+      "epoch": 0.23627134287032764,
+      "grad_norm": 0.2679831087589264,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 1.581,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 32
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 0.26359617710113525,
+      "learning_rate": 0.00018826787983255473,
+      "loss": 1.4674,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 33
+    },
+    {
+      "epoch": 0.25103830179972314,
+      "grad_norm": 0.30446046590805054,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 1.5038,
+      "memory/device_mem_reserved(gib)": 21.8,
+      "memory/max_mem_active(gib)": 21.55,
+      "memory/max_mem_allocated(gib)": 21.55,
+      "step": 34
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 34,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.17292722381783e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-34/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fcfaa0586b6a2ecea53c5d5918e29b57140459bd84f8ccd10b223317f2666e
+size 10001

checkpoint-68/README.md

@@ -0,0 +1,208 @@
+---
+base_model: model
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:model
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

checkpoint-68/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.up_proj",
+    "self_attn.q_proj",
+    "self_attn.o_proj",
+    "self_attn.k_proj",
+    "mlp.down_proj",
+    "mlp.gate_proj",
+    "self_attn.v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-68/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3d28ada5e88bf260383847f0470516b3c29de0858f6a287bf978506b4b97af
+size 739321784

checkpoint-68/chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

checkpoint-68/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7931ac59243ce57fdc2393008183ff7a94585c0aa5f9a4411a97897c370ba2
+size 376056741

checkpoint-68/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acba53108c4834096d4035e6ec0a0913daf054a2acb1b2dab537d280405ab115
+size 14645

checkpoint-68/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ece125e44f1c915f254d1320eb53b6559c9da64dcbe75c15e14fad1c85f4df
+size 1465

checkpoint-68/special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-68/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037