Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- gliner_config.json +144 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +75 -0
- trainer_state.json +741 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<<ENT>>": 128001,
|
| 3 |
+
"<<SEP>>": 128002,
|
| 4 |
+
"[MASK]": 128000
|
| 5 |
+
}
|
gliner_config.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128001,
|
| 3 |
+
"dropout": 0.4,
|
| 4 |
+
"embed_ent_token": true,
|
| 5 |
+
"encoder_config": {
|
| 6 |
+
"_attn_implementation_autoset": false,
|
| 7 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": null,
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"bad_words_ids": null,
|
| 12 |
+
"begin_suppress_tokens": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"cross_attention_hidden_size": null,
|
| 16 |
+
"decoder_start_token_id": null,
|
| 17 |
+
"diversity_penalty": 0.0,
|
| 18 |
+
"do_sample": false,
|
| 19 |
+
"early_stopping": false,
|
| 20 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 21 |
+
"eos_token_id": null,
|
| 22 |
+
"exponential_decay_length_penalty": null,
|
| 23 |
+
"finetuning_task": null,
|
| 24 |
+
"forced_bos_token_id": null,
|
| 25 |
+
"forced_eos_token_id": null,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 1024,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 4096,
|
| 35 |
+
"is_decoder": false,
|
| 36 |
+
"is_encoder_decoder": false,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-07,
|
| 42 |
+
"legacy": true,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"max_length": 20,
|
| 45 |
+
"max_position_embeddings": 512,
|
| 46 |
+
"max_relative_positions": -1,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "deberta-v2",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"norm_rel_ebd": "layer_norm",
|
| 51 |
+
"num_attention_heads": 16,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 24,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 0,
|
| 60 |
+
"pooler_dropout": 0,
|
| 61 |
+
"pooler_hidden_act": "gelu",
|
| 62 |
+
"pooler_hidden_size": 1024,
|
| 63 |
+
"pos_att_type": [
|
| 64 |
+
"p2c",
|
| 65 |
+
"c2p"
|
| 66 |
+
],
|
| 67 |
+
"position_biased_input": false,
|
| 68 |
+
"position_buckets": 256,
|
| 69 |
+
"prefix": null,
|
| 70 |
+
"problem_type": null,
|
| 71 |
+
"pruned_heads": {},
|
| 72 |
+
"relative_attention": true,
|
| 73 |
+
"remove_invalid_values": false,
|
| 74 |
+
"repetition_penalty": 1.0,
|
| 75 |
+
"return_dict": true,
|
| 76 |
+
"return_dict_in_generate": false,
|
| 77 |
+
"sep_token_id": null,
|
| 78 |
+
"share_att_key": true,
|
| 79 |
+
"suppress_tokens": null,
|
| 80 |
+
"task_specific_params": null,
|
| 81 |
+
"temperature": 1.0,
|
| 82 |
+
"tf_legacy_loss": false,
|
| 83 |
+
"tie_encoder_decoder": false,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"tokenizer_class": null,
|
| 86 |
+
"top_k": 50,
|
| 87 |
+
"top_p": 1.0,
|
| 88 |
+
"torch_dtype": null,
|
| 89 |
+
"torchscript": false,
|
| 90 |
+
"type_vocab_size": 0,
|
| 91 |
+
"typical_p": 1.0,
|
| 92 |
+
"use_bfloat16": false,
|
| 93 |
+
"vocab_size": 128003
|
| 94 |
+
},
|
| 95 |
+
"ent_token": "<<ENT>>",
|
| 96 |
+
"eval_every": 5000,
|
| 97 |
+
"fine_tune": true,
|
| 98 |
+
"freeze_token_rep": false,
|
| 99 |
+
"fuse_layers": false,
|
| 100 |
+
"has_rnn": true,
|
| 101 |
+
"hidden_size": 1024,
|
| 102 |
+
"label_smoothing": 0,
|
| 103 |
+
"labels_encoder": null,
|
| 104 |
+
"labels_encoder_config": null,
|
| 105 |
+
"labels_fusion_schema": "",
|
| 106 |
+
"log_dir": "models/",
|
| 107 |
+
"loss_alpha": 0.75,
|
| 108 |
+
"loss_gamma": 2,
|
| 109 |
+
"loss_reduction": "sum",
|
| 110 |
+
"lr_encoder": "1e-5",
|
| 111 |
+
"lr_others": "5e-5",
|
| 112 |
+
"max_grad_norm": 1.0,
|
| 113 |
+
"max_len": 2048,
|
| 114 |
+
"max_neg_type_ratio": 1,
|
| 115 |
+
"max_types": 30,
|
| 116 |
+
"max_width": 12,
|
| 117 |
+
"model_name": "microsoft/deberta-v3-large",
|
| 118 |
+
"model_type": "gliner",
|
| 119 |
+
"name": "span level gliner",
|
| 120 |
+
"num_post_fusion_layers": 1,
|
| 121 |
+
"num_rnns": 1,
|
| 122 |
+
"num_steps": 20000,
|
| 123 |
+
"post_fusion_schema": "",
|
| 124 |
+
"pre_fusion": true,
|
| 125 |
+
"prev_path": null,
|
| 126 |
+
"random_drop": true,
|
| 127 |
+
"root_dir": "gliner_logs",
|
| 128 |
+
"save_total_limit": 3,
|
| 129 |
+
"scheduler_type": "cosine",
|
| 130 |
+
"sep_token": "<<SEP>>",
|
| 131 |
+
"shuffle_types": true,
|
| 132 |
+
"size_sup": -1,
|
| 133 |
+
"span_mode": "markerV0",
|
| 134 |
+
"subtoken_pooling": "first",
|
| 135 |
+
"train_batch_size": 8,
|
| 136 |
+
"train_data": "../data/ner_batches_8b_tuned_100k.json",
|
| 137 |
+
"transformers_version": "4.48.0.dev0",
|
| 138 |
+
"val_data_dir": "none",
|
| 139 |
+
"vocab_size": 128003,
|
| 140 |
+
"warmup_ratio": 0.1,
|
| 141 |
+
"weight_decay_encoder": 0.01,
|
| 142 |
+
"weight_decay_other": 0.01,
|
| 143 |
+
"words_splitter_type": "whitespace"
|
| 144 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e3591fd58c3ee7ebe9a957fafeba6e635634e16ab5fa9329b6ad80d330ad8f9
|
| 3 |
+
size 1912078950
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed11b66a45d5d27da550d15fce8e14b77ceb06d1f0cfeb9513795fb99cb5724
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e115debc88a308ec6141837d91ce27474371bbc4ba1ac15e0c651b86a69e4cd3
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128001": {
|
| 44 |
+
"content": "<<ENT>>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128002": {
|
| 52 |
+
"content": "<<SEP>>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"bos_token": "[CLS]",
|
| 61 |
+
"clean_up_tokenization_spaces": false,
|
| 62 |
+
"cls_token": "[CLS]",
|
| 63 |
+
"do_lower_case": false,
|
| 64 |
+
"eos_token": "[SEP]",
|
| 65 |
+
"extra_special_tokens": {},
|
| 66 |
+
"mask_token": "[MASK]",
|
| 67 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 68 |
+
"pad_token": "[PAD]",
|
| 69 |
+
"sep_token": "[SEP]",
|
| 70 |
+
"sp_model_kwargs": {},
|
| 71 |
+
"split_by_punct": false,
|
| 72 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 73 |
+
"unk_token": "[UNK]",
|
| 74 |
+
"vocab_type": "spm"
|
| 75 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,741 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7711654268508679,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.017711654268508677,
|
| 13 |
+
"grad_norm": 840.4213256835938,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 284.3595,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.035423308537017355,
|
| 20 |
+
"grad_norm": 1422.4412841796875,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 132.2688,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.053134962805526036,
|
| 27 |
+
"grad_norm": 521.0823974609375,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 143.3815,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07084661707403471,
|
| 34 |
+
"grad_norm": 1643.88134765625,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 138.0503,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08855827134254339,
|
| 41 |
+
"grad_norm": 624.1228637695312,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 91.7494,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10626992561105207,
|
| 48 |
+
"grad_norm": 327.2431640625,
|
| 49 |
+
"learning_rate": 6e-06,
|
| 50 |
+
"loss": 78.6758,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12398157987956075,
|
| 55 |
+
"grad_norm": 0.0,
|
| 56 |
+
"learning_rate": 7e-06,
|
| 57 |
+
"loss": 86.4779,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14169323414806942,
|
| 62 |
+
"grad_norm": 659.7210083007812,
|
| 63 |
+
"learning_rate": 8.000000000000001e-06,
|
| 64 |
+
"loss": 103.229,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1594048884165781,
|
| 69 |
+
"grad_norm": 1251.806396484375,
|
| 70 |
+
"learning_rate": 9e-06,
|
| 71 |
+
"loss": 65.7367,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17711654268508678,
|
| 76 |
+
"grad_norm": 148.77456665039062,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 69.1247,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.19482819695359546,
|
| 83 |
+
"grad_norm": 401.77276611328125,
|
| 84 |
+
"learning_rate": 9.99695413509548e-06,
|
| 85 |
+
"loss": 187.7779,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.21253985122210414,
|
| 90 |
+
"grad_norm": 2775.739501953125,
|
| 91 |
+
"learning_rate": 9.987820251299121e-06,
|
| 92 |
+
"loss": 86.0222,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.23025150549061282,
|
| 97 |
+
"grad_norm": 606.4810791015625,
|
| 98 |
+
"learning_rate": 9.972609476841368e-06,
|
| 99 |
+
"loss": 109.5479,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2479631597591215,
|
| 104 |
+
"grad_norm": 111.0719985961914,
|
| 105 |
+
"learning_rate": 9.951340343707852e-06,
|
| 106 |
+
"loss": 76.4427,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.26567481402763016,
|
| 111 |
+
"grad_norm": 652.419921875,
|
| 112 |
+
"learning_rate": 9.924038765061042e-06,
|
| 113 |
+
"loss": 99.8802,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28338646829613884,
|
| 118 |
+
"grad_norm": 538.8716430664062,
|
| 119 |
+
"learning_rate": 9.890738003669029e-06,
|
| 120 |
+
"loss": 85.5841,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3010981225646475,
|
| 125 |
+
"grad_norm": 577.9231567382812,
|
| 126 |
+
"learning_rate": 9.851478631379982e-06,
|
| 127 |
+
"loss": 62.3816,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3188097768331562,
|
| 132 |
+
"grad_norm": 1849.4739990234375,
|
| 133 |
+
"learning_rate": 9.806308479691595e-06,
|
| 134 |
+
"loss": 72.0953,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3365214311016649,
|
| 139 |
+
"grad_norm": 1891.8170166015625,
|
| 140 |
+
"learning_rate": 9.755282581475769e-06,
|
| 141 |
+
"loss": 94.3675,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.35423308537017356,
|
| 146 |
+
"grad_norm": 1724.4739990234375,
|
| 147 |
+
"learning_rate": 9.698463103929542e-06,
|
| 148 |
+
"loss": 86.6209,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.37194473963868224,
|
| 153 |
+
"grad_norm": 1946.1993408203125,
|
| 154 |
+
"learning_rate": 9.635919272833938e-06,
|
| 155 |
+
"loss": 95.5281,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3896563939071909,
|
| 160 |
+
"grad_norm": 352.8471374511719,
|
| 161 |
+
"learning_rate": 9.567727288213005e-06,
|
| 162 |
+
"loss": 65.7924,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4073680481756996,
|
| 167 |
+
"grad_norm": 1524.947509765625,
|
| 168 |
+
"learning_rate": 9.493970231495836e-06,
|
| 169 |
+
"loss": 88.3867,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4250797024442083,
|
| 174 |
+
"grad_norm": 583.3900756835938,
|
| 175 |
+
"learning_rate": 9.414737964294636e-06,
|
| 176 |
+
"loss": 90.2626,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.44279135671271697,
|
| 181 |
+
"grad_norm": 1394.978759765625,
|
| 182 |
+
"learning_rate": 9.330127018922195e-06,
|
| 183 |
+
"loss": 65.8816,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.46050301098122565,
|
| 188 |
+
"grad_norm": 460.3956604003906,
|
| 189 |
+
"learning_rate": 9.24024048078213e-06,
|
| 190 |
+
"loss": 98.1954,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4782146652497343,
|
| 195 |
+
"grad_norm": 1408.5103759765625,
|
| 196 |
+
"learning_rate": 9.145187862775208e-06,
|
| 197 |
+
"loss": 66.155,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.495926319518243,
|
| 202 |
+
"grad_norm": 2149.823486328125,
|
| 203 |
+
"learning_rate": 9.045084971874738e-06,
|
| 204 |
+
"loss": 59.4641,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5136379737867517,
|
| 209 |
+
"grad_norm": 1315.8822021484375,
|
| 210 |
+
"learning_rate": 8.94005376803361e-06,
|
| 211 |
+
"loss": 54.4708,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5313496280552603,
|
| 216 |
+
"grad_norm": 5779.1162109375,
|
| 217 |
+
"learning_rate": 8.83022221559489e-06,
|
| 218 |
+
"loss": 65.8693,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.549061282323769,
|
| 223 |
+
"grad_norm": 1683.06689453125,
|
| 224 |
+
"learning_rate": 8.715724127386971e-06,
|
| 225 |
+
"loss": 59.8766,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5667729365922777,
|
| 230 |
+
"grad_norm": 249.68614196777344,
|
| 231 |
+
"learning_rate": 8.596699001693257e-06,
|
| 232 |
+
"loss": 54.9801,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5844845908607864,
|
| 237 |
+
"grad_norm": 807.7084350585938,
|
| 238 |
+
"learning_rate": 8.473291852294986e-06,
|
| 239 |
+
"loss": 88.5092,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.602196245129295,
|
| 244 |
+
"grad_norm": 1282.7015380859375,
|
| 245 |
+
"learning_rate": 8.345653031794292e-06,
|
| 246 |
+
"loss": 52.5884,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6199078993978038,
|
| 251 |
+
"grad_norm": 719.1715087890625,
|
| 252 |
+
"learning_rate": 8.213938048432697e-06,
|
| 253 |
+
"loss": 68.8219,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6376195536663124,
|
| 258 |
+
"grad_norm": 0.0,
|
| 259 |
+
"learning_rate": 8.078307376628292e-06,
|
| 260 |
+
"loss": 50.8381,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6553312079348211,
|
| 265 |
+
"grad_norm": 335.9521484375,
|
| 266 |
+
"learning_rate": 7.938926261462366e-06,
|
| 267 |
+
"loss": 64.6055,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6730428622033298,
|
| 272 |
+
"grad_norm": 548.884765625,
|
| 273 |
+
"learning_rate": 7.795964517353734e-06,
|
| 274 |
+
"loss": 55.1281,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6907545164718385,
|
| 279 |
+
"grad_norm": 3670.740478515625,
|
| 280 |
+
"learning_rate": 7.649596321166024e-06,
|
| 281 |
+
"loss": 54.0147,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7084661707403471,
|
| 286 |
+
"grad_norm": 444.0411376953125,
|
| 287 |
+
"learning_rate": 7.500000000000001e-06,
|
| 288 |
+
"loss": 64.277,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7261778250088559,
|
| 293 |
+
"grad_norm": 691.2824096679688,
|
| 294 |
+
"learning_rate": 7.347357813929455e-06,
|
| 295 |
+
"loss": 75.0035,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7438894792773645,
|
| 300 |
+
"grad_norm": 1208.0020751953125,
|
| 301 |
+
"learning_rate": 7.191855733945388e-06,
|
| 302 |
+
"loss": 50.5697,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7616011335458732,
|
| 307 |
+
"grad_norm": 254.70382690429688,
|
| 308 |
+
"learning_rate": 7.033683215379002e-06,
|
| 309 |
+
"loss": 75.5335,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7793127878143818,
|
| 314 |
+
"grad_norm": 292.61505126953125,
|
| 315 |
+
"learning_rate": 6.873032967079562e-06,
|
| 316 |
+
"loss": 48.5479,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7970244420828906,
|
| 321 |
+
"grad_norm": 166.0381622314453,
|
| 322 |
+
"learning_rate": 6.710100716628345e-06,
|
| 323 |
+
"loss": 64.7102,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8147360963513992,
|
| 328 |
+
"grad_norm": 0.0,
|
| 329 |
+
"learning_rate": 6.545084971874738e-06,
|
| 330 |
+
"loss": 79.722,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.832447750619908,
|
| 335 |
+
"grad_norm": 155.06393432617188,
|
| 336 |
+
"learning_rate": 6.378186779084996e-06,
|
| 337 |
+
"loss": 82.8574,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8501594048884166,
|
| 342 |
+
"grad_norm": 617.4712524414062,
|
| 343 |
+
"learning_rate": 6.209609477998339e-06,
|
| 344 |
+
"loss": 89.0717,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8678710591569253,
|
| 349 |
+
"grad_norm": 772.412109375,
|
| 350 |
+
"learning_rate": 6.039558454088796e-06,
|
| 351 |
+
"loss": 82.9971,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8855827134254339,
|
| 356 |
+
"grad_norm": 862.8140258789062,
|
| 357 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 358 |
+
"loss": 63.886,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9032943676939427,
|
| 363 |
+
"grad_norm": 382.09161376953125,
|
| 364 |
+
"learning_rate": 5.695865504800328e-06,
|
| 365 |
+
"loss": 53.4964,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9210060219624513,
|
| 370 |
+
"grad_norm": 460.5621643066406,
|
| 371 |
+
"learning_rate": 5.522642316338268e-06,
|
| 372 |
+
"loss": 46.1012,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9387176762309599,
|
| 377 |
+
"grad_norm": 1686.7965087890625,
|
| 378 |
+
"learning_rate": 5.348782368720627e-06,
|
| 379 |
+
"loss": 61.8082,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9564293304994687,
|
| 384 |
+
"grad_norm": 15522.65234375,
|
| 385 |
+
"learning_rate": 5.174497483512506e-06,
|
| 386 |
+
"loss": 75.6515,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9741409847679773,
|
| 391 |
+
"grad_norm": 8405.8447265625,
|
| 392 |
+
"learning_rate": 5e-06,
|
| 393 |
+
"loss": 52.1935,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.991852639036486,
|
| 398 |
+
"grad_norm": 1334.54541015625,
|
| 399 |
+
"learning_rate": 4.825502516487497e-06,
|
| 400 |
+
"loss": 40.6468,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.0,
|
| 405 |
+
"eval_loss": 176.01559448242188,
|
| 406 |
+
"eval_runtime": 57.5774,
|
| 407 |
+
"eval_samples_per_second": 43.594,
|
| 408 |
+
"eval_steps_per_second": 10.907,
|
| 409 |
+
"step": 5646
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.0095642933049946,
|
| 413 |
+
"grad_norm": 765.7606811523438,
|
| 414 |
+
"learning_rate": 4.651217631279374e-06,
|
| 415 |
+
"loss": 63.3825,
|
| 416 |
+
"step": 5700
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.0272759475735034,
|
| 420 |
+
"grad_norm": 527.5181274414062,
|
| 421 |
+
"learning_rate": 4.477357683661734e-06,
|
| 422 |
+
"loss": 43.7208,
|
| 423 |
+
"step": 5800
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.0449876018420121,
|
| 427 |
+
"grad_norm": 211.73487854003906,
|
| 428 |
+
"learning_rate": 4.304134495199675e-06,
|
| 429 |
+
"loss": 40.4991,
|
| 430 |
+
"step": 5900
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.0626992561105206,
|
| 434 |
+
"grad_norm": 400.1595764160156,
|
| 435 |
+
"learning_rate": 4.131759111665349e-06,
|
| 436 |
+
"loss": 43.3378,
|
| 437 |
+
"step": 6000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.0804109103790294,
|
| 441 |
+
"grad_norm": 389.70013427734375,
|
| 442 |
+
"learning_rate": 3.960441545911205e-06,
|
| 443 |
+
"loss": 41.4699,
|
| 444 |
+
"step": 6100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.098122564647538,
|
| 448 |
+
"grad_norm": 326.5900573730469,
|
| 449 |
+
"learning_rate": 3.790390522001662e-06,
|
| 450 |
+
"loss": 47.9553,
|
| 451 |
+
"step": 6200
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.1158342189160468,
|
| 455 |
+
"grad_norm": 7330.3310546875,
|
| 456 |
+
"learning_rate": 3.6218132209150047e-06,
|
| 457 |
+
"loss": 50.2975,
|
| 458 |
+
"step": 6300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.1335458731845554,
|
| 462 |
+
"grad_norm": 216.81912231445312,
|
| 463 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 464 |
+
"loss": 45.4736,
|
| 465 |
+
"step": 6400
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.151257527453064,
|
| 469 |
+
"grad_norm": 660.7682495117188,
|
| 470 |
+
"learning_rate": 3.289899283371657e-06,
|
| 471 |
+
"loss": 40.2617,
|
| 472 |
+
"step": 6500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.1689691817215728,
|
| 476 |
+
"grad_norm": 389.1190490722656,
|
| 477 |
+
"learning_rate": 3.12696703292044e-06,
|
| 478 |
+
"loss": 35.4133,
|
| 479 |
+
"step": 6600
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.1866808359900816,
|
| 483 |
+
"grad_norm": 877.7334594726562,
|
| 484 |
+
"learning_rate": 2.966316784621e-06,
|
| 485 |
+
"loss": 71.6576,
|
| 486 |
+
"step": 6700
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.20439249025859,
|
| 490 |
+
"grad_norm": 378.35980224609375,
|
| 491 |
+
"learning_rate": 2.8081442660546126e-06,
|
| 492 |
+
"loss": 34.5238,
|
| 493 |
+
"step": 6800
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.2221041445270988,
|
| 497 |
+
"grad_norm": 1453.03515625,
|
| 498 |
+
"learning_rate": 2.6526421860705474e-06,
|
| 499 |
+
"loss": 62.9686,
|
| 500 |
+
"step": 6900
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.2398157987956075,
|
| 504 |
+
"grad_norm": 132.0270538330078,
|
| 505 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 506 |
+
"loss": 52.0945,
|
| 507 |
+
"step": 7000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.257527453064116,
|
| 511 |
+
"grad_norm": 440.1296691894531,
|
| 512 |
+
"learning_rate": 2.3504036788339763e-06,
|
| 513 |
+
"loss": 39.2655,
|
| 514 |
+
"step": 7100
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.2752391073326248,
|
| 518 |
+
"grad_norm": 770.677734375,
|
| 519 |
+
"learning_rate": 2.204035482646267e-06,
|
| 520 |
+
"loss": 38.8261,
|
| 521 |
+
"step": 7200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.2929507616011335,
|
| 525 |
+
"grad_norm": 114.07510375976562,
|
| 526 |
+
"learning_rate": 2.061073738537635e-06,
|
| 527 |
+
"loss": 47.3239,
|
| 528 |
+
"step": 7300
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.3106624158696423,
|
| 532 |
+
"grad_norm": 10688.4658203125,
|
| 533 |
+
"learning_rate": 1.9216926233717087e-06,
|
| 534 |
+
"loss": 62.3463,
|
| 535 |
+
"step": 7400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.328374070138151,
|
| 539 |
+
"grad_norm": 1633.7628173828125,
|
| 540 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 541 |
+
"loss": 55.4716,
|
| 542 |
+
"step": 7500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.3460857244066595,
|
| 546 |
+
"grad_norm": 0.0,
|
| 547 |
+
"learning_rate": 1.6543469682057105e-06,
|
| 548 |
+
"loss": 59.58,
|
| 549 |
+
"step": 7600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.3637973786751683,
|
| 553 |
+
"grad_norm": 159.12704467773438,
|
| 554 |
+
"learning_rate": 1.5267081477050132e-06,
|
| 555 |
+
"loss": 41.1704,
|
| 556 |
+
"step": 7700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.381509032943677,
|
| 560 |
+
"grad_norm": 801.6414184570312,
|
| 561 |
+
"learning_rate": 1.4033009983067454e-06,
|
| 562 |
+
"loss": 51.0953,
|
| 563 |
+
"step": 7800
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.3992206872121855,
|
| 567 |
+
"grad_norm": 857.81201171875,
|
| 568 |
+
"learning_rate": 1.2842758726130283e-06,
|
| 569 |
+
"loss": 40.7129,
|
| 570 |
+
"step": 7900
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.4169323414806942,
|
| 574 |
+
"grad_norm": 575.1051635742188,
|
| 575 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 576 |
+
"loss": 46.1708,
|
| 577 |
+
"step": 8000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.434643995749203,
|
| 581 |
+
"grad_norm": 2294.723388671875,
|
| 582 |
+
"learning_rate": 1.0599462319663906e-06,
|
| 583 |
+
"loss": 60.1358,
|
| 584 |
+
"step": 8100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.4523556500177117,
|
| 588 |
+
"grad_norm": 932.974853515625,
|
| 589 |
+
"learning_rate": 9.549150281252633e-07,
|
| 590 |
+
"loss": 43.8091,
|
| 591 |
+
"step": 8200
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.4700673042862205,
|
| 595 |
+
"grad_norm": 874.0687255859375,
|
| 596 |
+
"learning_rate": 8.54812137224792e-07,
|
| 597 |
+
"loss": 37.7215,
|
| 598 |
+
"step": 8300
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.487778958554729,
|
| 602 |
+
"grad_norm": 262.20599365234375,
|
| 603 |
+
"learning_rate": 7.597595192178702e-07,
|
| 604 |
+
"loss": 85.4072,
|
| 605 |
+
"step": 8400
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.5054906128232377,
|
| 609 |
+
"grad_norm": 1489.546875,
|
| 610 |
+
"learning_rate": 6.698729810778065e-07,
|
| 611 |
+
"loss": 32.7225,
|
| 612 |
+
"step": 8500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.5232022670917464,
|
| 616 |
+
"grad_norm": 160.3507537841797,
|
| 617 |
+
"learning_rate": 5.852620357053651e-07,
|
| 618 |
+
"loss": 56.6163,
|
| 619 |
+
"step": 8600
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.540913921360255,
|
| 623 |
+
"grad_norm": 224.78094482421875,
|
| 624 |
+
"learning_rate": 5.06029768504166e-07,
|
| 625 |
+
"loss": 40.1567,
|
| 626 |
+
"step": 8700
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.5586255756287637,
|
| 630 |
+
"grad_norm": 2062.70263671875,
|
| 631 |
+
"learning_rate": 4.322727117869951e-07,
|
| 632 |
+
"loss": 44.4478,
|
| 633 |
+
"step": 8800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.5763372298972724,
|
| 637 |
+
"grad_norm": 2095.88525390625,
|
| 638 |
+
"learning_rate": 3.6408072716606346e-07,
|
| 639 |
+
"loss": 59.679,
|
| 640 |
+
"step": 8900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.594048884165781,
|
| 644 |
+
"grad_norm": 3169.360107421875,
|
| 645 |
+
"learning_rate": 3.015368960704584e-07,
|
| 646 |
+
"loss": 46.9302,
|
| 647 |
+
"step": 9000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.61176053843429,
|
| 651 |
+
"grad_norm": 172.900634765625,
|
| 652 |
+
"learning_rate": 2.447174185242324e-07,
|
| 653 |
+
"loss": 37.7532,
|
| 654 |
+
"step": 9100
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.6294721927027984,
|
| 658 |
+
"grad_norm": 281.58856201171875,
|
| 659 |
+
"learning_rate": 1.9369152030840553e-07,
|
| 660 |
+
"loss": 32.5123,
|
| 661 |
+
"step": 9200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.6471838469713072,
|
| 665 |
+
"grad_norm": 367.6300048828125,
|
| 666 |
+
"learning_rate": 1.4852136862001766e-07,
|
| 667 |
+
"loss": 40.0032,
|
| 668 |
+
"step": 9300
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.664895501239816,
|
| 672 |
+
"grad_norm": 373.369873046875,
|
| 673 |
+
"learning_rate": 1.0926199633097156e-07,
|
| 674 |
+
"loss": 37.6046,
|
| 675 |
+
"step": 9400
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.6826071555083244,
|
| 679 |
+
"grad_norm": 758.5933227539062,
|
| 680 |
+
"learning_rate": 7.59612349389599e-08,
|
| 681 |
+
"loss": 31.245,
|
| 682 |
+
"step": 9500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.7003188097768331,
|
| 686 |
+
"grad_norm": 557.6469116210938,
|
| 687 |
+
"learning_rate": 4.865965629214819e-08,
|
| 688 |
+
"loss": 68.3517,
|
| 689 |
+
"step": 9600
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.7180304640453419,
|
| 693 |
+
"grad_norm": 297.67327880859375,
|
| 694 |
+
"learning_rate": 2.7390523158633552e-08,
|
| 695 |
+
"loss": 45.4609,
|
| 696 |
+
"step": 9700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.7357421183138504,
|
| 700 |
+
"grad_norm": 98.50409698486328,
|
| 701 |
+
"learning_rate": 1.2179748700879013e-08,
|
| 702 |
+
"loss": 35.9993,
|
| 703 |
+
"step": 9800
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.7534537725823593,
|
| 707 |
+
"grad_norm": 911.8038940429688,
|
| 708 |
+
"learning_rate": 3.0458649045211897e-09,
|
| 709 |
+
"loss": 41.5838,
|
| 710 |
+
"step": 9900
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.7711654268508679,
|
| 714 |
+
"grad_norm": 755.3094482421875,
|
| 715 |
+
"learning_rate": 0.0,
|
| 716 |
+
"loss": 57.0455,
|
| 717 |
+
"step": 10000
|
| 718 |
+
}
|
| 719 |
+
],
|
| 720 |
+
"logging_steps": 100,
|
| 721 |
+
"max_steps": 10000,
|
| 722 |
+
"num_input_tokens_seen": 0,
|
| 723 |
+
"num_train_epochs": 2,
|
| 724 |
+
"save_steps": 5000,
|
| 725 |
+
"stateful_callbacks": {
|
| 726 |
+
"TrainerControl": {
|
| 727 |
+
"args": {
|
| 728 |
+
"should_epoch_stop": false,
|
| 729 |
+
"should_evaluate": false,
|
| 730 |
+
"should_log": false,
|
| 731 |
+
"should_save": true,
|
| 732 |
+
"should_training_stop": true
|
| 733 |
+
},
|
| 734 |
+
"attributes": {}
|
| 735 |
+
}
|
| 736 |
+
},
|
| 737 |
+
"total_flos": 0.0,
|
| 738 |
+
"train_batch_size": 4,
|
| 739 |
+
"trial_name": null,
|
| 740 |
+
"trial_params": null
|
| 741 |
+
}
|