Upload folder using huggingface_hub
Browse files- checkpoint-1000/config.json +176 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +7 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +56 -0
- checkpoint-1000/trainer_state.json +1273 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.txt +0 -0
- checkpoint-770/config.json +176 -0
- checkpoint-770/model.safetensors +3 -0
- checkpoint-770/optimizer.pt +3 -0
- checkpoint-770/rng_state.pth +3 -0
- checkpoint-770/scheduler.pt +3 -0
- checkpoint-770/special_tokens_map.json +7 -0
- checkpoint-770/tokenizer.json +0 -0
- checkpoint-770/tokenizer_config.json +56 -0
- checkpoint-770/trainer_state.json +985 -0
- checkpoint-770/training_args.bin +3 -0
- checkpoint-770/vocab.txt +0 -0
- config.json +176 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "B-Activity",
|
| 13 |
+
"1": "B-Administration",
|
| 14 |
+
"2": "B-Age",
|
| 15 |
+
"3": "B-Area",
|
| 16 |
+
"4": "B-Biological_attribute",
|
| 17 |
+
"5": "B-Biological_structure",
|
| 18 |
+
"6": "B-Clinical_event",
|
| 19 |
+
"7": "B-Color",
|
| 20 |
+
"8": "B-Coreference",
|
| 21 |
+
"9": "B-Date",
|
| 22 |
+
"10": "B-Detailed_description",
|
| 23 |
+
"11": "B-Diagnostic_procedure",
|
| 24 |
+
"12": "B-Disease_disorder",
|
| 25 |
+
"13": "B-Distance",
|
| 26 |
+
"14": "B-Dosage",
|
| 27 |
+
"15": "B-Duration",
|
| 28 |
+
"16": "B-Family_history",
|
| 29 |
+
"17": "B-Frequency",
|
| 30 |
+
"18": "B-Height",
|
| 31 |
+
"19": "B-History",
|
| 32 |
+
"20": "B-Lab_value",
|
| 33 |
+
"21": "B-Mass",
|
| 34 |
+
"22": "B-Medication",
|
| 35 |
+
"23": "B-Nonbiological_location",
|
| 36 |
+
"24": "B-Occupation",
|
| 37 |
+
"25": "B-Other_entity",
|
| 38 |
+
"26": "B-Other_event",
|
| 39 |
+
"27": "B-Outcome",
|
| 40 |
+
"28": "B-Personal_background",
|
| 41 |
+
"29": "B-Qualitative_concept",
|
| 42 |
+
"30": "B-Quantitative_concept",
|
| 43 |
+
"31": "B-Severity",
|
| 44 |
+
"32": "B-Sex",
|
| 45 |
+
"33": "B-Shape",
|
| 46 |
+
"34": "B-Sign_symptom",
|
| 47 |
+
"35": "B-Subject",
|
| 48 |
+
"36": "B-Texture",
|
| 49 |
+
"37": "B-Therapeutic_procedure",
|
| 50 |
+
"38": "B-Time",
|
| 51 |
+
"39": "B-Volume",
|
| 52 |
+
"40": "B-Weight",
|
| 53 |
+
"41": "I-Activity",
|
| 54 |
+
"42": "I-Administration",
|
| 55 |
+
"43": "I-Age",
|
| 56 |
+
"44": "I-Area",
|
| 57 |
+
"45": "I-Biological_structure",
|
| 58 |
+
"46": "I-Clinical_event",
|
| 59 |
+
"47": "I-Coreference",
|
| 60 |
+
"48": "I-Date",
|
| 61 |
+
"49": "I-Detailed_description",
|
| 62 |
+
"50": "I-Diagnostic_procedure",
|
| 63 |
+
"51": "I-Disease_disorder",
|
| 64 |
+
"52": "I-Distance",
|
| 65 |
+
"53": "I-Dosage",
|
| 66 |
+
"54": "I-Duration",
|
| 67 |
+
"55": "I-Family_history",
|
| 68 |
+
"56": "I-History",
|
| 69 |
+
"57": "I-Lab_value",
|
| 70 |
+
"58": "I-Mass",
|
| 71 |
+
"59": "I-Medication",
|
| 72 |
+
"60": "I-Nonbiological_location",
|
| 73 |
+
"61": "I-Other_entity",
|
| 74 |
+
"62": "I-Outcome",
|
| 75 |
+
"63": "I-Personal_background",
|
| 76 |
+
"64": "I-Quantitative_concept",
|
| 77 |
+
"65": "I-Severity",
|
| 78 |
+
"66": "I-Sex",
|
| 79 |
+
"67": "I-Sign_symptom",
|
| 80 |
+
"68": "I-Subject",
|
| 81 |
+
"69": "I-Texture",
|
| 82 |
+
"70": "I-Therapeutic_procedure",
|
| 83 |
+
"71": "I-Time",
|
| 84 |
+
"72": "I-Volume",
|
| 85 |
+
"73": "O"
|
| 86 |
+
},
|
| 87 |
+
"initializer_range": 0.02,
|
| 88 |
+
"label2id": {
|
| 89 |
+
"B-Activity": 0,
|
| 90 |
+
"B-Administration": 1,
|
| 91 |
+
"B-Age": 2,
|
| 92 |
+
"B-Area": 3,
|
| 93 |
+
"B-Biological_attribute": 4,
|
| 94 |
+
"B-Biological_structure": 5,
|
| 95 |
+
"B-Clinical_event": 6,
|
| 96 |
+
"B-Color": 7,
|
| 97 |
+
"B-Coreference": 8,
|
| 98 |
+
"B-Date": 9,
|
| 99 |
+
"B-Detailed_description": 10,
|
| 100 |
+
"B-Diagnostic_procedure": 11,
|
| 101 |
+
"B-Disease_disorder": 12,
|
| 102 |
+
"B-Distance": 13,
|
| 103 |
+
"B-Dosage": 14,
|
| 104 |
+
"B-Duration": 15,
|
| 105 |
+
"B-Family_history": 16,
|
| 106 |
+
"B-Frequency": 17,
|
| 107 |
+
"B-Height": 18,
|
| 108 |
+
"B-History": 19,
|
| 109 |
+
"B-Lab_value": 20,
|
| 110 |
+
"B-Mass": 21,
|
| 111 |
+
"B-Medication": 22,
|
| 112 |
+
"B-Nonbiological_location": 23,
|
| 113 |
+
"B-Occupation": 24,
|
| 114 |
+
"B-Other_entity": 25,
|
| 115 |
+
"B-Other_event": 26,
|
| 116 |
+
"B-Outcome": 27,
|
| 117 |
+
"B-Personal_background": 28,
|
| 118 |
+
"B-Qualitative_concept": 29,
|
| 119 |
+
"B-Quantitative_concept": 30,
|
| 120 |
+
"B-Severity": 31,
|
| 121 |
+
"B-Sex": 32,
|
| 122 |
+
"B-Shape": 33,
|
| 123 |
+
"B-Sign_symptom": 34,
|
| 124 |
+
"B-Subject": 35,
|
| 125 |
+
"B-Texture": 36,
|
| 126 |
+
"B-Therapeutic_procedure": 37,
|
| 127 |
+
"B-Time": 38,
|
| 128 |
+
"B-Volume": 39,
|
| 129 |
+
"B-Weight": 40,
|
| 130 |
+
"I-Activity": 41,
|
| 131 |
+
"I-Administration": 42,
|
| 132 |
+
"I-Age": 43,
|
| 133 |
+
"I-Area": 44,
|
| 134 |
+
"I-Biological_structure": 45,
|
| 135 |
+
"I-Clinical_event": 46,
|
| 136 |
+
"I-Coreference": 47,
|
| 137 |
+
"I-Date": 48,
|
| 138 |
+
"I-Detailed_description": 49,
|
| 139 |
+
"I-Diagnostic_procedure": 50,
|
| 140 |
+
"I-Disease_disorder": 51,
|
| 141 |
+
"I-Distance": 52,
|
| 142 |
+
"I-Dosage": 53,
|
| 143 |
+
"I-Duration": 54,
|
| 144 |
+
"I-Family_history": 55,
|
| 145 |
+
"I-History": 56,
|
| 146 |
+
"I-Lab_value": 57,
|
| 147 |
+
"I-Mass": 58,
|
| 148 |
+
"I-Medication": 59,
|
| 149 |
+
"I-Nonbiological_location": 60,
|
| 150 |
+
"I-Other_entity": 61,
|
| 151 |
+
"I-Outcome": 62,
|
| 152 |
+
"I-Personal_background": 63,
|
| 153 |
+
"I-Quantitative_concept": 64,
|
| 154 |
+
"I-Severity": 65,
|
| 155 |
+
"I-Sex": 66,
|
| 156 |
+
"I-Sign_symptom": 67,
|
| 157 |
+
"I-Subject": 68,
|
| 158 |
+
"I-Texture": 69,
|
| 159 |
+
"I-Therapeutic_procedure": 70,
|
| 160 |
+
"I-Time": 71,
|
| 161 |
+
"I-Volume": 72,
|
| 162 |
+
"O": 73
|
| 163 |
+
},
|
| 164 |
+
"max_position_embeddings": 512,
|
| 165 |
+
"model_type": "distilbert",
|
| 166 |
+
"n_heads": 12,
|
| 167 |
+
"n_layers": 6,
|
| 168 |
+
"pad_token_id": 0,
|
| 169 |
+
"qa_dropout": 0.1,
|
| 170 |
+
"seq_classif_dropout": 0.2,
|
| 171 |
+
"sinusoidal_pos_embds": false,
|
| 172 |
+
"tie_weights_": true,
|
| 173 |
+
"torch_dtype": "float32",
|
| 174 |
+
"transformers_version": "4.49.0",
|
| 175 |
+
"vocab_size": 30522
|
| 176 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66105cdf50d0239d3bac04e0fa72a22c3ba8b7df6f1842622809e99a35975a29
|
| 3 |
+
size 265691496
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8b3d57ad76b70fe322f7703a6f6cba6bf5f5067fd514ce894dc9d21d18283e4
|
| 3 |
+
size 531440954
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8915c23050f659e686094053a99d91ccceb84572d20ef244f15f83a250dc71fe
|
| 3 |
+
size 13990
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74b67834aacf6f555d713cdb4b053a4620bd2b12a56cc8d1be6b42a81da28112
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1273 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6937354988399073,
|
| 3 |
+
"best_model_checkpoint": "outputs/models/distilbert-clinical-ner/checkpoint-770",
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_f1": 0.019590382902938554,
|
| 14 |
+
"eval_loss": 4.235354900360107,
|
| 15 |
+
"eval_precision": 0.01608187134502924,
|
| 16 |
+
"eval_recall": 0.025056947608200455,
|
| 17 |
+
"eval_runtime": 0.1555,
|
| 18 |
+
"eval_samples_per_second": 128.613,
|
| 19 |
+
"eval_steps_per_second": 12.861,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_f1": 0.023399014778325126,
|
| 25 |
+
"eval_loss": 4.040920734405518,
|
| 26 |
+
"eval_precision": 0.02546916890080429,
|
| 27 |
+
"eval_recall": 0.02164009111617312,
|
| 28 |
+
"eval_runtime": 0.1064,
|
| 29 |
+
"eval_samples_per_second": 187.984,
|
| 30 |
+
"eval_steps_per_second": 18.798,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"eval_f1": 0.0045045045045045045,
|
| 36 |
+
"eval_loss": 3.6175544261932373,
|
| 37 |
+
"eval_precision": 0.2,
|
| 38 |
+
"eval_recall": 0.002277904328018223,
|
| 39 |
+
"eval_runtime": 0.1035,
|
| 40 |
+
"eval_samples_per_second": 193.236,
|
| 41 |
+
"eval_steps_per_second": 19.324,
|
| 42 |
+
"step": 30
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_f1": 0.0,
|
| 47 |
+
"eval_loss": 3.0632073879241943,
|
| 48 |
+
"eval_precision": 0.0,
|
| 49 |
+
"eval_recall": 0.0,
|
| 50 |
+
"eval_runtime": 0.1056,
|
| 51 |
+
"eval_samples_per_second": 189.304,
|
| 52 |
+
"eval_steps_per_second": 18.93,
|
| 53 |
+
"step": 40
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"grad_norm": 2.285052537918091,
|
| 58 |
+
"learning_rate": 1e-05,
|
| 59 |
+
"loss": 3.7184,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 5.0,
|
| 64 |
+
"eval_f1": 0.0,
|
| 65 |
+
"eval_loss": 2.6725738048553467,
|
| 66 |
+
"eval_precision": 0.0,
|
| 67 |
+
"eval_recall": 0.0,
|
| 68 |
+
"eval_runtime": 0.1038,
|
| 69 |
+
"eval_samples_per_second": 192.708,
|
| 70 |
+
"eval_steps_per_second": 19.271,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 6.0,
|
| 75 |
+
"eval_f1": 0.0022753128555176336,
|
| 76 |
+
"eval_loss": 2.3172459602355957,
|
| 77 |
+
"eval_precision": 1.0,
|
| 78 |
+
"eval_recall": 0.0011389521640091116,
|
| 79 |
+
"eval_runtime": 0.1056,
|
| 80 |
+
"eval_samples_per_second": 189.369,
|
| 81 |
+
"eval_steps_per_second": 18.937,
|
| 82 |
+
"step": 60
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 7.0,
|
| 86 |
+
"eval_f1": 0.24705882352941175,
|
| 87 |
+
"eval_loss": 2.010183334350586,
|
| 88 |
+
"eval_precision": 0.34854771784232363,
|
| 89 |
+
"eval_recall": 0.19134396355353075,
|
| 90 |
+
"eval_runtime": 0.1045,
|
| 91 |
+
"eval_samples_per_second": 191.384,
|
| 92 |
+
"eval_steps_per_second": 19.138,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"eval_f1": 0.3578104138851802,
|
| 98 |
+
"eval_loss": 1.7770382165908813,
|
| 99 |
+
"eval_precision": 0.432258064516129,
|
| 100 |
+
"eval_recall": 0.3052391799544419,
|
| 101 |
+
"eval_runtime": 0.1043,
|
| 102 |
+
"eval_samples_per_second": 191.78,
|
| 103 |
+
"eval_steps_per_second": 19.178,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 9.0,
|
| 108 |
+
"eval_f1": 0.4306709265175719,
|
| 109 |
+
"eval_loss": 1.578804612159729,
|
| 110 |
+
"eval_precision": 0.49053857350800584,
|
| 111 |
+
"eval_recall": 0.3838268792710706,
|
| 112 |
+
"eval_runtime": 0.1049,
|
| 113 |
+
"eval_samples_per_second": 190.736,
|
| 114 |
+
"eval_steps_per_second": 19.074,
|
| 115 |
+
"step": 90
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 10.0,
|
| 119 |
+
"grad_norm": 1.6135512590408325,
|
| 120 |
+
"learning_rate": 2e-05,
|
| 121 |
+
"loss": 2.0341,
|
| 122 |
+
"step": 100
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"eval_f1": 0.5129151291512916,
|
| 127 |
+
"eval_loss": 1.4062659740447998,
|
| 128 |
+
"eval_precision": 0.5574866310160428,
|
| 129 |
+
"eval_recall": 0.47494305239179957,
|
| 130 |
+
"eval_runtime": 0.1053,
|
| 131 |
+
"eval_samples_per_second": 189.876,
|
| 132 |
+
"eval_steps_per_second": 18.988,
|
| 133 |
+
"step": 100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 11.0,
|
| 137 |
+
"eval_f1": 0.5652435357787132,
|
| 138 |
+
"eval_loss": 1.2971620559692383,
|
| 139 |
+
"eval_precision": 0.5987261146496815,
|
| 140 |
+
"eval_recall": 0.5353075170842825,
|
| 141 |
+
"eval_runtime": 0.1046,
|
| 142 |
+
"eval_samples_per_second": 191.215,
|
| 143 |
+
"eval_steps_per_second": 19.122,
|
| 144 |
+
"step": 110
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.0,
|
| 148 |
+
"eval_f1": 0.5844155844155845,
|
| 149 |
+
"eval_loss": 1.22593092918396,
|
| 150 |
+
"eval_precision": 0.6066176470588235,
|
| 151 |
+
"eval_recall": 0.5637813211845103,
|
| 152 |
+
"eval_runtime": 0.1052,
|
| 153 |
+
"eval_samples_per_second": 190.037,
|
| 154 |
+
"eval_steps_per_second": 19.004,
|
| 155 |
+
"step": 120
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 13.0,
|
| 159 |
+
"eval_f1": 0.6020642201834862,
|
| 160 |
+
"eval_loss": 1.1731911897659302,
|
| 161 |
+
"eval_precision": 0.6062355658198614,
|
| 162 |
+
"eval_recall": 0.5979498861047836,
|
| 163 |
+
"eval_runtime": 0.1047,
|
| 164 |
+
"eval_samples_per_second": 190.934,
|
| 165 |
+
"eval_steps_per_second": 19.093,
|
| 166 |
+
"step": 130
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 14.0,
|
| 170 |
+
"eval_f1": 0.6093023255813953,
|
| 171 |
+
"eval_loss": 1.1392405033111572,
|
| 172 |
+
"eval_precision": 0.6223277909738717,
|
| 173 |
+
"eval_recall": 0.5968109339407744,
|
| 174 |
+
"eval_runtime": 0.1076,
|
| 175 |
+
"eval_samples_per_second": 185.839,
|
| 176 |
+
"eval_steps_per_second": 18.584,
|
| 177 |
+
"step": 140
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.0,
|
| 181 |
+
"grad_norm": 1.8851341009140015,
|
| 182 |
+
"learning_rate": 1.888888888888889e-05,
|
| 183 |
+
"loss": 1.0843,
|
| 184 |
+
"step": 150
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.0,
|
| 188 |
+
"eval_f1": 0.6329849012775842,
|
| 189 |
+
"eval_loss": 1.1109048128128052,
|
| 190 |
+
"eval_precision": 0.6457345971563981,
|
| 191 |
+
"eval_recall": 0.6207289293849658,
|
| 192 |
+
"eval_runtime": 0.1045,
|
| 193 |
+
"eval_samples_per_second": 191.342,
|
| 194 |
+
"eval_steps_per_second": 19.134,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 16.0,
|
| 199 |
+
"eval_f1": 0.6323103647944412,
|
| 200 |
+
"eval_loss": 1.111675500869751,
|
| 201 |
+
"eval_precision": 0.6431095406360424,
|
| 202 |
+
"eval_recall": 0.621867881548975,
|
| 203 |
+
"eval_runtime": 0.1064,
|
| 204 |
+
"eval_samples_per_second": 187.947,
|
| 205 |
+
"eval_steps_per_second": 18.795,
|
| 206 |
+
"step": 160
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 17.0,
|
| 210 |
+
"eval_f1": 0.6406976744186046,
|
| 211 |
+
"eval_loss": 1.1105479001998901,
|
| 212 |
+
"eval_precision": 0.6543942992874109,
|
| 213 |
+
"eval_recall": 0.6275626423690205,
|
| 214 |
+
"eval_runtime": 0.1038,
|
| 215 |
+
"eval_samples_per_second": 192.723,
|
| 216 |
+
"eval_steps_per_second": 19.272,
|
| 217 |
+
"step": 170
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 18.0,
|
| 221 |
+
"eval_f1": 0.6418338108882521,
|
| 222 |
+
"eval_loss": 1.1081936359405518,
|
| 223 |
+
"eval_precision": 0.6459054209919262,
|
| 224 |
+
"eval_recall": 0.6378132118451025,
|
| 225 |
+
"eval_runtime": 0.1093,
|
| 226 |
+
"eval_samples_per_second": 182.962,
|
| 227 |
+
"eval_steps_per_second": 18.296,
|
| 228 |
+
"step": 180
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 19.0,
|
| 232 |
+
"eval_f1": 0.656629994209612,
|
| 233 |
+
"eval_loss": 1.0905473232269287,
|
| 234 |
+
"eval_precision": 0.6678445229681979,
|
| 235 |
+
"eval_recall": 0.6457858769931663,
|
| 236 |
+
"eval_runtime": 0.1058,
|
| 237 |
+
"eval_samples_per_second": 189.016,
|
| 238 |
+
"eval_steps_per_second": 18.902,
|
| 239 |
+
"step": 190
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 20.0,
|
| 243 |
+
"grad_norm": 2.453874111175537,
|
| 244 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 245 |
+
"loss": 0.6709,
|
| 246 |
+
"step": 200
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 20.0,
|
| 250 |
+
"eval_f1": 0.6527536231884057,
|
| 251 |
+
"eval_loss": 1.0979650020599365,
|
| 252 |
+
"eval_precision": 0.6646989374262101,
|
| 253 |
+
"eval_recall": 0.6412300683371298,
|
| 254 |
+
"eval_runtime": 0.1051,
|
| 255 |
+
"eval_samples_per_second": 190.38,
|
| 256 |
+
"eval_steps_per_second": 19.038,
|
| 257 |
+
"step": 200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 21.0,
|
| 261 |
+
"eval_f1": 0.660889659156557,
|
| 262 |
+
"eval_loss": 1.1073075532913208,
|
| 263 |
+
"eval_precision": 0.6705744431418523,
|
| 264 |
+
"eval_recall": 0.6514806378132119,
|
| 265 |
+
"eval_runtime": 0.1063,
|
| 266 |
+
"eval_samples_per_second": 188.158,
|
| 267 |
+
"eval_steps_per_second": 18.816,
|
| 268 |
+
"step": 210
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 22.0,
|
| 272 |
+
"eval_f1": 0.6520231213872832,
|
| 273 |
+
"eval_loss": 1.109878420829773,
|
| 274 |
+
"eval_precision": 0.6619718309859155,
|
| 275 |
+
"eval_recall": 0.642369020501139,
|
| 276 |
+
"eval_runtime": 0.1108,
|
| 277 |
+
"eval_samples_per_second": 180.582,
|
| 278 |
+
"eval_steps_per_second": 18.058,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 23.0,
|
| 283 |
+
"eval_f1": 0.6666666666666666,
|
| 284 |
+
"eval_loss": 1.1079308986663818,
|
| 285 |
+
"eval_precision": 0.6838323353293413,
|
| 286 |
+
"eval_recall": 0.6503416856492027,
|
| 287 |
+
"eval_runtime": 0.1051,
|
| 288 |
+
"eval_samples_per_second": 190.371,
|
| 289 |
+
"eval_steps_per_second": 19.037,
|
| 290 |
+
"step": 230
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 24.0,
|
| 294 |
+
"eval_f1": 0.6685714285714285,
|
| 295 |
+
"eval_loss": 1.0995490550994873,
|
| 296 |
+
"eval_precision": 0.6708715596330275,
|
| 297 |
+
"eval_recall": 0.6662870159453302,
|
| 298 |
+
"eval_runtime": 0.1076,
|
| 299 |
+
"eval_samples_per_second": 185.917,
|
| 300 |
+
"eval_steps_per_second": 18.592,
|
| 301 |
+
"step": 240
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 25.0,
|
| 305 |
+
"grad_norm": 1.9804632663726807,
|
| 306 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 307 |
+
"loss": 0.4563,
|
| 308 |
+
"step": 250
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 25.0,
|
| 312 |
+
"eval_f1": 0.6623831775700935,
|
| 313 |
+
"eval_loss": 1.1412475109100342,
|
| 314 |
+
"eval_precision": 0.6798561151079137,
|
| 315 |
+
"eval_recall": 0.6457858769931663,
|
| 316 |
+
"eval_runtime": 0.1043,
|
| 317 |
+
"eval_samples_per_second": 191.672,
|
| 318 |
+
"eval_steps_per_second": 19.167,
|
| 319 |
+
"step": 250
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 26.0,
|
| 323 |
+
"eval_f1": 0.6685878962536023,
|
| 324 |
+
"eval_loss": 1.1206316947937012,
|
| 325 |
+
"eval_precision": 0.676779463243874,
|
| 326 |
+
"eval_recall": 0.6605922551252847,
|
| 327 |
+
"eval_runtime": 0.1025,
|
| 328 |
+
"eval_samples_per_second": 195.213,
|
| 329 |
+
"eval_steps_per_second": 19.521,
|
| 330 |
+
"step": 260
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 27.0,
|
| 334 |
+
"eval_f1": 0.674013921113689,
|
| 335 |
+
"eval_loss": 1.1223537921905518,
|
| 336 |
+
"eval_precision": 0.6867612293144209,
|
| 337 |
+
"eval_recall": 0.6617312072892938,
|
| 338 |
+
"eval_runtime": 0.1023,
|
| 339 |
+
"eval_samples_per_second": 195.488,
|
| 340 |
+
"eval_steps_per_second": 19.549,
|
| 341 |
+
"step": 270
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 28.0,
|
| 345 |
+
"eval_f1": 0.6787595084844938,
|
| 346 |
+
"eval_loss": 1.1268706321716309,
|
| 347 |
+
"eval_precision": 0.6979542719614922,
|
| 348 |
+
"eval_recall": 0.6605922551252847,
|
| 349 |
+
"eval_runtime": 0.107,
|
| 350 |
+
"eval_samples_per_second": 186.844,
|
| 351 |
+
"eval_steps_per_second": 18.684,
|
| 352 |
+
"step": 280
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 29.0,
|
| 356 |
+
"eval_f1": 0.6817391304347827,
|
| 357 |
+
"eval_loss": 1.143689751625061,
|
| 358 |
+
"eval_precision": 0.6942148760330579,
|
| 359 |
+
"eval_recall": 0.6697038724373576,
|
| 360 |
+
"eval_runtime": 0.1048,
|
| 361 |
+
"eval_samples_per_second": 190.916,
|
| 362 |
+
"eval_steps_per_second": 19.092,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 30.0,
|
| 367 |
+
"grad_norm": 1.2570631504058838,
|
| 368 |
+
"learning_rate": 1.555555555555556e-05,
|
| 369 |
+
"loss": 0.3229,
|
| 370 |
+
"step": 300
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 30.0,
|
| 374 |
+
"eval_f1": 0.6781807714450201,
|
| 375 |
+
"eval_loss": 1.1411770582199097,
|
| 376 |
+
"eval_precision": 0.6856810244470314,
|
| 377 |
+
"eval_recall": 0.6708428246013668,
|
| 378 |
+
"eval_runtime": 0.1118,
|
| 379 |
+
"eval_samples_per_second": 178.865,
|
| 380 |
+
"eval_steps_per_second": 17.887,
|
| 381 |
+
"step": 300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 31.0,
|
| 385 |
+
"eval_f1": 0.6797235023041475,
|
| 386 |
+
"eval_loss": 1.1665282249450684,
|
| 387 |
+
"eval_precision": 0.6876456876456877,
|
| 388 |
+
"eval_recall": 0.6719817767653758,
|
| 389 |
+
"eval_runtime": 0.1061,
|
| 390 |
+
"eval_samples_per_second": 188.516,
|
| 391 |
+
"eval_steps_per_second": 18.852,
|
| 392 |
+
"step": 310
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 32.0,
|
| 396 |
+
"eval_f1": 0.6785714285714286,
|
| 397 |
+
"eval_loss": 1.147858738899231,
|
| 398 |
+
"eval_precision": 0.6864801864801865,
|
| 399 |
+
"eval_recall": 0.6708428246013668,
|
| 400 |
+
"eval_runtime": 0.1079,
|
| 401 |
+
"eval_samples_per_second": 185.36,
|
| 402 |
+
"eval_steps_per_second": 18.536,
|
| 403 |
+
"step": 320
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 33.0,
|
| 407 |
+
"eval_f1": 0.6774193548387096,
|
| 408 |
+
"eval_loss": 1.1554282903671265,
|
| 409 |
+
"eval_precision": 0.6853146853146853,
|
| 410 |
+
"eval_recall": 0.6697038724373576,
|
| 411 |
+
"eval_runtime": 0.1037,
|
| 412 |
+
"eval_samples_per_second": 192.925,
|
| 413 |
+
"eval_steps_per_second": 19.292,
|
| 414 |
+
"step": 330
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 34.0,
|
| 418 |
+
"eval_f1": 0.6797687861271676,
|
| 419 |
+
"eval_loss": 1.15742027759552,
|
| 420 |
+
"eval_precision": 0.6901408450704225,
|
| 421 |
+
"eval_recall": 0.6697038724373576,
|
| 422 |
+
"eval_runtime": 0.1053,
|
| 423 |
+
"eval_samples_per_second": 189.904,
|
| 424 |
+
"eval_steps_per_second": 18.99,
|
| 425 |
+
"step": 340
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 35.0,
|
| 429 |
+
"grad_norm": 1.0945429801940918,
|
| 430 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 431 |
+
"loss": 0.2396,
|
| 432 |
+
"step": 350
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 35.0,
|
| 436 |
+
"eval_f1": 0.6797235023041475,
|
| 437 |
+
"eval_loss": 1.1754865646362305,
|
| 438 |
+
"eval_precision": 0.6876456876456877,
|
| 439 |
+
"eval_recall": 0.6719817767653758,
|
| 440 |
+
"eval_runtime": 0.1057,
|
| 441 |
+
"eval_samples_per_second": 189.199,
|
| 442 |
+
"eval_steps_per_second": 18.92,
|
| 443 |
+
"step": 350
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 36.0,
|
| 447 |
+
"eval_f1": 0.6735870818915801,
|
| 448 |
+
"eval_loss": 1.1885067224502563,
|
| 449 |
+
"eval_precision": 0.6822429906542056,
|
| 450 |
+
"eval_recall": 0.6651480637813212,
|
| 451 |
+
"eval_runtime": 0.1,
|
| 452 |
+
"eval_samples_per_second": 200.0,
|
| 453 |
+
"eval_steps_per_second": 20.0,
|
| 454 |
+
"step": 360
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 37.0,
|
| 458 |
+
"eval_f1": 0.6806526806526807,
|
| 459 |
+
"eval_loss": 1.181584119796753,
|
| 460 |
+
"eval_precision": 0.6968973747016707,
|
| 461 |
+
"eval_recall": 0.6651480637813212,
|
| 462 |
+
"eval_runtime": 0.1076,
|
| 463 |
+
"eval_samples_per_second": 185.858,
|
| 464 |
+
"eval_steps_per_second": 18.586,
|
| 465 |
+
"step": 370
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 38.0,
|
| 469 |
+
"eval_f1": 0.6787172011661807,
|
| 470 |
+
"eval_loss": 1.1876161098480225,
|
| 471 |
+
"eval_precision": 0.6953405017921147,
|
| 472 |
+
"eval_recall": 0.662870159453303,
|
| 473 |
+
"eval_runtime": 0.1161,
|
| 474 |
+
"eval_samples_per_second": 172.269,
|
| 475 |
+
"eval_steps_per_second": 17.227,
|
| 476 |
+
"step": 380
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 39.0,
|
| 480 |
+
"eval_f1": 0.6818713450292397,
|
| 481 |
+
"eval_loss": 1.2116471529006958,
|
| 482 |
+
"eval_precision": 0.7007211538461539,
|
| 483 |
+
"eval_recall": 0.664009111617312,
|
| 484 |
+
"eval_runtime": 0.1027,
|
| 485 |
+
"eval_samples_per_second": 194.71,
|
| 486 |
+
"eval_steps_per_second": 19.471,
|
| 487 |
+
"step": 390
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 40.0,
|
| 491 |
+
"grad_norm": 0.8599975109100342,
|
| 492 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 493 |
+
"loss": 0.1848,
|
| 494 |
+
"step": 400
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 40.0,
|
| 498 |
+
"eval_f1": 0.6786542923433874,
|
| 499 |
+
"eval_loss": 1.1997044086456299,
|
| 500 |
+
"eval_precision": 0.6914893617021277,
|
| 501 |
+
"eval_recall": 0.6662870159453302,
|
| 502 |
+
"eval_runtime": 0.1098,
|
| 503 |
+
"eval_samples_per_second": 182.124,
|
| 504 |
+
"eval_steps_per_second": 18.212,
|
| 505 |
+
"step": 400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 41.0,
|
| 509 |
+
"eval_f1": 0.6817917393833625,
|
| 510 |
+
"eval_loss": 1.2281190156936646,
|
| 511 |
+
"eval_precision": 0.6967895362663495,
|
| 512 |
+
"eval_recall": 0.6674259681093394,
|
| 513 |
+
"eval_runtime": 0.1026,
|
| 514 |
+
"eval_samples_per_second": 195.027,
|
| 515 |
+
"eval_steps_per_second": 19.503,
|
| 516 |
+
"step": 410
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 42.0,
|
| 520 |
+
"eval_f1": 0.6820542412002308,
|
| 521 |
+
"eval_loss": 1.205224633216858,
|
| 522 |
+
"eval_precision": 0.6912280701754386,
|
| 523 |
+
"eval_recall": 0.673120728929385,
|
| 524 |
+
"eval_runtime": 0.1029,
|
| 525 |
+
"eval_samples_per_second": 194.454,
|
| 526 |
+
"eval_steps_per_second": 19.445,
|
| 527 |
+
"step": 420
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 43.0,
|
| 531 |
+
"eval_f1": 0.6834112149532711,
|
| 532 |
+
"eval_loss": 1.2441879510879517,
|
| 533 |
+
"eval_precision": 0.7014388489208633,
|
| 534 |
+
"eval_recall": 0.6662870159453302,
|
| 535 |
+
"eval_runtime": 0.1013,
|
| 536 |
+
"eval_samples_per_second": 197.51,
|
| 537 |
+
"eval_steps_per_second": 19.751,
|
| 538 |
+
"step": 430
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 44.0,
|
| 542 |
+
"eval_f1": 0.6762672811059909,
|
| 543 |
+
"eval_loss": 1.2410287857055664,
|
| 544 |
+
"eval_precision": 0.6841491841491841,
|
| 545 |
+
"eval_recall": 0.6685649202733486,
|
| 546 |
+
"eval_runtime": 0.1039,
|
| 547 |
+
"eval_samples_per_second": 192.454,
|
| 548 |
+
"eval_steps_per_second": 19.245,
|
| 549 |
+
"step": 440
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 45.0,
|
| 553 |
+
"grad_norm": 0.8666434288024902,
|
| 554 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 555 |
+
"loss": 0.1472,
|
| 556 |
+
"step": 450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 45.0,
|
| 560 |
+
"eval_f1": 0.6809744779582366,
|
| 561 |
+
"eval_loss": 1.2373775243759155,
|
| 562 |
+
"eval_precision": 0.693853427895981,
|
| 563 |
+
"eval_recall": 0.6685649202733486,
|
| 564 |
+
"eval_runtime": 0.1016,
|
| 565 |
+
"eval_samples_per_second": 196.912,
|
| 566 |
+
"eval_steps_per_second": 19.691,
|
| 567 |
+
"step": 450
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 46.0,
|
| 571 |
+
"eval_f1": 0.6786961583236321,
|
| 572 |
+
"eval_loss": 1.237067461013794,
|
| 573 |
+
"eval_precision": 0.694047619047619,
|
| 574 |
+
"eval_recall": 0.664009111617312,
|
| 575 |
+
"eval_runtime": 0.1002,
|
| 576 |
+
"eval_samples_per_second": 199.663,
|
| 577 |
+
"eval_steps_per_second": 19.966,
|
| 578 |
+
"step": 460
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 47.0,
|
| 582 |
+
"eval_f1": 0.6889016676250718,
|
| 583 |
+
"eval_loss": 1.2270065546035767,
|
| 584 |
+
"eval_precision": 0.6957026713124274,
|
| 585 |
+
"eval_recall": 0.6822323462414579,
|
| 586 |
+
"eval_runtime": 0.1051,
|
| 587 |
+
"eval_samples_per_second": 190.295,
|
| 588 |
+
"eval_steps_per_second": 19.03,
|
| 589 |
+
"step": 470
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 48.0,
|
| 593 |
+
"eval_f1": 0.6805555555555555,
|
| 594 |
+
"eval_loss": 1.238765001296997,
|
| 595 |
+
"eval_precision": 0.691764705882353,
|
| 596 |
+
"eval_recall": 0.6697038724373576,
|
| 597 |
+
"eval_runtime": 0.1066,
|
| 598 |
+
"eval_samples_per_second": 187.677,
|
| 599 |
+
"eval_steps_per_second": 18.768,
|
| 600 |
+
"step": 480
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 49.0,
|
| 604 |
+
"eval_f1": 0.6790914385556202,
|
| 605 |
+
"eval_loss": 1.2525634765625,
|
| 606 |
+
"eval_precision": 0.6948748510131109,
|
| 607 |
+
"eval_recall": 0.664009111617312,
|
| 608 |
+
"eval_runtime": 0.1021,
|
| 609 |
+
"eval_samples_per_second": 195.942,
|
| 610 |
+
"eval_steps_per_second": 19.594,
|
| 611 |
+
"step": 490
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 50.0,
|
| 615 |
+
"grad_norm": 0.8096102476119995,
|
| 616 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 617 |
+
"loss": 0.1184,
|
| 618 |
+
"step": 500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 50.0,
|
| 622 |
+
"eval_f1": 0.681421083284799,
|
| 623 |
+
"eval_loss": 1.2390888929367065,
|
| 624 |
+
"eval_precision": 0.6972586412395709,
|
| 625 |
+
"eval_recall": 0.6662870159453302,
|
| 626 |
+
"eval_runtime": 0.1042,
|
| 627 |
+
"eval_samples_per_second": 191.926,
|
| 628 |
+
"eval_steps_per_second": 19.193,
|
| 629 |
+
"step": 500
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 51.0,
|
| 633 |
+
"eval_f1": 0.6782810685249709,
|
| 634 |
+
"eval_loss": 1.2617552280426025,
|
| 635 |
+
"eval_precision": 0.6919431279620853,
|
| 636 |
+
"eval_recall": 0.6651480637813212,
|
| 637 |
+
"eval_runtime": 0.1011,
|
| 638 |
+
"eval_samples_per_second": 197.736,
|
| 639 |
+
"eval_steps_per_second": 19.774,
|
| 640 |
+
"step": 510
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 52.0,
|
| 644 |
+
"eval_f1": 0.6814469078179697,
|
| 645 |
+
"eval_loss": 1.2573115825653076,
|
| 646 |
+
"eval_precision": 0.6985645933014354,
|
| 647 |
+
"eval_recall": 0.6651480637813212,
|
| 648 |
+
"eval_runtime": 0.1033,
|
| 649 |
+
"eval_samples_per_second": 193.643,
|
| 650 |
+
"eval_steps_per_second": 19.364,
|
| 651 |
+
"step": 520
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 53.0,
|
| 655 |
+
"eval_f1": 0.681369704004643,
|
| 656 |
+
"eval_loss": 1.2631280422210693,
|
| 657 |
+
"eval_precision": 0.6946745562130178,
|
| 658 |
+
"eval_recall": 0.6685649202733486,
|
| 659 |
+
"eval_runtime": 0.1027,
|
| 660 |
+
"eval_samples_per_second": 194.742,
|
| 661 |
+
"eval_steps_per_second": 19.474,
|
| 662 |
+
"step": 530
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 54.0,
|
| 666 |
+
"eval_f1": 0.6822429906542057,
|
| 667 |
+
"eval_loss": 1.2612630128860474,
|
| 668 |
+
"eval_precision": 0.7002398081534772,
|
| 669 |
+
"eval_recall": 0.6651480637813212,
|
| 670 |
+
"eval_runtime": 0.1034,
|
| 671 |
+
"eval_samples_per_second": 193.355,
|
| 672 |
+
"eval_steps_per_second": 19.335,
|
| 673 |
+
"step": 540
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 55.0,
|
| 677 |
+
"grad_norm": 1.258770227432251,
|
| 678 |
+
"learning_rate": 1e-05,
|
| 679 |
+
"loss": 0.0965,
|
| 680 |
+
"step": 550
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 55.0,
|
| 684 |
+
"eval_f1": 0.678592036930179,
|
| 685 |
+
"eval_loss": 1.2565994262695312,
|
| 686 |
+
"eval_precision": 0.6877192982456141,
|
| 687 |
+
"eval_recall": 0.6697038724373576,
|
| 688 |
+
"eval_runtime": 0.1065,
|
| 689 |
+
"eval_samples_per_second": 187.769,
|
| 690 |
+
"eval_steps_per_second": 18.777,
|
| 691 |
+
"step": 550
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 56.0,
|
| 695 |
+
"eval_f1": 0.6720461095100864,
|
| 696 |
+
"eval_loss": 1.286030888557434,
|
| 697 |
+
"eval_precision": 0.6802800466744457,
|
| 698 |
+
"eval_recall": 0.664009111617312,
|
| 699 |
+
"eval_runtime": 0.1017,
|
| 700 |
+
"eval_samples_per_second": 196.637,
|
| 701 |
+
"eval_steps_per_second": 19.664,
|
| 702 |
+
"step": 560
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 57.0,
|
| 706 |
+
"eval_f1": 0.6774941995359629,
|
| 707 |
+
"eval_loss": 1.2746167182922363,
|
| 708 |
+
"eval_precision": 0.6903073286052009,
|
| 709 |
+
"eval_recall": 0.6651480637813212,
|
| 710 |
+
"eval_runtime": 0.104,
|
| 711 |
+
"eval_samples_per_second": 192.291,
|
| 712 |
+
"eval_steps_per_second": 19.229,
|
| 713 |
+
"step": 570
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 58.0,
|
| 717 |
+
"eval_f1": 0.6813441483198146,
|
| 718 |
+
"eval_loss": 1.2719839811325073,
|
| 719 |
+
"eval_precision": 0.6933962264150944,
|
| 720 |
+
"eval_recall": 0.6697038724373576,
|
| 721 |
+
"eval_runtime": 0.1009,
|
| 722 |
+
"eval_samples_per_second": 198.12,
|
| 723 |
+
"eval_steps_per_second": 19.812,
|
| 724 |
+
"step": 580
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 59.0,
|
| 728 |
+
"eval_f1": 0.6845168800931315,
|
| 729 |
+
"eval_loss": 1.2790720462799072,
|
| 730 |
+
"eval_precision": 0.7,
|
| 731 |
+
"eval_recall": 0.6697038724373576,
|
| 732 |
+
"eval_runtime": 0.1025,
|
| 733 |
+
"eval_samples_per_second": 195.09,
|
| 734 |
+
"eval_steps_per_second": 19.509,
|
| 735 |
+
"step": 590
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 60.0,
|
| 739 |
+
"grad_norm": 0.6421855688095093,
|
| 740 |
+
"learning_rate": 8.888888888888888e-06,
|
| 741 |
+
"loss": 0.0841,
|
| 742 |
+
"step": 600
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 60.0,
|
| 746 |
+
"eval_f1": 0.6827309236947792,
|
| 747 |
+
"eval_loss": 1.2661317586898804,
|
| 748 |
+
"eval_precision": 0.6878612716763006,
|
| 749 |
+
"eval_recall": 0.6776765375854215,
|
| 750 |
+
"eval_runtime": 0.1054,
|
| 751 |
+
"eval_samples_per_second": 189.834,
|
| 752 |
+
"eval_steps_per_second": 18.983,
|
| 753 |
+
"step": 600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 61.0,
|
| 757 |
+
"eval_f1": 0.6803039158386909,
|
| 758 |
+
"eval_loss": 1.2873255014419556,
|
| 759 |
+
"eval_precision": 0.6986794717887155,
|
| 760 |
+
"eval_recall": 0.662870159453303,
|
| 761 |
+
"eval_runtime": 0.1028,
|
| 762 |
+
"eval_samples_per_second": 194.643,
|
| 763 |
+
"eval_steps_per_second": 19.464,
|
| 764 |
+
"step": 610
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 62.0,
|
| 768 |
+
"eval_f1": 0.6809248554913295,
|
| 769 |
+
"eval_loss": 1.2766045331954956,
|
| 770 |
+
"eval_precision": 0.6913145539906104,
|
| 771 |
+
"eval_recall": 0.6708428246013668,
|
| 772 |
+
"eval_runtime": 0.1044,
|
| 773 |
+
"eval_samples_per_second": 191.487,
|
| 774 |
+
"eval_steps_per_second": 19.149,
|
| 775 |
+
"step": 620
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 63.0,
|
| 779 |
+
"eval_f1": 0.6755658734764944,
|
| 780 |
+
"eval_loss": 1.2915081977844238,
|
| 781 |
+
"eval_precision": 0.6887573964497041,
|
| 782 |
+
"eval_recall": 0.662870159453303,
|
| 783 |
+
"eval_runtime": 0.1078,
|
| 784 |
+
"eval_samples_per_second": 185.542,
|
| 785 |
+
"eval_steps_per_second": 18.554,
|
| 786 |
+
"step": 630
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 64.0,
|
| 790 |
+
"eval_f1": 0.6732101616628174,
|
| 791 |
+
"eval_loss": 1.2793446779251099,
|
| 792 |
+
"eval_precision": 0.6826697892271663,
|
| 793 |
+
"eval_recall": 0.664009111617312,
|
| 794 |
+
"eval_runtime": 0.1016,
|
| 795 |
+
"eval_samples_per_second": 196.942,
|
| 796 |
+
"eval_steps_per_second": 19.694,
|
| 797 |
+
"step": 640
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 65.0,
|
| 801 |
+
"grad_norm": 0.5916463136672974,
|
| 802 |
+
"learning_rate": 7.77777777777778e-06,
|
| 803 |
+
"loss": 0.0714,
|
| 804 |
+
"step": 650
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 65.0,
|
| 808 |
+
"eval_f1": 0.6820276497695852,
|
| 809 |
+
"eval_loss": 1.3019025325775146,
|
| 810 |
+
"eval_precision": 0.6899766899766899,
|
| 811 |
+
"eval_recall": 0.6742596810933941,
|
| 812 |
+
"eval_runtime": 0.1008,
|
| 813 |
+
"eval_samples_per_second": 198.393,
|
| 814 |
+
"eval_steps_per_second": 19.839,
|
| 815 |
+
"step": 650
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 66.0,
|
| 819 |
+
"eval_f1": 0.6853473438412142,
|
| 820 |
+
"eval_loss": 1.2911741733551025,
|
| 821 |
+
"eval_precision": 0.7029940119760479,
|
| 822 |
+
"eval_recall": 0.6685649202733486,
|
| 823 |
+
"eval_runtime": 0.106,
|
| 824 |
+
"eval_samples_per_second": 188.757,
|
| 825 |
+
"eval_steps_per_second": 18.876,
|
| 826 |
+
"step": 660
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 67.0,
|
| 830 |
+
"eval_f1": 0.67816091954023,
|
| 831 |
+
"eval_loss": 1.2967917919158936,
|
| 832 |
+
"eval_precision": 0.6844547563805105,
|
| 833 |
+
"eval_recall": 0.6719817767653758,
|
| 834 |
+
"eval_runtime": 0.1092,
|
| 835 |
+
"eval_samples_per_second": 183.175,
|
| 836 |
+
"eval_steps_per_second": 18.318,
|
| 837 |
+
"step": 670
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 68.0,
|
| 841 |
+
"eval_f1": 0.6895348837209303,
|
| 842 |
+
"eval_loss": 1.2946228981018066,
|
| 843 |
+
"eval_precision": 0.7042755344418052,
|
| 844 |
+
"eval_recall": 0.6753986332574032,
|
| 845 |
+
"eval_runtime": 0.1052,
|
| 846 |
+
"eval_samples_per_second": 190.167,
|
| 847 |
+
"eval_steps_per_second": 19.017,
|
| 848 |
+
"step": 680
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 69.0,
|
| 852 |
+
"eval_f1": 0.6863425925925927,
|
| 853 |
+
"eval_loss": 1.2976857423782349,
|
| 854 |
+
"eval_precision": 0.6976470588235294,
|
| 855 |
+
"eval_recall": 0.6753986332574032,
|
| 856 |
+
"eval_runtime": 0.103,
|
| 857 |
+
"eval_samples_per_second": 194.22,
|
| 858 |
+
"eval_steps_per_second": 19.422,
|
| 859 |
+
"step": 690
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 70.0,
|
| 863 |
+
"grad_norm": 0.7995481491088867,
|
| 864 |
+
"learning_rate": 6.666666666666667e-06,
|
| 865 |
+
"loss": 0.064,
|
| 866 |
+
"step": 700
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 70.0,
|
| 870 |
+
"eval_f1": 0.6771014492753623,
|
| 871 |
+
"eval_loss": 1.295568585395813,
|
| 872 |
+
"eval_precision": 0.6894923258559622,
|
| 873 |
+
"eval_recall": 0.6651480637813212,
|
| 874 |
+
"eval_runtime": 0.1031,
|
| 875 |
+
"eval_samples_per_second": 193.92,
|
| 876 |
+
"eval_steps_per_second": 19.392,
|
| 877 |
+
"step": 700
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 71.0,
|
| 881 |
+
"eval_f1": 0.6797687861271676,
|
| 882 |
+
"eval_loss": 1.2898850440979004,
|
| 883 |
+
"eval_precision": 0.6901408450704225,
|
| 884 |
+
"eval_recall": 0.6697038724373576,
|
| 885 |
+
"eval_runtime": 0.1005,
|
| 886 |
+
"eval_samples_per_second": 198.942,
|
| 887 |
+
"eval_steps_per_second": 19.894,
|
| 888 |
+
"step": 710
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 72.0,
|
| 892 |
+
"eval_f1": 0.6806526806526807,
|
| 893 |
+
"eval_loss": 1.3075172901153564,
|
| 894 |
+
"eval_precision": 0.6968973747016707,
|
| 895 |
+
"eval_recall": 0.6651480637813212,
|
| 896 |
+
"eval_runtime": 0.1087,
|
| 897 |
+
"eval_samples_per_second": 184.017,
|
| 898 |
+
"eval_steps_per_second": 18.402,
|
| 899 |
+
"step": 720
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 73.0,
|
| 903 |
+
"eval_f1": 0.683750728013978,
|
| 904 |
+
"eval_loss": 1.2973222732543945,
|
| 905 |
+
"eval_precision": 0.699642431466031,
|
| 906 |
+
"eval_recall": 0.6685649202733486,
|
| 907 |
+
"eval_runtime": 0.1054,
|
| 908 |
+
"eval_samples_per_second": 189.672,
|
| 909 |
+
"eval_steps_per_second": 18.967,
|
| 910 |
+
"step": 730
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 74.0,
|
| 914 |
+
"eval_f1": 0.6872812135355894,
|
| 915 |
+
"eval_loss": 1.3102946281433105,
|
| 916 |
+
"eval_precision": 0.7045454545454546,
|
| 917 |
+
"eval_recall": 0.6708428246013668,
|
| 918 |
+
"eval_runtime": 0.1064,
|
| 919 |
+
"eval_samples_per_second": 188.0,
|
| 920 |
+
"eval_steps_per_second": 18.8,
|
| 921 |
+
"step": 740
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 75.0,
|
| 925 |
+
"grad_norm": 0.8353786468505859,
|
| 926 |
+
"learning_rate": 5.555555555555557e-06,
|
| 927 |
+
"loss": 0.0575,
|
| 928 |
+
"step": 750
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 75.0,
|
| 932 |
+
"eval_f1": 0.6797915460335843,
|
| 933 |
+
"eval_loss": 1.3147099018096924,
|
| 934 |
+
"eval_precision": 0.6914016489988222,
|
| 935 |
+
"eval_recall": 0.6685649202733486,
|
| 936 |
+
"eval_runtime": 0.1049,
|
| 937 |
+
"eval_samples_per_second": 190.589,
|
| 938 |
+
"eval_steps_per_second": 19.059,
|
| 939 |
+
"step": 750
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 76.0,
|
| 943 |
+
"eval_f1": 0.6845168800931315,
|
| 944 |
+
"eval_loss": 1.3087732791900635,
|
| 945 |
+
"eval_precision": 0.7,
|
| 946 |
+
"eval_recall": 0.6697038724373576,
|
| 947 |
+
"eval_runtime": 0.105,
|
| 948 |
+
"eval_samples_per_second": 190.4,
|
| 949 |
+
"eval_steps_per_second": 19.04,
|
| 950 |
+
"step": 760
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 77.0,
|
| 954 |
+
"eval_f1": 0.6937354988399073,
|
| 955 |
+
"eval_loss": 1.3092721700668335,
|
| 956 |
+
"eval_precision": 0.706855791962175,
|
| 957 |
+
"eval_recall": 0.6810933940774487,
|
| 958 |
+
"eval_runtime": 0.1053,
|
| 959 |
+
"eval_samples_per_second": 189.996,
|
| 960 |
+
"eval_steps_per_second": 19.0,
|
| 961 |
+
"step": 770
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 78.0,
|
| 965 |
+
"eval_f1": 0.6890951276102089,
|
| 966 |
+
"eval_loss": 1.3059155941009521,
|
| 967 |
+
"eval_precision": 0.7021276595744681,
|
| 968 |
+
"eval_recall": 0.6765375854214123,
|
| 969 |
+
"eval_runtime": 0.1108,
|
| 970 |
+
"eval_samples_per_second": 180.481,
|
| 971 |
+
"eval_steps_per_second": 18.048,
|
| 972 |
+
"step": 780
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 79.0,
|
| 976 |
+
"eval_f1": 0.686012768427162,
|
| 977 |
+
"eval_loss": 1.3059110641479492,
|
| 978 |
+
"eval_precision": 0.6994082840236686,
|
| 979 |
+
"eval_recall": 0.673120728929385,
|
| 980 |
+
"eval_runtime": 0.1188,
|
| 981 |
+
"eval_samples_per_second": 168.352,
|
| 982 |
+
"eval_steps_per_second": 16.835,
|
| 983 |
+
"step": 790
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 80.0,
|
| 987 |
+
"grad_norm": 0.9341310858726501,
|
| 988 |
+
"learning_rate": 4.444444444444444e-06,
|
| 989 |
+
"loss": 0.0521,
|
| 990 |
+
"step": 800
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 80.0,
|
| 994 |
+
"eval_f1": 0.684393063583815,
|
| 995 |
+
"eval_loss": 1.3110581636428833,
|
| 996 |
+
"eval_precision": 0.6948356807511737,
|
| 997 |
+
"eval_recall": 0.6742596810933941,
|
| 998 |
+
"eval_runtime": 0.1046,
|
| 999 |
+
"eval_samples_per_second": 191.295,
|
| 1000 |
+
"eval_steps_per_second": 19.13,
|
| 1001 |
+
"step": 800
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 81.0,
|
| 1005 |
+
"eval_f1": 0.6876824284880326,
|
| 1006 |
+
"eval_loss": 1.3156492710113525,
|
| 1007 |
+
"eval_precision": 0.7053892215568862,
|
| 1008 |
+
"eval_recall": 0.6708428246013668,
|
| 1009 |
+
"eval_runtime": 0.1053,
|
| 1010 |
+
"eval_samples_per_second": 189.894,
|
| 1011 |
+
"eval_steps_per_second": 18.989,
|
| 1012 |
+
"step": 810
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 82.0,
|
| 1016 |
+
"eval_f1": 0.6812680115273776,
|
| 1017 |
+
"eval_loss": 1.3226007223129272,
|
| 1018 |
+
"eval_precision": 0.6896149358226371,
|
| 1019 |
+
"eval_recall": 0.673120728929385,
|
| 1020 |
+
"eval_runtime": 0.1059,
|
| 1021 |
+
"eval_samples_per_second": 188.943,
|
| 1022 |
+
"eval_steps_per_second": 18.894,
|
| 1023 |
+
"step": 820
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 83.0,
|
| 1027 |
+
"eval_f1": 0.686046511627907,
|
| 1028 |
+
"eval_loss": 1.318352460861206,
|
| 1029 |
+
"eval_precision": 0.7007125890736342,
|
| 1030 |
+
"eval_recall": 0.6719817767653758,
|
| 1031 |
+
"eval_runtime": 0.1064,
|
| 1032 |
+
"eval_samples_per_second": 187.885,
|
| 1033 |
+
"eval_steps_per_second": 18.789,
|
| 1034 |
+
"step": 830
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 84.0,
|
| 1038 |
+
"eval_f1": 0.6872451951077461,
|
| 1039 |
+
"eval_loss": 1.3170461654663086,
|
| 1040 |
+
"eval_precision": 0.7032181168057211,
|
| 1041 |
+
"eval_recall": 0.6719817767653758,
|
| 1042 |
+
"eval_runtime": 0.1059,
|
| 1043 |
+
"eval_samples_per_second": 188.868,
|
| 1044 |
+
"eval_steps_per_second": 18.887,
|
| 1045 |
+
"step": 840
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 85.0,
|
| 1049 |
+
"grad_norm": 0.3394979238510132,
|
| 1050 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1051 |
+
"loss": 0.0491,
|
| 1052 |
+
"step": 850
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 85.0,
|
| 1056 |
+
"eval_f1": 0.6856810244470314,
|
| 1057 |
+
"eval_loss": 1.3184274435043335,
|
| 1058 |
+
"eval_precision": 0.7011904761904761,
|
| 1059 |
+
"eval_recall": 0.6708428246013668,
|
| 1060 |
+
"eval_runtime": 0.1079,
|
| 1061 |
+
"eval_samples_per_second": 185.331,
|
| 1062 |
+
"eval_steps_per_second": 18.533,
|
| 1063 |
+
"step": 850
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 86.0,
|
| 1067 |
+
"eval_f1": 0.6844238563983788,
|
| 1068 |
+
"eval_loss": 1.3142564296722412,
|
| 1069 |
+
"eval_precision": 0.696113074204947,
|
| 1070 |
+
"eval_recall": 0.673120728929385,
|
| 1071 |
+
"eval_runtime": 0.1054,
|
| 1072 |
+
"eval_samples_per_second": 189.669,
|
| 1073 |
+
"eval_steps_per_second": 18.967,
|
| 1074 |
+
"step": 860
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 87.0,
|
| 1078 |
+
"eval_f1": 0.6868451688009312,
|
| 1079 |
+
"eval_loss": 1.3147000074386597,
|
| 1080 |
+
"eval_precision": 0.7023809523809523,
|
| 1081 |
+
"eval_recall": 0.6719817767653758,
|
| 1082 |
+
"eval_runtime": 0.1079,
|
| 1083 |
+
"eval_samples_per_second": 185.364,
|
| 1084 |
+
"eval_steps_per_second": 18.536,
|
| 1085 |
+
"step": 870
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 88.0,
|
| 1089 |
+
"eval_f1": 0.6852173913043478,
|
| 1090 |
+
"eval_loss": 1.3220981359481812,
|
| 1091 |
+
"eval_precision": 0.6977567886658795,
|
| 1092 |
+
"eval_recall": 0.673120728929385,
|
| 1093 |
+
"eval_runtime": 0.1143,
|
| 1094 |
+
"eval_samples_per_second": 175.042,
|
| 1095 |
+
"eval_steps_per_second": 17.504,
|
| 1096 |
+
"step": 880
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 89.0,
|
| 1100 |
+
"eval_f1": 0.6840277777777779,
|
| 1101 |
+
"eval_loss": 1.3263325691223145,
|
| 1102 |
+
"eval_precision": 0.6952941176470588,
|
| 1103 |
+
"eval_recall": 0.673120728929385,
|
| 1104 |
+
"eval_runtime": 0.1098,
|
| 1105 |
+
"eval_samples_per_second": 182.123,
|
| 1106 |
+
"eval_steps_per_second": 18.212,
|
| 1107 |
+
"step": 890
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 90.0,
|
| 1111 |
+
"grad_norm": 0.362501323223114,
|
| 1112 |
+
"learning_rate": 2.222222222222222e-06,
|
| 1113 |
+
"loss": 0.0467,
|
| 1114 |
+
"step": 900
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 90.0,
|
| 1118 |
+
"eval_f1": 0.6836321573163678,
|
| 1119 |
+
"eval_loss": 1.321544885635376,
|
| 1120 |
+
"eval_precision": 0.6944770857814336,
|
| 1121 |
+
"eval_recall": 0.673120728929385,
|
| 1122 |
+
"eval_runtime": 0.1062,
|
| 1123 |
+
"eval_samples_per_second": 188.379,
|
| 1124 |
+
"eval_steps_per_second": 18.838,
|
| 1125 |
+
"step": 900
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 91.0,
|
| 1129 |
+
"eval_f1": 0.6844238563983788,
|
| 1130 |
+
"eval_loss": 1.3238760232925415,
|
| 1131 |
+
"eval_precision": 0.696113074204947,
|
| 1132 |
+
"eval_recall": 0.673120728929385,
|
| 1133 |
+
"eval_runtime": 0.1075,
|
| 1134 |
+
"eval_samples_per_second": 186.029,
|
| 1135 |
+
"eval_steps_per_second": 18.603,
|
| 1136 |
+
"step": 910
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 92.0,
|
| 1140 |
+
"eval_f1": 0.6825028968713789,
|
| 1141 |
+
"eval_loss": 1.3248389959335327,
|
| 1142 |
+
"eval_precision": 0.6945754716981132,
|
| 1143 |
+
"eval_recall": 0.6708428246013668,
|
| 1144 |
+
"eval_runtime": 0.1058,
|
| 1145 |
+
"eval_samples_per_second": 189.077,
|
| 1146 |
+
"eval_steps_per_second": 18.908,
|
| 1147 |
+
"step": 920
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 93.0,
|
| 1151 |
+
"eval_f1": 0.6801853997682503,
|
| 1152 |
+
"eval_loss": 1.326583743095398,
|
| 1153 |
+
"eval_precision": 0.6922169811320755,
|
| 1154 |
+
"eval_recall": 0.6685649202733486,
|
| 1155 |
+
"eval_runtime": 0.1054,
|
| 1156 |
+
"eval_samples_per_second": 189.799,
|
| 1157 |
+
"eval_steps_per_second": 18.98,
|
| 1158 |
+
"step": 930
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 94.0,
|
| 1162 |
+
"eval_f1": 0.6836321573163678,
|
| 1163 |
+
"eval_loss": 1.3237107992172241,
|
| 1164 |
+
"eval_precision": 0.6944770857814336,
|
| 1165 |
+
"eval_recall": 0.673120728929385,
|
| 1166 |
+
"eval_runtime": 0.1053,
|
| 1167 |
+
"eval_samples_per_second": 189.896,
|
| 1168 |
+
"eval_steps_per_second": 18.99,
|
| 1169 |
+
"step": 940
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 95.0,
|
| 1173 |
+
"grad_norm": 0.33692023158073425,
|
| 1174 |
+
"learning_rate": 1.111111111111111e-06,
|
| 1175 |
+
"loss": 0.0451,
|
| 1176 |
+
"step": 950
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 95.0,
|
| 1180 |
+
"eval_f1": 0.6836321573163678,
|
| 1181 |
+
"eval_loss": 1.323667049407959,
|
| 1182 |
+
"eval_precision": 0.6944770857814336,
|
| 1183 |
+
"eval_recall": 0.673120728929385,
|
| 1184 |
+
"eval_runtime": 0.1052,
|
| 1185 |
+
"eval_samples_per_second": 190.154,
|
| 1186 |
+
"eval_steps_per_second": 19.015,
|
| 1187 |
+
"step": 950
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 96.0,
|
| 1191 |
+
"eval_f1": 0.6840579710144927,
|
| 1192 |
+
"eval_loss": 1.3248512744903564,
|
| 1193 |
+
"eval_precision": 0.6965761511216056,
|
| 1194 |
+
"eval_recall": 0.6719817767653758,
|
| 1195 |
+
"eval_runtime": 0.1046,
|
| 1196 |
+
"eval_samples_per_second": 191.223,
|
| 1197 |
+
"eval_steps_per_second": 19.122,
|
| 1198 |
+
"step": 960
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 97.0,
|
| 1202 |
+
"eval_f1": 0.6848520023215323,
|
| 1203 |
+
"eval_loss": 1.326843023300171,
|
| 1204 |
+
"eval_precision": 0.6982248520710059,
|
| 1205 |
+
"eval_recall": 0.6719817767653758,
|
| 1206 |
+
"eval_runtime": 0.1043,
|
| 1207 |
+
"eval_samples_per_second": 191.797,
|
| 1208 |
+
"eval_steps_per_second": 19.18,
|
| 1209 |
+
"step": 970
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 98.0,
|
| 1213 |
+
"eval_f1": 0.6852173913043478,
|
| 1214 |
+
"eval_loss": 1.3268158435821533,
|
| 1215 |
+
"eval_precision": 0.6977567886658795,
|
| 1216 |
+
"eval_recall": 0.673120728929385,
|
| 1217 |
+
"eval_runtime": 0.1047,
|
| 1218 |
+
"eval_samples_per_second": 190.969,
|
| 1219 |
+
"eval_steps_per_second": 19.097,
|
| 1220 |
+
"step": 980
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 99.0,
|
| 1224 |
+
"eval_f1": 0.6848203939745077,
|
| 1225 |
+
"eval_loss": 1.3256183862686157,
|
| 1226 |
+
"eval_precision": 0.6969339622641509,
|
| 1227 |
+
"eval_recall": 0.673120728929385,
|
| 1228 |
+
"eval_runtime": 0.1053,
|
| 1229 |
+
"eval_samples_per_second": 189.91,
|
| 1230 |
+
"eval_steps_per_second": 18.991,
|
| 1231 |
+
"step": 990
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 100.0,
|
| 1235 |
+
"grad_norm": 0.3960552215576172,
|
| 1236 |
+
"learning_rate": 0.0,
|
| 1237 |
+
"loss": 0.0445,
|
| 1238 |
+
"step": 1000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 100.0,
|
| 1242 |
+
"eval_f1": 0.6848203939745077,
|
| 1243 |
+
"eval_loss": 1.3252696990966797,
|
| 1244 |
+
"eval_precision": 0.6969339622641509,
|
| 1245 |
+
"eval_recall": 0.673120728929385,
|
| 1246 |
+
"eval_runtime": 0.1112,
|
| 1247 |
+
"eval_samples_per_second": 179.827,
|
| 1248 |
+
"eval_steps_per_second": 17.983,
|
| 1249 |
+
"step": 1000
|
| 1250 |
+
}
|
| 1251 |
+
],
|
| 1252 |
+
"logging_steps": 50,
|
| 1253 |
+
"max_steps": 1000,
|
| 1254 |
+
"num_input_tokens_seen": 0,
|
| 1255 |
+
"num_train_epochs": 100,
|
| 1256 |
+
"save_steps": 500,
|
| 1257 |
+
"stateful_callbacks": {
|
| 1258 |
+
"TrainerControl": {
|
| 1259 |
+
"args": {
|
| 1260 |
+
"should_epoch_stop": false,
|
| 1261 |
+
"should_evaluate": false,
|
| 1262 |
+
"should_log": false,
|
| 1263 |
+
"should_save": true,
|
| 1264 |
+
"should_training_stop": true
|
| 1265 |
+
},
|
| 1266 |
+
"attributes": {}
|
| 1267 |
+
}
|
| 1268 |
+
},
|
| 1269 |
+
"total_flos": 523292762112000.0,
|
| 1270 |
+
"train_batch_size": 16,
|
| 1271 |
+
"trial_name": null,
|
| 1272 |
+
"trial_params": null
|
| 1273 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:752be49abc948927108e2467a489df708fc2c98f0a2eb2cad2df41eff128d5d9
|
| 3 |
+
size 5304
|
checkpoint-1000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-770/config.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "B-Activity",
|
| 13 |
+
"1": "B-Administration",
|
| 14 |
+
"2": "B-Age",
|
| 15 |
+
"3": "B-Area",
|
| 16 |
+
"4": "B-Biological_attribute",
|
| 17 |
+
"5": "B-Biological_structure",
|
| 18 |
+
"6": "B-Clinical_event",
|
| 19 |
+
"7": "B-Color",
|
| 20 |
+
"8": "B-Coreference",
|
| 21 |
+
"9": "B-Date",
|
| 22 |
+
"10": "B-Detailed_description",
|
| 23 |
+
"11": "B-Diagnostic_procedure",
|
| 24 |
+
"12": "B-Disease_disorder",
|
| 25 |
+
"13": "B-Distance",
|
| 26 |
+
"14": "B-Dosage",
|
| 27 |
+
"15": "B-Duration",
|
| 28 |
+
"16": "B-Family_history",
|
| 29 |
+
"17": "B-Frequency",
|
| 30 |
+
"18": "B-Height",
|
| 31 |
+
"19": "B-History",
|
| 32 |
+
"20": "B-Lab_value",
|
| 33 |
+
"21": "B-Mass",
|
| 34 |
+
"22": "B-Medication",
|
| 35 |
+
"23": "B-Nonbiological_location",
|
| 36 |
+
"24": "B-Occupation",
|
| 37 |
+
"25": "B-Other_entity",
|
| 38 |
+
"26": "B-Other_event",
|
| 39 |
+
"27": "B-Outcome",
|
| 40 |
+
"28": "B-Personal_background",
|
| 41 |
+
"29": "B-Qualitative_concept",
|
| 42 |
+
"30": "B-Quantitative_concept",
|
| 43 |
+
"31": "B-Severity",
|
| 44 |
+
"32": "B-Sex",
|
| 45 |
+
"33": "B-Shape",
|
| 46 |
+
"34": "B-Sign_symptom",
|
| 47 |
+
"35": "B-Subject",
|
| 48 |
+
"36": "B-Texture",
|
| 49 |
+
"37": "B-Therapeutic_procedure",
|
| 50 |
+
"38": "B-Time",
|
| 51 |
+
"39": "B-Volume",
|
| 52 |
+
"40": "B-Weight",
|
| 53 |
+
"41": "I-Activity",
|
| 54 |
+
"42": "I-Administration",
|
| 55 |
+
"43": "I-Age",
|
| 56 |
+
"44": "I-Area",
|
| 57 |
+
"45": "I-Biological_structure",
|
| 58 |
+
"46": "I-Clinical_event",
|
| 59 |
+
"47": "I-Coreference",
|
| 60 |
+
"48": "I-Date",
|
| 61 |
+
"49": "I-Detailed_description",
|
| 62 |
+
"50": "I-Diagnostic_procedure",
|
| 63 |
+
"51": "I-Disease_disorder",
|
| 64 |
+
"52": "I-Distance",
|
| 65 |
+
"53": "I-Dosage",
|
| 66 |
+
"54": "I-Duration",
|
| 67 |
+
"55": "I-Family_history",
|
| 68 |
+
"56": "I-History",
|
| 69 |
+
"57": "I-Lab_value",
|
| 70 |
+
"58": "I-Mass",
|
| 71 |
+
"59": "I-Medication",
|
| 72 |
+
"60": "I-Nonbiological_location",
|
| 73 |
+
"61": "I-Other_entity",
|
| 74 |
+
"62": "I-Outcome",
|
| 75 |
+
"63": "I-Personal_background",
|
| 76 |
+
"64": "I-Quantitative_concept",
|
| 77 |
+
"65": "I-Severity",
|
| 78 |
+
"66": "I-Sex",
|
| 79 |
+
"67": "I-Sign_symptom",
|
| 80 |
+
"68": "I-Subject",
|
| 81 |
+
"69": "I-Texture",
|
| 82 |
+
"70": "I-Therapeutic_procedure",
|
| 83 |
+
"71": "I-Time",
|
| 84 |
+
"72": "I-Volume",
|
| 85 |
+
"73": "O"
|
| 86 |
+
},
|
| 87 |
+
"initializer_range": 0.02,
|
| 88 |
+
"label2id": {
|
| 89 |
+
"B-Activity": 0,
|
| 90 |
+
"B-Administration": 1,
|
| 91 |
+
"B-Age": 2,
|
| 92 |
+
"B-Area": 3,
|
| 93 |
+
"B-Biological_attribute": 4,
|
| 94 |
+
"B-Biological_structure": 5,
|
| 95 |
+
"B-Clinical_event": 6,
|
| 96 |
+
"B-Color": 7,
|
| 97 |
+
"B-Coreference": 8,
|
| 98 |
+
"B-Date": 9,
|
| 99 |
+
"B-Detailed_description": 10,
|
| 100 |
+
"B-Diagnostic_procedure": 11,
|
| 101 |
+
"B-Disease_disorder": 12,
|
| 102 |
+
"B-Distance": 13,
|
| 103 |
+
"B-Dosage": 14,
|
| 104 |
+
"B-Duration": 15,
|
| 105 |
+
"B-Family_history": 16,
|
| 106 |
+
"B-Frequency": 17,
|
| 107 |
+
"B-Height": 18,
|
| 108 |
+
"B-History": 19,
|
| 109 |
+
"B-Lab_value": 20,
|
| 110 |
+
"B-Mass": 21,
|
| 111 |
+
"B-Medication": 22,
|
| 112 |
+
"B-Nonbiological_location": 23,
|
| 113 |
+
"B-Occupation": 24,
|
| 114 |
+
"B-Other_entity": 25,
|
| 115 |
+
"B-Other_event": 26,
|
| 116 |
+
"B-Outcome": 27,
|
| 117 |
+
"B-Personal_background": 28,
|
| 118 |
+
"B-Qualitative_concept": 29,
|
| 119 |
+
"B-Quantitative_concept": 30,
|
| 120 |
+
"B-Severity": 31,
|
| 121 |
+
"B-Sex": 32,
|
| 122 |
+
"B-Shape": 33,
|
| 123 |
+
"B-Sign_symptom": 34,
|
| 124 |
+
"B-Subject": 35,
|
| 125 |
+
"B-Texture": 36,
|
| 126 |
+
"B-Therapeutic_procedure": 37,
|
| 127 |
+
"B-Time": 38,
|
| 128 |
+
"B-Volume": 39,
|
| 129 |
+
"B-Weight": 40,
|
| 130 |
+
"I-Activity": 41,
|
| 131 |
+
"I-Administration": 42,
|
| 132 |
+
"I-Age": 43,
|
| 133 |
+
"I-Area": 44,
|
| 134 |
+
"I-Biological_structure": 45,
|
| 135 |
+
"I-Clinical_event": 46,
|
| 136 |
+
"I-Coreference": 47,
|
| 137 |
+
"I-Date": 48,
|
| 138 |
+
"I-Detailed_description": 49,
|
| 139 |
+
"I-Diagnostic_procedure": 50,
|
| 140 |
+
"I-Disease_disorder": 51,
|
| 141 |
+
"I-Distance": 52,
|
| 142 |
+
"I-Dosage": 53,
|
| 143 |
+
"I-Duration": 54,
|
| 144 |
+
"I-Family_history": 55,
|
| 145 |
+
"I-History": 56,
|
| 146 |
+
"I-Lab_value": 57,
|
| 147 |
+
"I-Mass": 58,
|
| 148 |
+
"I-Medication": 59,
|
| 149 |
+
"I-Nonbiological_location": 60,
|
| 150 |
+
"I-Other_entity": 61,
|
| 151 |
+
"I-Outcome": 62,
|
| 152 |
+
"I-Personal_background": 63,
|
| 153 |
+
"I-Quantitative_concept": 64,
|
| 154 |
+
"I-Severity": 65,
|
| 155 |
+
"I-Sex": 66,
|
| 156 |
+
"I-Sign_symptom": 67,
|
| 157 |
+
"I-Subject": 68,
|
| 158 |
+
"I-Texture": 69,
|
| 159 |
+
"I-Therapeutic_procedure": 70,
|
| 160 |
+
"I-Time": 71,
|
| 161 |
+
"I-Volume": 72,
|
| 162 |
+
"O": 73
|
| 163 |
+
},
|
| 164 |
+
"max_position_embeddings": 512,
|
| 165 |
+
"model_type": "distilbert",
|
| 166 |
+
"n_heads": 12,
|
| 167 |
+
"n_layers": 6,
|
| 168 |
+
"pad_token_id": 0,
|
| 169 |
+
"qa_dropout": 0.1,
|
| 170 |
+
"seq_classif_dropout": 0.2,
|
| 171 |
+
"sinusoidal_pos_embds": false,
|
| 172 |
+
"tie_weights_": true,
|
| 173 |
+
"torch_dtype": "float32",
|
| 174 |
+
"transformers_version": "4.49.0",
|
| 175 |
+
"vocab_size": 30522
|
| 176 |
+
}
|
checkpoint-770/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:326f38cbbe8b00407d06f53521d4910fcb093e796b288f95c3aef96f06cc66a9
|
| 3 |
+
size 265691496
|
checkpoint-770/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da32f62356caaccc4e811a59680b274a7aefdd85a8e22e90d77e216351e85b11
|
| 3 |
+
size 531440954
|
checkpoint-770/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f56a8bf119fed612b50bb9bf41da5743f4e5076a930e56fb6dfdfa4736b2503
|
| 3 |
+
size 13990
|
checkpoint-770/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f3b3e477747577ebcf7c540abe93633653f5162401d45c09c21e1fd38c550ce
|
| 3 |
+
size 1064
|
checkpoint-770/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
checkpoint-770/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-770/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-770/trainer_state.json
ADDED
|
@@ -0,0 +1,985 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6937354988399073,
|
| 3 |
+
"best_model_checkpoint": "outputs/models/distilbert-clinical-ner/checkpoint-770",
|
| 4 |
+
"epoch": 77.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 770,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_f1": 0.019590382902938554,
|
| 14 |
+
"eval_loss": 4.235354900360107,
|
| 15 |
+
"eval_precision": 0.01608187134502924,
|
| 16 |
+
"eval_recall": 0.025056947608200455,
|
| 17 |
+
"eval_runtime": 0.1555,
|
| 18 |
+
"eval_samples_per_second": 128.613,
|
| 19 |
+
"eval_steps_per_second": 12.861,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_f1": 0.023399014778325126,
|
| 25 |
+
"eval_loss": 4.040920734405518,
|
| 26 |
+
"eval_precision": 0.02546916890080429,
|
| 27 |
+
"eval_recall": 0.02164009111617312,
|
| 28 |
+
"eval_runtime": 0.1064,
|
| 29 |
+
"eval_samples_per_second": 187.984,
|
| 30 |
+
"eval_steps_per_second": 18.798,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"eval_f1": 0.0045045045045045045,
|
| 36 |
+
"eval_loss": 3.6175544261932373,
|
| 37 |
+
"eval_precision": 0.2,
|
| 38 |
+
"eval_recall": 0.002277904328018223,
|
| 39 |
+
"eval_runtime": 0.1035,
|
| 40 |
+
"eval_samples_per_second": 193.236,
|
| 41 |
+
"eval_steps_per_second": 19.324,
|
| 42 |
+
"step": 30
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_f1": 0.0,
|
| 47 |
+
"eval_loss": 3.0632073879241943,
|
| 48 |
+
"eval_precision": 0.0,
|
| 49 |
+
"eval_recall": 0.0,
|
| 50 |
+
"eval_runtime": 0.1056,
|
| 51 |
+
"eval_samples_per_second": 189.304,
|
| 52 |
+
"eval_steps_per_second": 18.93,
|
| 53 |
+
"step": 40
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"grad_norm": 2.285052537918091,
|
| 58 |
+
"learning_rate": 1e-05,
|
| 59 |
+
"loss": 3.7184,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 5.0,
|
| 64 |
+
"eval_f1": 0.0,
|
| 65 |
+
"eval_loss": 2.6725738048553467,
|
| 66 |
+
"eval_precision": 0.0,
|
| 67 |
+
"eval_recall": 0.0,
|
| 68 |
+
"eval_runtime": 0.1038,
|
| 69 |
+
"eval_samples_per_second": 192.708,
|
| 70 |
+
"eval_steps_per_second": 19.271,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 6.0,
|
| 75 |
+
"eval_f1": 0.0022753128555176336,
|
| 76 |
+
"eval_loss": 2.3172459602355957,
|
| 77 |
+
"eval_precision": 1.0,
|
| 78 |
+
"eval_recall": 0.0011389521640091116,
|
| 79 |
+
"eval_runtime": 0.1056,
|
| 80 |
+
"eval_samples_per_second": 189.369,
|
| 81 |
+
"eval_steps_per_second": 18.937,
|
| 82 |
+
"step": 60
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 7.0,
|
| 86 |
+
"eval_f1": 0.24705882352941175,
|
| 87 |
+
"eval_loss": 2.010183334350586,
|
| 88 |
+
"eval_precision": 0.34854771784232363,
|
| 89 |
+
"eval_recall": 0.19134396355353075,
|
| 90 |
+
"eval_runtime": 0.1045,
|
| 91 |
+
"eval_samples_per_second": 191.384,
|
| 92 |
+
"eval_steps_per_second": 19.138,
|
| 93 |
+
"step": 70
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"eval_f1": 0.3578104138851802,
|
| 98 |
+
"eval_loss": 1.7770382165908813,
|
| 99 |
+
"eval_precision": 0.432258064516129,
|
| 100 |
+
"eval_recall": 0.3052391799544419,
|
| 101 |
+
"eval_runtime": 0.1043,
|
| 102 |
+
"eval_samples_per_second": 191.78,
|
| 103 |
+
"eval_steps_per_second": 19.178,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 9.0,
|
| 108 |
+
"eval_f1": 0.4306709265175719,
|
| 109 |
+
"eval_loss": 1.578804612159729,
|
| 110 |
+
"eval_precision": 0.49053857350800584,
|
| 111 |
+
"eval_recall": 0.3838268792710706,
|
| 112 |
+
"eval_runtime": 0.1049,
|
| 113 |
+
"eval_samples_per_second": 190.736,
|
| 114 |
+
"eval_steps_per_second": 19.074,
|
| 115 |
+
"step": 90
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 10.0,
|
| 119 |
+
"grad_norm": 1.6135512590408325,
|
| 120 |
+
"learning_rate": 2e-05,
|
| 121 |
+
"loss": 2.0341,
|
| 122 |
+
"step": 100
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 10.0,
|
| 126 |
+
"eval_f1": 0.5129151291512916,
|
| 127 |
+
"eval_loss": 1.4062659740447998,
|
| 128 |
+
"eval_precision": 0.5574866310160428,
|
| 129 |
+
"eval_recall": 0.47494305239179957,
|
| 130 |
+
"eval_runtime": 0.1053,
|
| 131 |
+
"eval_samples_per_second": 189.876,
|
| 132 |
+
"eval_steps_per_second": 18.988,
|
| 133 |
+
"step": 100
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 11.0,
|
| 137 |
+
"eval_f1": 0.5652435357787132,
|
| 138 |
+
"eval_loss": 1.2971620559692383,
|
| 139 |
+
"eval_precision": 0.5987261146496815,
|
| 140 |
+
"eval_recall": 0.5353075170842825,
|
| 141 |
+
"eval_runtime": 0.1046,
|
| 142 |
+
"eval_samples_per_second": 191.215,
|
| 143 |
+
"eval_steps_per_second": 19.122,
|
| 144 |
+
"step": 110
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.0,
|
| 148 |
+
"eval_f1": 0.5844155844155845,
|
| 149 |
+
"eval_loss": 1.22593092918396,
|
| 150 |
+
"eval_precision": 0.6066176470588235,
|
| 151 |
+
"eval_recall": 0.5637813211845103,
|
| 152 |
+
"eval_runtime": 0.1052,
|
| 153 |
+
"eval_samples_per_second": 190.037,
|
| 154 |
+
"eval_steps_per_second": 19.004,
|
| 155 |
+
"step": 120
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 13.0,
|
| 159 |
+
"eval_f1": 0.6020642201834862,
|
| 160 |
+
"eval_loss": 1.1731911897659302,
|
| 161 |
+
"eval_precision": 0.6062355658198614,
|
| 162 |
+
"eval_recall": 0.5979498861047836,
|
| 163 |
+
"eval_runtime": 0.1047,
|
| 164 |
+
"eval_samples_per_second": 190.934,
|
| 165 |
+
"eval_steps_per_second": 19.093,
|
| 166 |
+
"step": 130
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 14.0,
|
| 170 |
+
"eval_f1": 0.6093023255813953,
|
| 171 |
+
"eval_loss": 1.1392405033111572,
|
| 172 |
+
"eval_precision": 0.6223277909738717,
|
| 173 |
+
"eval_recall": 0.5968109339407744,
|
| 174 |
+
"eval_runtime": 0.1076,
|
| 175 |
+
"eval_samples_per_second": 185.839,
|
| 176 |
+
"eval_steps_per_second": 18.584,
|
| 177 |
+
"step": 140
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.0,
|
| 181 |
+
"grad_norm": 1.8851341009140015,
|
| 182 |
+
"learning_rate": 1.888888888888889e-05,
|
| 183 |
+
"loss": 1.0843,
|
| 184 |
+
"step": 150
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 15.0,
|
| 188 |
+
"eval_f1": 0.6329849012775842,
|
| 189 |
+
"eval_loss": 1.1109048128128052,
|
| 190 |
+
"eval_precision": 0.6457345971563981,
|
| 191 |
+
"eval_recall": 0.6207289293849658,
|
| 192 |
+
"eval_runtime": 0.1045,
|
| 193 |
+
"eval_samples_per_second": 191.342,
|
| 194 |
+
"eval_steps_per_second": 19.134,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 16.0,
|
| 199 |
+
"eval_f1": 0.6323103647944412,
|
| 200 |
+
"eval_loss": 1.111675500869751,
|
| 201 |
+
"eval_precision": 0.6431095406360424,
|
| 202 |
+
"eval_recall": 0.621867881548975,
|
| 203 |
+
"eval_runtime": 0.1064,
|
| 204 |
+
"eval_samples_per_second": 187.947,
|
| 205 |
+
"eval_steps_per_second": 18.795,
|
| 206 |
+
"step": 160
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 17.0,
|
| 210 |
+
"eval_f1": 0.6406976744186046,
|
| 211 |
+
"eval_loss": 1.1105479001998901,
|
| 212 |
+
"eval_precision": 0.6543942992874109,
|
| 213 |
+
"eval_recall": 0.6275626423690205,
|
| 214 |
+
"eval_runtime": 0.1038,
|
| 215 |
+
"eval_samples_per_second": 192.723,
|
| 216 |
+
"eval_steps_per_second": 19.272,
|
| 217 |
+
"step": 170
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 18.0,
|
| 221 |
+
"eval_f1": 0.6418338108882521,
|
| 222 |
+
"eval_loss": 1.1081936359405518,
|
| 223 |
+
"eval_precision": 0.6459054209919262,
|
| 224 |
+
"eval_recall": 0.6378132118451025,
|
| 225 |
+
"eval_runtime": 0.1093,
|
| 226 |
+
"eval_samples_per_second": 182.962,
|
| 227 |
+
"eval_steps_per_second": 18.296,
|
| 228 |
+
"step": 180
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 19.0,
|
| 232 |
+
"eval_f1": 0.656629994209612,
|
| 233 |
+
"eval_loss": 1.0905473232269287,
|
| 234 |
+
"eval_precision": 0.6678445229681979,
|
| 235 |
+
"eval_recall": 0.6457858769931663,
|
| 236 |
+
"eval_runtime": 0.1058,
|
| 237 |
+
"eval_samples_per_second": 189.016,
|
| 238 |
+
"eval_steps_per_second": 18.902,
|
| 239 |
+
"step": 190
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 20.0,
|
| 243 |
+
"grad_norm": 2.453874111175537,
|
| 244 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 245 |
+
"loss": 0.6709,
|
| 246 |
+
"step": 200
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 20.0,
|
| 250 |
+
"eval_f1": 0.6527536231884057,
|
| 251 |
+
"eval_loss": 1.0979650020599365,
|
| 252 |
+
"eval_precision": 0.6646989374262101,
|
| 253 |
+
"eval_recall": 0.6412300683371298,
|
| 254 |
+
"eval_runtime": 0.1051,
|
| 255 |
+
"eval_samples_per_second": 190.38,
|
| 256 |
+
"eval_steps_per_second": 19.038,
|
| 257 |
+
"step": 200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 21.0,
|
| 261 |
+
"eval_f1": 0.660889659156557,
|
| 262 |
+
"eval_loss": 1.1073075532913208,
|
| 263 |
+
"eval_precision": 0.6705744431418523,
|
| 264 |
+
"eval_recall": 0.6514806378132119,
|
| 265 |
+
"eval_runtime": 0.1063,
|
| 266 |
+
"eval_samples_per_second": 188.158,
|
| 267 |
+
"eval_steps_per_second": 18.816,
|
| 268 |
+
"step": 210
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 22.0,
|
| 272 |
+
"eval_f1": 0.6520231213872832,
|
| 273 |
+
"eval_loss": 1.109878420829773,
|
| 274 |
+
"eval_precision": 0.6619718309859155,
|
| 275 |
+
"eval_recall": 0.642369020501139,
|
| 276 |
+
"eval_runtime": 0.1108,
|
| 277 |
+
"eval_samples_per_second": 180.582,
|
| 278 |
+
"eval_steps_per_second": 18.058,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 23.0,
|
| 283 |
+
"eval_f1": 0.6666666666666666,
|
| 284 |
+
"eval_loss": 1.1079308986663818,
|
| 285 |
+
"eval_precision": 0.6838323353293413,
|
| 286 |
+
"eval_recall": 0.6503416856492027,
|
| 287 |
+
"eval_runtime": 0.1051,
|
| 288 |
+
"eval_samples_per_second": 190.371,
|
| 289 |
+
"eval_steps_per_second": 19.037,
|
| 290 |
+
"step": 230
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 24.0,
|
| 294 |
+
"eval_f1": 0.6685714285714285,
|
| 295 |
+
"eval_loss": 1.0995490550994873,
|
| 296 |
+
"eval_precision": 0.6708715596330275,
|
| 297 |
+
"eval_recall": 0.6662870159453302,
|
| 298 |
+
"eval_runtime": 0.1076,
|
| 299 |
+
"eval_samples_per_second": 185.917,
|
| 300 |
+
"eval_steps_per_second": 18.592,
|
| 301 |
+
"step": 240
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 25.0,
|
| 305 |
+
"grad_norm": 1.9804632663726807,
|
| 306 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 307 |
+
"loss": 0.4563,
|
| 308 |
+
"step": 250
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 25.0,
|
| 312 |
+
"eval_f1": 0.6623831775700935,
|
| 313 |
+
"eval_loss": 1.1412475109100342,
|
| 314 |
+
"eval_precision": 0.6798561151079137,
|
| 315 |
+
"eval_recall": 0.6457858769931663,
|
| 316 |
+
"eval_runtime": 0.1043,
|
| 317 |
+
"eval_samples_per_second": 191.672,
|
| 318 |
+
"eval_steps_per_second": 19.167,
|
| 319 |
+
"step": 250
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 26.0,
|
| 323 |
+
"eval_f1": 0.6685878962536023,
|
| 324 |
+
"eval_loss": 1.1206316947937012,
|
| 325 |
+
"eval_precision": 0.676779463243874,
|
| 326 |
+
"eval_recall": 0.6605922551252847,
|
| 327 |
+
"eval_runtime": 0.1025,
|
| 328 |
+
"eval_samples_per_second": 195.213,
|
| 329 |
+
"eval_steps_per_second": 19.521,
|
| 330 |
+
"step": 260
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 27.0,
|
| 334 |
+
"eval_f1": 0.674013921113689,
|
| 335 |
+
"eval_loss": 1.1223537921905518,
|
| 336 |
+
"eval_precision": 0.6867612293144209,
|
| 337 |
+
"eval_recall": 0.6617312072892938,
|
| 338 |
+
"eval_runtime": 0.1023,
|
| 339 |
+
"eval_samples_per_second": 195.488,
|
| 340 |
+
"eval_steps_per_second": 19.549,
|
| 341 |
+
"step": 270
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 28.0,
|
| 345 |
+
"eval_f1": 0.6787595084844938,
|
| 346 |
+
"eval_loss": 1.1268706321716309,
|
| 347 |
+
"eval_precision": 0.6979542719614922,
|
| 348 |
+
"eval_recall": 0.6605922551252847,
|
| 349 |
+
"eval_runtime": 0.107,
|
| 350 |
+
"eval_samples_per_second": 186.844,
|
| 351 |
+
"eval_steps_per_second": 18.684,
|
| 352 |
+
"step": 280
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 29.0,
|
| 356 |
+
"eval_f1": 0.6817391304347827,
|
| 357 |
+
"eval_loss": 1.143689751625061,
|
| 358 |
+
"eval_precision": 0.6942148760330579,
|
| 359 |
+
"eval_recall": 0.6697038724373576,
|
| 360 |
+
"eval_runtime": 0.1048,
|
| 361 |
+
"eval_samples_per_second": 190.916,
|
| 362 |
+
"eval_steps_per_second": 19.092,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 30.0,
|
| 367 |
+
"grad_norm": 1.2570631504058838,
|
| 368 |
+
"learning_rate": 1.555555555555556e-05,
|
| 369 |
+
"loss": 0.3229,
|
| 370 |
+
"step": 300
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 30.0,
|
| 374 |
+
"eval_f1": 0.6781807714450201,
|
| 375 |
+
"eval_loss": 1.1411770582199097,
|
| 376 |
+
"eval_precision": 0.6856810244470314,
|
| 377 |
+
"eval_recall": 0.6708428246013668,
|
| 378 |
+
"eval_runtime": 0.1118,
|
| 379 |
+
"eval_samples_per_second": 178.865,
|
| 380 |
+
"eval_steps_per_second": 17.887,
|
| 381 |
+
"step": 300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 31.0,
|
| 385 |
+
"eval_f1": 0.6797235023041475,
|
| 386 |
+
"eval_loss": 1.1665282249450684,
|
| 387 |
+
"eval_precision": 0.6876456876456877,
|
| 388 |
+
"eval_recall": 0.6719817767653758,
|
| 389 |
+
"eval_runtime": 0.1061,
|
| 390 |
+
"eval_samples_per_second": 188.516,
|
| 391 |
+
"eval_steps_per_second": 18.852,
|
| 392 |
+
"step": 310
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 32.0,
|
| 396 |
+
"eval_f1": 0.6785714285714286,
|
| 397 |
+
"eval_loss": 1.147858738899231,
|
| 398 |
+
"eval_precision": 0.6864801864801865,
|
| 399 |
+
"eval_recall": 0.6708428246013668,
|
| 400 |
+
"eval_runtime": 0.1079,
|
| 401 |
+
"eval_samples_per_second": 185.36,
|
| 402 |
+
"eval_steps_per_second": 18.536,
|
| 403 |
+
"step": 320
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 33.0,
|
| 407 |
+
"eval_f1": 0.6774193548387096,
|
| 408 |
+
"eval_loss": 1.1554282903671265,
|
| 409 |
+
"eval_precision": 0.6853146853146853,
|
| 410 |
+
"eval_recall": 0.6697038724373576,
|
| 411 |
+
"eval_runtime": 0.1037,
|
| 412 |
+
"eval_samples_per_second": 192.925,
|
| 413 |
+
"eval_steps_per_second": 19.292,
|
| 414 |
+
"step": 330
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 34.0,
|
| 418 |
+
"eval_f1": 0.6797687861271676,
|
| 419 |
+
"eval_loss": 1.15742027759552,
|
| 420 |
+
"eval_precision": 0.6901408450704225,
|
| 421 |
+
"eval_recall": 0.6697038724373576,
|
| 422 |
+
"eval_runtime": 0.1053,
|
| 423 |
+
"eval_samples_per_second": 189.904,
|
| 424 |
+
"eval_steps_per_second": 18.99,
|
| 425 |
+
"step": 340
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 35.0,
|
| 429 |
+
"grad_norm": 1.0945429801940918,
|
| 430 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 431 |
+
"loss": 0.2396,
|
| 432 |
+
"step": 350
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 35.0,
|
| 436 |
+
"eval_f1": 0.6797235023041475,
|
| 437 |
+
"eval_loss": 1.1754865646362305,
|
| 438 |
+
"eval_precision": 0.6876456876456877,
|
| 439 |
+
"eval_recall": 0.6719817767653758,
|
| 440 |
+
"eval_runtime": 0.1057,
|
| 441 |
+
"eval_samples_per_second": 189.199,
|
| 442 |
+
"eval_steps_per_second": 18.92,
|
| 443 |
+
"step": 350
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 36.0,
|
| 447 |
+
"eval_f1": 0.6735870818915801,
|
| 448 |
+
"eval_loss": 1.1885067224502563,
|
| 449 |
+
"eval_precision": 0.6822429906542056,
|
| 450 |
+
"eval_recall": 0.6651480637813212,
|
| 451 |
+
"eval_runtime": 0.1,
|
| 452 |
+
"eval_samples_per_second": 200.0,
|
| 453 |
+
"eval_steps_per_second": 20.0,
|
| 454 |
+
"step": 360
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 37.0,
|
| 458 |
+
"eval_f1": 0.6806526806526807,
|
| 459 |
+
"eval_loss": 1.181584119796753,
|
| 460 |
+
"eval_precision": 0.6968973747016707,
|
| 461 |
+
"eval_recall": 0.6651480637813212,
|
| 462 |
+
"eval_runtime": 0.1076,
|
| 463 |
+
"eval_samples_per_second": 185.858,
|
| 464 |
+
"eval_steps_per_second": 18.586,
|
| 465 |
+
"step": 370
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 38.0,
|
| 469 |
+
"eval_f1": 0.6787172011661807,
|
| 470 |
+
"eval_loss": 1.1876161098480225,
|
| 471 |
+
"eval_precision": 0.6953405017921147,
|
| 472 |
+
"eval_recall": 0.662870159453303,
|
| 473 |
+
"eval_runtime": 0.1161,
|
| 474 |
+
"eval_samples_per_second": 172.269,
|
| 475 |
+
"eval_steps_per_second": 17.227,
|
| 476 |
+
"step": 380
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 39.0,
|
| 480 |
+
"eval_f1": 0.6818713450292397,
|
| 481 |
+
"eval_loss": 1.2116471529006958,
|
| 482 |
+
"eval_precision": 0.7007211538461539,
|
| 483 |
+
"eval_recall": 0.664009111617312,
|
| 484 |
+
"eval_runtime": 0.1027,
|
| 485 |
+
"eval_samples_per_second": 194.71,
|
| 486 |
+
"eval_steps_per_second": 19.471,
|
| 487 |
+
"step": 390
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 40.0,
|
| 491 |
+
"grad_norm": 0.8599975109100342,
|
| 492 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 493 |
+
"loss": 0.1848,
|
| 494 |
+
"step": 400
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 40.0,
|
| 498 |
+
"eval_f1": 0.6786542923433874,
|
| 499 |
+
"eval_loss": 1.1997044086456299,
|
| 500 |
+
"eval_precision": 0.6914893617021277,
|
| 501 |
+
"eval_recall": 0.6662870159453302,
|
| 502 |
+
"eval_runtime": 0.1098,
|
| 503 |
+
"eval_samples_per_second": 182.124,
|
| 504 |
+
"eval_steps_per_second": 18.212,
|
| 505 |
+
"step": 400
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 41.0,
|
| 509 |
+
"eval_f1": 0.6817917393833625,
|
| 510 |
+
"eval_loss": 1.2281190156936646,
|
| 511 |
+
"eval_precision": 0.6967895362663495,
|
| 512 |
+
"eval_recall": 0.6674259681093394,
|
| 513 |
+
"eval_runtime": 0.1026,
|
| 514 |
+
"eval_samples_per_second": 195.027,
|
| 515 |
+
"eval_steps_per_second": 19.503,
|
| 516 |
+
"step": 410
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 42.0,
|
| 520 |
+
"eval_f1": 0.6820542412002308,
|
| 521 |
+
"eval_loss": 1.205224633216858,
|
| 522 |
+
"eval_precision": 0.6912280701754386,
|
| 523 |
+
"eval_recall": 0.673120728929385,
|
| 524 |
+
"eval_runtime": 0.1029,
|
| 525 |
+
"eval_samples_per_second": 194.454,
|
| 526 |
+
"eval_steps_per_second": 19.445,
|
| 527 |
+
"step": 420
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 43.0,
|
| 531 |
+
"eval_f1": 0.6834112149532711,
|
| 532 |
+
"eval_loss": 1.2441879510879517,
|
| 533 |
+
"eval_precision": 0.7014388489208633,
|
| 534 |
+
"eval_recall": 0.6662870159453302,
|
| 535 |
+
"eval_runtime": 0.1013,
|
| 536 |
+
"eval_samples_per_second": 197.51,
|
| 537 |
+
"eval_steps_per_second": 19.751,
|
| 538 |
+
"step": 430
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 44.0,
|
| 542 |
+
"eval_f1": 0.6762672811059909,
|
| 543 |
+
"eval_loss": 1.2410287857055664,
|
| 544 |
+
"eval_precision": 0.6841491841491841,
|
| 545 |
+
"eval_recall": 0.6685649202733486,
|
| 546 |
+
"eval_runtime": 0.1039,
|
| 547 |
+
"eval_samples_per_second": 192.454,
|
| 548 |
+
"eval_steps_per_second": 19.245,
|
| 549 |
+
"step": 440
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 45.0,
|
| 553 |
+
"grad_norm": 0.8666434288024902,
|
| 554 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 555 |
+
"loss": 0.1472,
|
| 556 |
+
"step": 450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 45.0,
|
| 560 |
+
"eval_f1": 0.6809744779582366,
|
| 561 |
+
"eval_loss": 1.2373775243759155,
|
| 562 |
+
"eval_precision": 0.693853427895981,
|
| 563 |
+
"eval_recall": 0.6685649202733486,
|
| 564 |
+
"eval_runtime": 0.1016,
|
| 565 |
+
"eval_samples_per_second": 196.912,
|
| 566 |
+
"eval_steps_per_second": 19.691,
|
| 567 |
+
"step": 450
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 46.0,
|
| 571 |
+
"eval_f1": 0.6786961583236321,
|
| 572 |
+
"eval_loss": 1.237067461013794,
|
| 573 |
+
"eval_precision": 0.694047619047619,
|
| 574 |
+
"eval_recall": 0.664009111617312,
|
| 575 |
+
"eval_runtime": 0.1002,
|
| 576 |
+
"eval_samples_per_second": 199.663,
|
| 577 |
+
"eval_steps_per_second": 19.966,
|
| 578 |
+
"step": 460
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 47.0,
|
| 582 |
+
"eval_f1": 0.6889016676250718,
|
| 583 |
+
"eval_loss": 1.2270065546035767,
|
| 584 |
+
"eval_precision": 0.6957026713124274,
|
| 585 |
+
"eval_recall": 0.6822323462414579,
|
| 586 |
+
"eval_runtime": 0.1051,
|
| 587 |
+
"eval_samples_per_second": 190.295,
|
| 588 |
+
"eval_steps_per_second": 19.03,
|
| 589 |
+
"step": 470
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 48.0,
|
| 593 |
+
"eval_f1": 0.6805555555555555,
|
| 594 |
+
"eval_loss": 1.238765001296997,
|
| 595 |
+
"eval_precision": 0.691764705882353,
|
| 596 |
+
"eval_recall": 0.6697038724373576,
|
| 597 |
+
"eval_runtime": 0.1066,
|
| 598 |
+
"eval_samples_per_second": 187.677,
|
| 599 |
+
"eval_steps_per_second": 18.768,
|
| 600 |
+
"step": 480
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 49.0,
|
| 604 |
+
"eval_f1": 0.6790914385556202,
|
| 605 |
+
"eval_loss": 1.2525634765625,
|
| 606 |
+
"eval_precision": 0.6948748510131109,
|
| 607 |
+
"eval_recall": 0.664009111617312,
|
| 608 |
+
"eval_runtime": 0.1021,
|
| 609 |
+
"eval_samples_per_second": 195.942,
|
| 610 |
+
"eval_steps_per_second": 19.594,
|
| 611 |
+
"step": 490
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 50.0,
|
| 615 |
+
"grad_norm": 0.8096102476119995,
|
| 616 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 617 |
+
"loss": 0.1184,
|
| 618 |
+
"step": 500
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 50.0,
|
| 622 |
+
"eval_f1": 0.681421083284799,
|
| 623 |
+
"eval_loss": 1.2390888929367065,
|
| 624 |
+
"eval_precision": 0.6972586412395709,
|
| 625 |
+
"eval_recall": 0.6662870159453302,
|
| 626 |
+
"eval_runtime": 0.1042,
|
| 627 |
+
"eval_samples_per_second": 191.926,
|
| 628 |
+
"eval_steps_per_second": 19.193,
|
| 629 |
+
"step": 500
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 51.0,
|
| 633 |
+
"eval_f1": 0.6782810685249709,
|
| 634 |
+
"eval_loss": 1.2617552280426025,
|
| 635 |
+
"eval_precision": 0.6919431279620853,
|
| 636 |
+
"eval_recall": 0.6651480637813212,
|
| 637 |
+
"eval_runtime": 0.1011,
|
| 638 |
+
"eval_samples_per_second": 197.736,
|
| 639 |
+
"eval_steps_per_second": 19.774,
|
| 640 |
+
"step": 510
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 52.0,
|
| 644 |
+
"eval_f1": 0.6814469078179697,
|
| 645 |
+
"eval_loss": 1.2573115825653076,
|
| 646 |
+
"eval_precision": 0.6985645933014354,
|
| 647 |
+
"eval_recall": 0.6651480637813212,
|
| 648 |
+
"eval_runtime": 0.1033,
|
| 649 |
+
"eval_samples_per_second": 193.643,
|
| 650 |
+
"eval_steps_per_second": 19.364,
|
| 651 |
+
"step": 520
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 53.0,
|
| 655 |
+
"eval_f1": 0.681369704004643,
|
| 656 |
+
"eval_loss": 1.2631280422210693,
|
| 657 |
+
"eval_precision": 0.6946745562130178,
|
| 658 |
+
"eval_recall": 0.6685649202733486,
|
| 659 |
+
"eval_runtime": 0.1027,
|
| 660 |
+
"eval_samples_per_second": 194.742,
|
| 661 |
+
"eval_steps_per_second": 19.474,
|
| 662 |
+
"step": 530
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 54.0,
|
| 666 |
+
"eval_f1": 0.6822429906542057,
|
| 667 |
+
"eval_loss": 1.2612630128860474,
|
| 668 |
+
"eval_precision": 0.7002398081534772,
|
| 669 |
+
"eval_recall": 0.6651480637813212,
|
| 670 |
+
"eval_runtime": 0.1034,
|
| 671 |
+
"eval_samples_per_second": 193.355,
|
| 672 |
+
"eval_steps_per_second": 19.335,
|
| 673 |
+
"step": 540
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 55.0,
|
| 677 |
+
"grad_norm": 1.258770227432251,
|
| 678 |
+
"learning_rate": 1e-05,
|
| 679 |
+
"loss": 0.0965,
|
| 680 |
+
"step": 550
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 55.0,
|
| 684 |
+
"eval_f1": 0.678592036930179,
|
| 685 |
+
"eval_loss": 1.2565994262695312,
|
| 686 |
+
"eval_precision": 0.6877192982456141,
|
| 687 |
+
"eval_recall": 0.6697038724373576,
|
| 688 |
+
"eval_runtime": 0.1065,
|
| 689 |
+
"eval_samples_per_second": 187.769,
|
| 690 |
+
"eval_steps_per_second": 18.777,
|
| 691 |
+
"step": 550
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 56.0,
|
| 695 |
+
"eval_f1": 0.6720461095100864,
|
| 696 |
+
"eval_loss": 1.286030888557434,
|
| 697 |
+
"eval_precision": 0.6802800466744457,
|
| 698 |
+
"eval_recall": 0.664009111617312,
|
| 699 |
+
"eval_runtime": 0.1017,
|
| 700 |
+
"eval_samples_per_second": 196.637,
|
| 701 |
+
"eval_steps_per_second": 19.664,
|
| 702 |
+
"step": 560
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 57.0,
|
| 706 |
+
"eval_f1": 0.6774941995359629,
|
| 707 |
+
"eval_loss": 1.2746167182922363,
|
| 708 |
+
"eval_precision": 0.6903073286052009,
|
| 709 |
+
"eval_recall": 0.6651480637813212,
|
| 710 |
+
"eval_runtime": 0.104,
|
| 711 |
+
"eval_samples_per_second": 192.291,
|
| 712 |
+
"eval_steps_per_second": 19.229,
|
| 713 |
+
"step": 570
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 58.0,
|
| 717 |
+
"eval_f1": 0.6813441483198146,
|
| 718 |
+
"eval_loss": 1.2719839811325073,
|
| 719 |
+
"eval_precision": 0.6933962264150944,
|
| 720 |
+
"eval_recall": 0.6697038724373576,
|
| 721 |
+
"eval_runtime": 0.1009,
|
| 722 |
+
"eval_samples_per_second": 198.12,
|
| 723 |
+
"eval_steps_per_second": 19.812,
|
| 724 |
+
"step": 580
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 59.0,
|
| 728 |
+
"eval_f1": 0.6845168800931315,
|
| 729 |
+
"eval_loss": 1.2790720462799072,
|
| 730 |
+
"eval_precision": 0.7,
|
| 731 |
+
"eval_recall": 0.6697038724373576,
|
| 732 |
+
"eval_runtime": 0.1025,
|
| 733 |
+
"eval_samples_per_second": 195.09,
|
| 734 |
+
"eval_steps_per_second": 19.509,
|
| 735 |
+
"step": 590
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 60.0,
|
| 739 |
+
"grad_norm": 0.6421855688095093,
|
| 740 |
+
"learning_rate": 8.888888888888888e-06,
|
| 741 |
+
"loss": 0.0841,
|
| 742 |
+
"step": 600
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 60.0,
|
| 746 |
+
"eval_f1": 0.6827309236947792,
|
| 747 |
+
"eval_loss": 1.2661317586898804,
|
| 748 |
+
"eval_precision": 0.6878612716763006,
|
| 749 |
+
"eval_recall": 0.6776765375854215,
|
| 750 |
+
"eval_runtime": 0.1054,
|
| 751 |
+
"eval_samples_per_second": 189.834,
|
| 752 |
+
"eval_steps_per_second": 18.983,
|
| 753 |
+
"step": 600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 61.0,
|
| 757 |
+
"eval_f1": 0.6803039158386909,
|
| 758 |
+
"eval_loss": 1.2873255014419556,
|
| 759 |
+
"eval_precision": 0.6986794717887155,
|
| 760 |
+
"eval_recall": 0.662870159453303,
|
| 761 |
+
"eval_runtime": 0.1028,
|
| 762 |
+
"eval_samples_per_second": 194.643,
|
| 763 |
+
"eval_steps_per_second": 19.464,
|
| 764 |
+
"step": 610
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 62.0,
|
| 768 |
+
"eval_f1": 0.6809248554913295,
|
| 769 |
+
"eval_loss": 1.2766045331954956,
|
| 770 |
+
"eval_precision": 0.6913145539906104,
|
| 771 |
+
"eval_recall": 0.6708428246013668,
|
| 772 |
+
"eval_runtime": 0.1044,
|
| 773 |
+
"eval_samples_per_second": 191.487,
|
| 774 |
+
"eval_steps_per_second": 19.149,
|
| 775 |
+
"step": 620
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 63.0,
|
| 779 |
+
"eval_f1": 0.6755658734764944,
|
| 780 |
+
"eval_loss": 1.2915081977844238,
|
| 781 |
+
"eval_precision": 0.6887573964497041,
|
| 782 |
+
"eval_recall": 0.662870159453303,
|
| 783 |
+
"eval_runtime": 0.1078,
|
| 784 |
+
"eval_samples_per_second": 185.542,
|
| 785 |
+
"eval_steps_per_second": 18.554,
|
| 786 |
+
"step": 630
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 64.0,
|
| 790 |
+
"eval_f1": 0.6732101616628174,
|
| 791 |
+
"eval_loss": 1.2793446779251099,
|
| 792 |
+
"eval_precision": 0.6826697892271663,
|
| 793 |
+
"eval_recall": 0.664009111617312,
|
| 794 |
+
"eval_runtime": 0.1016,
|
| 795 |
+
"eval_samples_per_second": 196.942,
|
| 796 |
+
"eval_steps_per_second": 19.694,
|
| 797 |
+
"step": 640
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 65.0,
|
| 801 |
+
"grad_norm": 0.5916463136672974,
|
| 802 |
+
"learning_rate": 7.77777777777778e-06,
|
| 803 |
+
"loss": 0.0714,
|
| 804 |
+
"step": 650
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 65.0,
|
| 808 |
+
"eval_f1": 0.6820276497695852,
|
| 809 |
+
"eval_loss": 1.3019025325775146,
|
| 810 |
+
"eval_precision": 0.6899766899766899,
|
| 811 |
+
"eval_recall": 0.6742596810933941,
|
| 812 |
+
"eval_runtime": 0.1008,
|
| 813 |
+
"eval_samples_per_second": 198.393,
|
| 814 |
+
"eval_steps_per_second": 19.839,
|
| 815 |
+
"step": 650
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 66.0,
|
| 819 |
+
"eval_f1": 0.6853473438412142,
|
| 820 |
+
"eval_loss": 1.2911741733551025,
|
| 821 |
+
"eval_precision": 0.7029940119760479,
|
| 822 |
+
"eval_recall": 0.6685649202733486,
|
| 823 |
+
"eval_runtime": 0.106,
|
| 824 |
+
"eval_samples_per_second": 188.757,
|
| 825 |
+
"eval_steps_per_second": 18.876,
|
| 826 |
+
"step": 660
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 67.0,
|
| 830 |
+
"eval_f1": 0.67816091954023,
|
| 831 |
+
"eval_loss": 1.2967917919158936,
|
| 832 |
+
"eval_precision": 0.6844547563805105,
|
| 833 |
+
"eval_recall": 0.6719817767653758,
|
| 834 |
+
"eval_runtime": 0.1092,
|
| 835 |
+
"eval_samples_per_second": 183.175,
|
| 836 |
+
"eval_steps_per_second": 18.318,
|
| 837 |
+
"step": 670
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 68.0,
|
| 841 |
+
"eval_f1": 0.6895348837209303,
|
| 842 |
+
"eval_loss": 1.2946228981018066,
|
| 843 |
+
"eval_precision": 0.7042755344418052,
|
| 844 |
+
"eval_recall": 0.6753986332574032,
|
| 845 |
+
"eval_runtime": 0.1052,
|
| 846 |
+
"eval_samples_per_second": 190.167,
|
| 847 |
+
"eval_steps_per_second": 19.017,
|
| 848 |
+
"step": 680
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 69.0,
|
| 852 |
+
"eval_f1": 0.6863425925925927,
|
| 853 |
+
"eval_loss": 1.2976857423782349,
|
| 854 |
+
"eval_precision": 0.6976470588235294,
|
| 855 |
+
"eval_recall": 0.6753986332574032,
|
| 856 |
+
"eval_runtime": 0.103,
|
| 857 |
+
"eval_samples_per_second": 194.22,
|
| 858 |
+
"eval_steps_per_second": 19.422,
|
| 859 |
+
"step": 690
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 70.0,
|
| 863 |
+
"grad_norm": 0.7995481491088867,
|
| 864 |
+
"learning_rate": 6.666666666666667e-06,
|
| 865 |
+
"loss": 0.064,
|
| 866 |
+
"step": 700
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 70.0,
|
| 870 |
+
"eval_f1": 0.6771014492753623,
|
| 871 |
+
"eval_loss": 1.295568585395813,
|
| 872 |
+
"eval_precision": 0.6894923258559622,
|
| 873 |
+
"eval_recall": 0.6651480637813212,
|
| 874 |
+
"eval_runtime": 0.1031,
|
| 875 |
+
"eval_samples_per_second": 193.92,
|
| 876 |
+
"eval_steps_per_second": 19.392,
|
| 877 |
+
"step": 700
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 71.0,
|
| 881 |
+
"eval_f1": 0.6797687861271676,
|
| 882 |
+
"eval_loss": 1.2898850440979004,
|
| 883 |
+
"eval_precision": 0.6901408450704225,
|
| 884 |
+
"eval_recall": 0.6697038724373576,
|
| 885 |
+
"eval_runtime": 0.1005,
|
| 886 |
+
"eval_samples_per_second": 198.942,
|
| 887 |
+
"eval_steps_per_second": 19.894,
|
| 888 |
+
"step": 710
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 72.0,
|
| 892 |
+
"eval_f1": 0.6806526806526807,
|
| 893 |
+
"eval_loss": 1.3075172901153564,
|
| 894 |
+
"eval_precision": 0.6968973747016707,
|
| 895 |
+
"eval_recall": 0.6651480637813212,
|
| 896 |
+
"eval_runtime": 0.1087,
|
| 897 |
+
"eval_samples_per_second": 184.017,
|
| 898 |
+
"eval_steps_per_second": 18.402,
|
| 899 |
+
"step": 720
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 73.0,
|
| 903 |
+
"eval_f1": 0.683750728013978,
|
| 904 |
+
"eval_loss": 1.2973222732543945,
|
| 905 |
+
"eval_precision": 0.699642431466031,
|
| 906 |
+
"eval_recall": 0.6685649202733486,
|
| 907 |
+
"eval_runtime": 0.1054,
|
| 908 |
+
"eval_samples_per_second": 189.672,
|
| 909 |
+
"eval_steps_per_second": 18.967,
|
| 910 |
+
"step": 730
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 74.0,
|
| 914 |
+
"eval_f1": 0.6872812135355894,
|
| 915 |
+
"eval_loss": 1.3102946281433105,
|
| 916 |
+
"eval_precision": 0.7045454545454546,
|
| 917 |
+
"eval_recall": 0.6708428246013668,
|
| 918 |
+
"eval_runtime": 0.1064,
|
| 919 |
+
"eval_samples_per_second": 188.0,
|
| 920 |
+
"eval_steps_per_second": 18.8,
|
| 921 |
+
"step": 740
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 75.0,
|
| 925 |
+
"grad_norm": 0.8353786468505859,
|
| 926 |
+
"learning_rate": 5.555555555555557e-06,
|
| 927 |
+
"loss": 0.0575,
|
| 928 |
+
"step": 750
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 75.0,
|
| 932 |
+
"eval_f1": 0.6797915460335843,
|
| 933 |
+
"eval_loss": 1.3147099018096924,
|
| 934 |
+
"eval_precision": 0.6914016489988222,
|
| 935 |
+
"eval_recall": 0.6685649202733486,
|
| 936 |
+
"eval_runtime": 0.1049,
|
| 937 |
+
"eval_samples_per_second": 190.589,
|
| 938 |
+
"eval_steps_per_second": 19.059,
|
| 939 |
+
"step": 750
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 76.0,
|
| 943 |
+
"eval_f1": 0.6845168800931315,
|
| 944 |
+
"eval_loss": 1.3087732791900635,
|
| 945 |
+
"eval_precision": 0.7,
|
| 946 |
+
"eval_recall": 0.6697038724373576,
|
| 947 |
+
"eval_runtime": 0.105,
|
| 948 |
+
"eval_samples_per_second": 190.4,
|
| 949 |
+
"eval_steps_per_second": 19.04,
|
| 950 |
+
"step": 760
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 77.0,
|
| 954 |
+
"eval_f1": 0.6937354988399073,
|
| 955 |
+
"eval_loss": 1.3092721700668335,
|
| 956 |
+
"eval_precision": 0.706855791962175,
|
| 957 |
+
"eval_recall": 0.6810933940774487,
|
| 958 |
+
"eval_runtime": 0.1053,
|
| 959 |
+
"eval_samples_per_second": 189.996,
|
| 960 |
+
"eval_steps_per_second": 19.0,
|
| 961 |
+
"step": 770
|
| 962 |
+
}
|
| 963 |
+
],
|
| 964 |
+
"logging_steps": 50,
|
| 965 |
+
"max_steps": 1000,
|
| 966 |
+
"num_input_tokens_seen": 0,
|
| 967 |
+
"num_train_epochs": 100,
|
| 968 |
+
"save_steps": 500,
|
| 969 |
+
"stateful_callbacks": {
|
| 970 |
+
"TrainerControl": {
|
| 971 |
+
"args": {
|
| 972 |
+
"should_epoch_stop": false,
|
| 973 |
+
"should_evaluate": false,
|
| 974 |
+
"should_log": false,
|
| 975 |
+
"should_save": true,
|
| 976 |
+
"should_training_stop": false
|
| 977 |
+
},
|
| 978 |
+
"attributes": {}
|
| 979 |
+
}
|
| 980 |
+
},
|
| 981 |
+
"total_flos": 402935426826240.0,
|
| 982 |
+
"train_batch_size": 16,
|
| 983 |
+
"trial_name": null,
|
| 984 |
+
"trial_params": null
|
| 985 |
+
}
|
checkpoint-770/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:752be49abc948927108e2467a489df708fc2c98f0a2eb2cad2df41eff128d5d9
|
| 3 |
+
size 5304
|
checkpoint-770/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "B-Activity",
|
| 13 |
+
"1": "B-Administration",
|
| 14 |
+
"2": "B-Age",
|
| 15 |
+
"3": "B-Area",
|
| 16 |
+
"4": "B-Biological_attribute",
|
| 17 |
+
"5": "B-Biological_structure",
|
| 18 |
+
"6": "B-Clinical_event",
|
| 19 |
+
"7": "B-Color",
|
| 20 |
+
"8": "B-Coreference",
|
| 21 |
+
"9": "B-Date",
|
| 22 |
+
"10": "B-Detailed_description",
|
| 23 |
+
"11": "B-Diagnostic_procedure",
|
| 24 |
+
"12": "B-Disease_disorder",
|
| 25 |
+
"13": "B-Distance",
|
| 26 |
+
"14": "B-Dosage",
|
| 27 |
+
"15": "B-Duration",
|
| 28 |
+
"16": "B-Family_history",
|
| 29 |
+
"17": "B-Frequency",
|
| 30 |
+
"18": "B-Height",
|
| 31 |
+
"19": "B-History",
|
| 32 |
+
"20": "B-Lab_value",
|
| 33 |
+
"21": "B-Mass",
|
| 34 |
+
"22": "B-Medication",
|
| 35 |
+
"23": "B-Nonbiological_location",
|
| 36 |
+
"24": "B-Occupation",
|
| 37 |
+
"25": "B-Other_entity",
|
| 38 |
+
"26": "B-Other_event",
|
| 39 |
+
"27": "B-Outcome",
|
| 40 |
+
"28": "B-Personal_background",
|
| 41 |
+
"29": "B-Qualitative_concept",
|
| 42 |
+
"30": "B-Quantitative_concept",
|
| 43 |
+
"31": "B-Severity",
|
| 44 |
+
"32": "B-Sex",
|
| 45 |
+
"33": "B-Shape",
|
| 46 |
+
"34": "B-Sign_symptom",
|
| 47 |
+
"35": "B-Subject",
|
| 48 |
+
"36": "B-Texture",
|
| 49 |
+
"37": "B-Therapeutic_procedure",
|
| 50 |
+
"38": "B-Time",
|
| 51 |
+
"39": "B-Volume",
|
| 52 |
+
"40": "B-Weight",
|
| 53 |
+
"41": "I-Activity",
|
| 54 |
+
"42": "I-Administration",
|
| 55 |
+
"43": "I-Age",
|
| 56 |
+
"44": "I-Area",
|
| 57 |
+
"45": "I-Biological_structure",
|
| 58 |
+
"46": "I-Clinical_event",
|
| 59 |
+
"47": "I-Coreference",
|
| 60 |
+
"48": "I-Date",
|
| 61 |
+
"49": "I-Detailed_description",
|
| 62 |
+
"50": "I-Diagnostic_procedure",
|
| 63 |
+
"51": "I-Disease_disorder",
|
| 64 |
+
"52": "I-Distance",
|
| 65 |
+
"53": "I-Dosage",
|
| 66 |
+
"54": "I-Duration",
|
| 67 |
+
"55": "I-Family_history",
|
| 68 |
+
"56": "I-History",
|
| 69 |
+
"57": "I-Lab_value",
|
| 70 |
+
"58": "I-Mass",
|
| 71 |
+
"59": "I-Medication",
|
| 72 |
+
"60": "I-Nonbiological_location",
|
| 73 |
+
"61": "I-Other_entity",
|
| 74 |
+
"62": "I-Outcome",
|
| 75 |
+
"63": "I-Personal_background",
|
| 76 |
+
"64": "I-Quantitative_concept",
|
| 77 |
+
"65": "I-Severity",
|
| 78 |
+
"66": "I-Sex",
|
| 79 |
+
"67": "I-Sign_symptom",
|
| 80 |
+
"68": "I-Subject",
|
| 81 |
+
"69": "I-Texture",
|
| 82 |
+
"70": "I-Therapeutic_procedure",
|
| 83 |
+
"71": "I-Time",
|
| 84 |
+
"72": "I-Volume",
|
| 85 |
+
"73": "O"
|
| 86 |
+
},
|
| 87 |
+
"initializer_range": 0.02,
|
| 88 |
+
"label2id": {
|
| 89 |
+
"B-Activity": 0,
|
| 90 |
+
"B-Administration": 1,
|
| 91 |
+
"B-Age": 2,
|
| 92 |
+
"B-Area": 3,
|
| 93 |
+
"B-Biological_attribute": 4,
|
| 94 |
+
"B-Biological_structure": 5,
|
| 95 |
+
"B-Clinical_event": 6,
|
| 96 |
+
"B-Color": 7,
|
| 97 |
+
"B-Coreference": 8,
|
| 98 |
+
"B-Date": 9,
|
| 99 |
+
"B-Detailed_description": 10,
|
| 100 |
+
"B-Diagnostic_procedure": 11,
|
| 101 |
+
"B-Disease_disorder": 12,
|
| 102 |
+
"B-Distance": 13,
|
| 103 |
+
"B-Dosage": 14,
|
| 104 |
+
"B-Duration": 15,
|
| 105 |
+
"B-Family_history": 16,
|
| 106 |
+
"B-Frequency": 17,
|
| 107 |
+
"B-Height": 18,
|
| 108 |
+
"B-History": 19,
|
| 109 |
+
"B-Lab_value": 20,
|
| 110 |
+
"B-Mass": 21,
|
| 111 |
+
"B-Medication": 22,
|
| 112 |
+
"B-Nonbiological_location": 23,
|
| 113 |
+
"B-Occupation": 24,
|
| 114 |
+
"B-Other_entity": 25,
|
| 115 |
+
"B-Other_event": 26,
|
| 116 |
+
"B-Outcome": 27,
|
| 117 |
+
"B-Personal_background": 28,
|
| 118 |
+
"B-Qualitative_concept": 29,
|
| 119 |
+
"B-Quantitative_concept": 30,
|
| 120 |
+
"B-Severity": 31,
|
| 121 |
+
"B-Sex": 32,
|
| 122 |
+
"B-Shape": 33,
|
| 123 |
+
"B-Sign_symptom": 34,
|
| 124 |
+
"B-Subject": 35,
|
| 125 |
+
"B-Texture": 36,
|
| 126 |
+
"B-Therapeutic_procedure": 37,
|
| 127 |
+
"B-Time": 38,
|
| 128 |
+
"B-Volume": 39,
|
| 129 |
+
"B-Weight": 40,
|
| 130 |
+
"I-Activity": 41,
|
| 131 |
+
"I-Administration": 42,
|
| 132 |
+
"I-Age": 43,
|
| 133 |
+
"I-Area": 44,
|
| 134 |
+
"I-Biological_structure": 45,
|
| 135 |
+
"I-Clinical_event": 46,
|
| 136 |
+
"I-Coreference": 47,
|
| 137 |
+
"I-Date": 48,
|
| 138 |
+
"I-Detailed_description": 49,
|
| 139 |
+
"I-Diagnostic_procedure": 50,
|
| 140 |
+
"I-Disease_disorder": 51,
|
| 141 |
+
"I-Distance": 52,
|
| 142 |
+
"I-Dosage": 53,
|
| 143 |
+
"I-Duration": 54,
|
| 144 |
+
"I-Family_history": 55,
|
| 145 |
+
"I-History": 56,
|
| 146 |
+
"I-Lab_value": 57,
|
| 147 |
+
"I-Mass": 58,
|
| 148 |
+
"I-Medication": 59,
|
| 149 |
+
"I-Nonbiological_location": 60,
|
| 150 |
+
"I-Other_entity": 61,
|
| 151 |
+
"I-Outcome": 62,
|
| 152 |
+
"I-Personal_background": 63,
|
| 153 |
+
"I-Quantitative_concept": 64,
|
| 154 |
+
"I-Severity": 65,
|
| 155 |
+
"I-Sex": 66,
|
| 156 |
+
"I-Sign_symptom": 67,
|
| 157 |
+
"I-Subject": 68,
|
| 158 |
+
"I-Texture": 69,
|
| 159 |
+
"I-Therapeutic_procedure": 70,
|
| 160 |
+
"I-Time": 71,
|
| 161 |
+
"I-Volume": 72,
|
| 162 |
+
"O": 73
|
| 163 |
+
},
|
| 164 |
+
"max_position_embeddings": 512,
|
| 165 |
+
"model_type": "distilbert",
|
| 166 |
+
"n_heads": 12,
|
| 167 |
+
"n_layers": 6,
|
| 168 |
+
"pad_token_id": 0,
|
| 169 |
+
"qa_dropout": 0.1,
|
| 170 |
+
"seq_classif_dropout": 0.2,
|
| 171 |
+
"sinusoidal_pos_embds": false,
|
| 172 |
+
"tie_weights_": true,
|
| 173 |
+
"torch_dtype": "float32",
|
| 174 |
+
"transformers_version": "4.49.0",
|
| 175 |
+
"vocab_size": 30522
|
| 176 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:326f38cbbe8b00407d06f53521d4910fcb093e796b288f95c3aef96f06cc66a9
|
| 3 |
+
size 265691496
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:752be49abc948927108e2467a489df708fc2c98f0a2eb2cad2df41eff128d5d9
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|