Hugging Face's logo

cite-text-analysis
/
case-analysis-bert-base-uncased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cite-text-analysis commited on
Commit
1000c6f
•
1 Parent(s): 9a0ab0e

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. training_checkpoints/checkpoint-6272/added_tokens.json +3 -0
  2. training_checkpoints/checkpoint-6272/config.json +39 -0
  3. training_checkpoints/checkpoint-6272/model.safetensors +3 -0
  4. training_checkpoints/checkpoint-6272/optimizer.pt +3 -0
  5. training_checkpoints/checkpoint-6272/rng_state.pth +3 -0
  6. training_checkpoints/checkpoint-6272/scheduler.pt +3 -0
  7. training_checkpoints/checkpoint-6272/special_tokens_map.json +13 -0
  8. training_checkpoints/checkpoint-6272/tokenizer.json +0 -0
  9. training_checkpoints/checkpoint-6272/tokenizer_config.json +63 -0
  10. training_checkpoints/checkpoint-6272/trainer_state.json +721 -0
  11. training_checkpoints/checkpoint-6272/training_args.bin +3 -0
  12. training_checkpoints/checkpoint-6272/vocab.txt +0 -0
training_checkpoints/checkpoint-6272/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 30522
3
+ }
training_checkpoints/checkpoint-6272/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "positive",
14
+ "1": "negative",
15
+ "2": "neutral",
16
+ "3": "rel_by_party"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "negative": 1,
22
+ "neutral": 2,
23
+ "positive": 0,
24
+ "rel_by_party": 3
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 30522,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30523
39
+ }
training_checkpoints/checkpoint-6272/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e255e20b3b0cbd1ea4ff99fcd454e4c96eaecab7a1b5dab6657ca32b45215b
3
+ size 437967872
training_checkpoints/checkpoint-6272/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726118d3155410164ec3646996569a483d15ff7bd6d2e891737d8cc1587ef9a1
3
+ size 876056826
training_checkpoints/checkpoint-6272/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181bbe0859e2b606e9bf9e360a70cbee953d88cd14b993dedbe8e2ff418f6de6
3
+ size 14244
training_checkpoints/checkpoint-6272/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e59c73d33b34696db381608ac87be85d90f011ed00ef77efc2207ce0a949c38
3
+ size 1064
training_checkpoints/checkpoint-6272/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "[UNK]"
13
+ }
training_checkpoints/checkpoint-6272/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-6272/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "30522": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "[CLS]",
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "pad_token": "<pad>",
58
+ "sep_token": "[SEP]",
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "unk_token": "[UNK]"
63
+ }
training_checkpoints/checkpoint-6272/trainer_state.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6528931773500395,
3
+ "best_model_checkpoint": "case-analysis-bert-base-uncased/checkpoint-2912",
4
+ "epoch": 28.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6272,
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_accuracy": 0.7861915367483296,
14
+ "eval_f1_macro": 0.5606209513919795,
15
+ "eval_f1_micro": 0.7861915367483298,
16
+ "eval_f1_weighted": 0.7596863457967054,
17
+ "eval_loss": 0.7283128499984741,
18
+ "eval_macro_fpr": 0.1142150114777894,
19
+ "eval_macro_sensitivity": 0.5571958513134984,
20
+ "eval_macro_specificity": 0.8974437739369907,
21
+ "eval_precision": 0.7487100743874461,
22
+ "eval_precision_macro": 0.584767668299669,
23
+ "eval_recall": 0.7861915367483296,
24
+ "eval_recall_macro": 0.5571958513134984,
25
+ "eval_runtime": 9.7006,
26
+ "eval_samples_per_second": 46.286,
27
+ "eval_steps_per_second": 5.876,
28
+ "eval_weighted_fpr": 0.08311688311688312,
29
+ "eval_weighted_sensitivity": 0.7861915367483296,
30
+ "eval_weighted_specificity": 0.8035835589996332,
31
+ "step": 224
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.799554565701559,
36
+ "eval_f1_macro": 0.5913567856292314,
37
+ "eval_f1_micro": 0.799554565701559,
38
+ "eval_f1_weighted": 0.7794312570974847,
39
+ "eval_loss": 0.816001296043396,
40
+ "eval_macro_fpr": 0.09972743460349152,
41
+ "eval_macro_sensitivity": 0.6065148418089594,
42
+ "eval_macro_specificity": 0.910318444398066,
43
+ "eval_precision": 0.7603126937076594,
44
+ "eval_precision_macro": 0.5769576335614072,
45
+ "eval_recall": 0.799554565701559,
46
+ "eval_recall_macro": 0.6065148418089594,
47
+ "eval_runtime": 39.2963,
48
+ "eval_samples_per_second": 11.426,
49
+ "eval_steps_per_second": 1.451,
50
+ "eval_weighted_fpr": 0.07712082262210797,
51
+ "eval_weighted_sensitivity": 0.799554565701559,
52
+ "eval_weighted_specificity": 0.8417192118907049,
53
+ "step": 448
54
+ },
55
+ {
56
+ "epoch": 2.232142857142857,
57
+ "grad_norm": 10.089143753051758,
58
+ "learning_rate": 4.6302083333333335e-05,
59
+ "loss": 0.6512,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.7906458797327395,
65
+ "eval_f1_macro": 0.5840451851613266,
66
+ "eval_f1_micro": 0.7906458797327395,
67
+ "eval_f1_weighted": 0.771952482046502,
68
+ "eval_loss": 0.8587548136711121,
69
+ "eval_macro_fpr": 0.10045553338392213,
70
+ "eval_macro_sensitivity": 0.5989408048231577,
71
+ "eval_macro_specificity": 0.9104668136432382,
72
+ "eval_precision": 0.7597703984690992,
73
+ "eval_precision_macro": 0.5770004879708264,
74
+ "eval_recall": 0.7906458797327395,
75
+ "eval_recall_macro": 0.5989408048231577,
76
+ "eval_runtime": 36.0068,
77
+ "eval_samples_per_second": 12.47,
78
+ "eval_steps_per_second": 1.583,
79
+ "eval_weighted_fpr": 0.0811044003451251,
80
+ "eval_weighted_sensitivity": 0.7906458797327395,
81
+ "eval_weighted_specificity": 0.8512213748402133,
82
+ "step": 672
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.7817371937639198,
87
+ "eval_f1_macro": 0.6299493260025852,
88
+ "eval_f1_micro": 0.7817371937639198,
89
+ "eval_f1_weighted": 0.7804892003577936,
90
+ "eval_loss": 1.0820659399032593,
91
+ "eval_macro_fpr": 0.09955325556886446,
92
+ "eval_macro_sensitivity": 0.6429130620307091,
93
+ "eval_macro_specificity": 0.9124114631310538,
94
+ "eval_precision": 0.7819490155060428,
95
+ "eval_precision_macro": 0.6213857962213225,
96
+ "eval_recall": 0.7817371937639198,
97
+ "eval_recall_macro": 0.6429130620307091,
98
+ "eval_runtime": 32.7545,
99
+ "eval_samples_per_second": 13.708,
100
+ "eval_steps_per_second": 1.74,
101
+ "eval_weighted_fpr": 0.08514335360556038,
102
+ "eval_weighted_sensitivity": 0.7817371937639198,
103
+ "eval_weighted_specificity": 0.8679086587602954,
104
+ "step": 896
105
+ },
106
+ {
107
+ "epoch": 4.464285714285714,
108
+ "grad_norm": 0.3640059232711792,
109
+ "learning_rate": 4.258184523809524e-05,
110
+ "loss": 0.3466,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 5.0,
115
+ "eval_accuracy": 0.8084632516703786,
116
+ "eval_f1_macro": 0.619470115868435,
117
+ "eval_f1_micro": 0.8084632516703786,
118
+ "eval_f1_weighted": 0.7927603955642376,
119
+ "eval_loss": 1.0612273216247559,
120
+ "eval_macro_fpr": 0.09480480467421379,
121
+ "eval_macro_sensitivity": 0.6262706556824204,
122
+ "eval_macro_specificity": 0.9138770264258179,
123
+ "eval_precision": 0.7999415514782998,
124
+ "eval_precision_macro": 0.7128659611992946,
125
+ "eval_recall": 0.8084632516703786,
126
+ "eval_recall_macro": 0.6262706556824204,
127
+ "eval_runtime": 34.7281,
128
+ "eval_samples_per_second": 12.929,
129
+ "eval_steps_per_second": 1.641,
130
+ "eval_weighted_fpr": 0.07319148936170213,
131
+ "eval_weighted_sensitivity": 0.8084632516703786,
132
+ "eval_weighted_specificity": 0.847044854032893,
133
+ "step": 1120
134
+ },
135
+ {
136
+ "epoch": 6.0,
137
+ "eval_accuracy": 0.7928730512249443,
138
+ "eval_f1_macro": 0.6273476992208005,
139
+ "eval_f1_micro": 0.7928730512249443,
140
+ "eval_f1_weighted": 0.7896519709076985,
141
+ "eval_loss": 1.2559400796890259,
142
+ "eval_macro_fpr": 0.09508832825281638,
143
+ "eval_macro_sensitivity": 0.6361528640940406,
144
+ "eval_macro_specificity": 0.9161350599199577,
145
+ "eval_precision": 0.7876580739535682,
146
+ "eval_precision_macro": 0.6205792331164909,
147
+ "eval_recall": 0.7928730512249443,
148
+ "eval_recall_macro": 0.6361528640940406,
149
+ "eval_runtime": 38.0322,
150
+ "eval_samples_per_second": 11.806,
151
+ "eval_steps_per_second": 1.499,
152
+ "eval_weighted_fpr": 0.08010335917312661,
153
+ "eval_weighted_sensitivity": 0.7928730512249443,
154
+ "eval_weighted_specificity": 0.8716671884548861,
155
+ "step": 1344
156
+ },
157
+ {
158
+ "epoch": 6.696428571428571,
159
+ "grad_norm": 0.05509716644883156,
160
+ "learning_rate": 3.8869047619047625e-05,
161
+ "loss": 0.1715,
162
+ "step": 1500
163
+ },
164
+ {
165
+ "epoch": 7.0,
166
+ "eval_accuracy": 0.7928730512249443,
167
+ "eval_f1_macro": 0.623650691198171,
168
+ "eval_f1_micro": 0.7928730512249443,
169
+ "eval_f1_weighted": 0.7892792124992886,
170
+ "eval_loss": 1.3700848817825317,
171
+ "eval_macro_fpr": 0.09905686727492574,
172
+ "eval_macro_sensitivity": 0.6178801987625516,
173
+ "eval_macro_specificity": 0.9121558558439,
174
+ "eval_precision": 0.7889374292245007,
175
+ "eval_precision_macro": 0.6344745555953697,
176
+ "eval_recall": 0.7928730512249443,
177
+ "eval_recall_macro": 0.6178801987625516,
178
+ "eval_runtime": 38.6276,
179
+ "eval_samples_per_second": 11.624,
180
+ "eval_steps_per_second": 1.476,
181
+ "eval_weighted_fpr": 0.08010335917312661,
182
+ "eval_weighted_sensitivity": 0.7928730512249443,
183
+ "eval_weighted_specificity": 0.8557503721506562,
184
+ "step": 1568
185
+ },
186
+ {
187
+ "epoch": 8.0,
188
+ "eval_accuracy": 0.8106904231625836,
189
+ "eval_f1_macro": 0.6464437798898967,
190
+ "eval_f1_micro": 0.8106904231625834,
191
+ "eval_f1_weighted": 0.8064189899649085,
192
+ "eval_loss": 1.4005118608474731,
193
+ "eval_macro_fpr": 0.0921754708102674,
194
+ "eval_macro_sensitivity": 0.6370398282162988,
195
+ "eval_macro_specificity": 0.9178527413440807,
196
+ "eval_precision": 0.8034816923327339,
197
+ "eval_precision_macro": 0.6578060011883542,
198
+ "eval_recall": 0.8106904231625836,
199
+ "eval_recall_macro": 0.6370398282162988,
200
+ "eval_runtime": 35.6698,
201
+ "eval_samples_per_second": 12.588,
202
+ "eval_steps_per_second": 1.598,
203
+ "eval_weighted_fpr": 0.07221750212404418,
204
+ "eval_weighted_sensitivity": 0.8106904231625836,
205
+ "eval_weighted_specificity": 0.860720542213739,
206
+ "step": 1792
207
+ },
208
+ {
209
+ "epoch": 8.928571428571429,
210
+ "grad_norm": 0.005432427860796452,
211
+ "learning_rate": 3.514880952380952e-05,
212
+ "loss": 0.0636,
213
+ "step": 2000
214
+ },
215
+ {
216
+ "epoch": 9.0,
217
+ "eval_accuracy": 0.8017817371937639,
218
+ "eval_f1_macro": 0.6263115408785538,
219
+ "eval_f1_micro": 0.8017817371937639,
220
+ "eval_f1_weighted": 0.7896240754364972,
221
+ "eval_loss": 1.473650336265564,
222
+ "eval_macro_fpr": 0.10259295399855256,
223
+ "eval_macro_sensitivity": 0.6149052987288282,
224
+ "eval_macro_specificity": 0.9072211454744684,
225
+ "eval_precision": 0.788055851480147,
226
+ "eval_precision_macro": 0.6582800876341822,
227
+ "eval_recall": 0.8017817371937639,
228
+ "eval_recall_macro": 0.6149052987288282,
229
+ "eval_runtime": 34.11,
230
+ "eval_samples_per_second": 13.163,
231
+ "eval_steps_per_second": 1.671,
232
+ "eval_weighted_fpr": 0.07613344739093242,
233
+ "eval_weighted_sensitivity": 0.8017817371937639,
234
+ "eval_weighted_specificity": 0.8271028447041098,
235
+ "step": 2016
236
+ },
237
+ {
238
+ "epoch": 10.0,
239
+ "eval_accuracy": 0.7884187082405345,
240
+ "eval_f1_macro": 0.6331690370327951,
241
+ "eval_f1_micro": 0.7884187082405345,
242
+ "eval_f1_weighted": 0.7909426185077314,
243
+ "eval_loss": 1.7568920850753784,
244
+ "eval_macro_fpr": 0.09595908153187079,
245
+ "eval_macro_sensitivity": 0.6428373560726501,
246
+ "eval_macro_specificity": 0.91584307980206,
247
+ "eval_precision": 0.7961677526311304,
248
+ "eval_precision_macro": 0.6275270485563467,
249
+ "eval_recall": 0.7884187082405345,
250
+ "eval_recall_macro": 0.6428373560726501,
251
+ "eval_runtime": 42.7436,
252
+ "eval_samples_per_second": 10.504,
253
+ "eval_steps_per_second": 1.334,
254
+ "eval_weighted_fpr": 0.08210890233362143,
255
+ "eval_weighted_sensitivity": 0.7884187082405345,
256
+ "eval_weighted_specificity": 0.8749536109677053,
257
+ "step": 2240
258
+ },
259
+ {
260
+ "epoch": 11.0,
261
+ "eval_accuracy": 0.7906458797327395,
262
+ "eval_f1_macro": 0.6101321036639349,
263
+ "eval_f1_micro": 0.7906458797327395,
264
+ "eval_f1_weighted": 0.7845175231806186,
265
+ "eval_loss": 1.7140623331069946,
266
+ "eval_macro_fpr": 0.1035198920558284,
267
+ "eval_macro_sensitivity": 0.6082973730032554,
268
+ "eval_macro_specificity": 0.9082706582818566,
269
+ "eval_precision": 0.7824040660397941,
270
+ "eval_precision_macro": 0.6165716760629552,
271
+ "eval_recall": 0.7906458797327395,
272
+ "eval_recall_macro": 0.6082973730032554,
273
+ "eval_runtime": 37.438,
274
+ "eval_samples_per_second": 11.993,
275
+ "eval_steps_per_second": 1.523,
276
+ "eval_weighted_fpr": 0.0811044003451251,
277
+ "eval_weighted_sensitivity": 0.7906458797327395,
278
+ "eval_weighted_specificity": 0.842436753394687,
279
+ "step": 2464
280
+ },
281
+ {
282
+ "epoch": 11.160714285714286,
283
+ "grad_norm": 0.0017704592319205403,
284
+ "learning_rate": 3.142857142857143e-05,
285
+ "loss": 0.0159,
286
+ "step": 2500
287
+ },
288
+ {
289
+ "epoch": 12.0,
290
+ "eval_accuracy": 0.7951002227171492,
291
+ "eval_f1_macro": 0.6372747490500124,
292
+ "eval_f1_micro": 0.7951002227171492,
293
+ "eval_f1_weighted": 0.7916670590899947,
294
+ "eval_loss": 1.714410662651062,
295
+ "eval_macro_fpr": 0.09685632952239012,
296
+ "eval_macro_sensitivity": 0.6412759206876854,
297
+ "eval_macro_specificity": 0.9140152346037369,
298
+ "eval_precision": 0.7913770752065027,
299
+ "eval_precision_macro": 0.6393393002684569,
300
+ "eval_recall": 0.7951002227171492,
301
+ "eval_recall_macro": 0.6412759206876854,
302
+ "eval_runtime": 34.7517,
303
+ "eval_samples_per_second": 12.92,
304
+ "eval_steps_per_second": 1.64,
305
+ "eval_weighted_fpr": 0.07910576096302666,
306
+ "eval_weighted_sensitivity": 0.7951002227171492,
307
+ "eval_weighted_specificity": 0.8609607156977986,
308
+ "step": 2688
309
+ },
310
+ {
311
+ "epoch": 13.0,
312
+ "eval_accuracy": 0.799554565701559,
313
+ "eval_f1_macro": 0.6528931773500395,
314
+ "eval_f1_micro": 0.799554565701559,
315
+ "eval_f1_weighted": 0.798188843376642,
316
+ "eval_loss": 1.7243342399597168,
317
+ "eval_macro_fpr": 0.09420589017594908,
318
+ "eval_macro_sensitivity": 0.6525655716832187,
319
+ "eval_macro_specificity": 0.9158469519501292,
320
+ "eval_precision": 0.7968817042081011,
321
+ "eval_precision_macro": 0.6534600751896625,
322
+ "eval_recall": 0.799554565701559,
323
+ "eval_recall_macro": 0.6525655716832187,
324
+ "eval_runtime": 35.7184,
325
+ "eval_samples_per_second": 12.571,
326
+ "eval_steps_per_second": 1.596,
327
+ "eval_weighted_fpr": 0.07712082262210797,
328
+ "eval_weighted_sensitivity": 0.799554565701559,
329
+ "eval_weighted_specificity": 0.8638332420989578,
330
+ "step": 2912
331
+ },
332
+ {
333
+ "epoch": 13.392857142857142,
334
+ "grad_norm": 0.0014869036385789514,
335
+ "learning_rate": 2.7708333333333337e-05,
336
+ "loss": 0.0043,
337
+ "step": 3000
338
+ },
339
+ {
340
+ "epoch": 14.0,
341
+ "eval_accuracy": 0.7973273942093542,
342
+ "eval_f1_macro": 0.6334742709127367,
343
+ "eval_f1_micro": 0.7973273942093542,
344
+ "eval_f1_weighted": 0.7911632678226206,
345
+ "eval_loss": 1.8550578355789185,
346
+ "eval_macro_fpr": 0.10413380473626513,
347
+ "eval_macro_sensitivity": 0.6189159939159938,
348
+ "eval_macro_specificity": 0.9071845213512801,
349
+ "eval_precision": 0.7948329741898784,
350
+ "eval_precision_macro": 0.6575689935064936,
351
+ "eval_recall": 0.7973273942093542,
352
+ "eval_recall_macro": 0.6189159939159938,
353
+ "eval_runtime": 37.3063,
354
+ "eval_samples_per_second": 12.035,
355
+ "eval_steps_per_second": 1.528,
356
+ "eval_weighted_fpr": 0.07811158798283262,
357
+ "eval_weighted_sensitivity": 0.7973273942093542,
358
+ "eval_weighted_specificity": 0.8314106911957669,
359
+ "step": 3136
360
+ },
361
+ {
362
+ "epoch": 15.0,
363
+ "eval_accuracy": 0.7928730512249443,
364
+ "eval_f1_macro": 0.6104462132353847,
365
+ "eval_f1_micro": 0.7928730512249443,
366
+ "eval_f1_weighted": 0.7860581271310794,
367
+ "eval_loss": 1.8840636014938354,
368
+ "eval_macro_fpr": 0.10077968846838097,
369
+ "eval_macro_sensitivity": 0.616244778009484,
370
+ "eval_macro_specificity": 0.9109811795750432,
371
+ "eval_precision": 0.7868702804113628,
372
+ "eval_precision_macro": 0.6153843681293956,
373
+ "eval_recall": 0.7928730512249443,
374
+ "eval_recall_macro": 0.616244778009484,
375
+ "eval_runtime": 37.5124,
376
+ "eval_samples_per_second": 11.969,
377
+ "eval_steps_per_second": 1.519,
378
+ "eval_weighted_fpr": 0.08010335917312661,
379
+ "eval_weighted_sensitivity": 0.7928730512249443,
380
+ "eval_weighted_specificity": 0.8510516670752286,
381
+ "step": 3360
382
+ },
383
+ {
384
+ "epoch": 15.625,
385
+ "grad_norm": 0.0012946381466463208,
386
+ "learning_rate": 2.3995535714285717e-05,
387
+ "loss": 0.0029,
388
+ "step": 3500
389
+ },
390
+ {
391
+ "epoch": 16.0,
392
+ "eval_accuracy": 0.755011135857461,
393
+ "eval_f1_macro": 0.6015295009953532,
394
+ "eval_f1_micro": 0.755011135857461,
395
+ "eval_f1_weighted": 0.7660603471590911,
396
+ "eval_loss": 2.0852534770965576,
397
+ "eval_macro_fpr": 0.1100287944234454,
398
+ "eval_macro_sensitivity": 0.6118684574566927,
399
+ "eval_macro_specificity": 0.9061965043355904,
400
+ "eval_precision": 0.7837194577525304,
401
+ "eval_precision_macro": 0.6010349959287868,
402
+ "eval_recall": 0.755011135857461,
403
+ "eval_recall_macro": 0.6118684574566927,
404
+ "eval_runtime": 40.7827,
405
+ "eval_samples_per_second": 11.01,
406
+ "eval_steps_per_second": 1.398,
407
+ "eval_weighted_fpr": 0.09760425909494233,
408
+ "eval_weighted_sensitivity": 0.755011135857461,
409
+ "eval_weighted_specificity": 0.8697748814849007,
410
+ "step": 3584
411
+ },
412
+ {
413
+ "epoch": 17.0,
414
+ "eval_accuracy": 0.7839643652561247,
415
+ "eval_f1_macro": 0.5916565481092323,
416
+ "eval_f1_micro": 0.7839643652561247,
417
+ "eval_f1_weighted": 0.7797414440266076,
418
+ "eval_loss": 1.9721872806549072,
419
+ "eval_macro_fpr": 0.10755611089319247,
420
+ "eval_macro_sensitivity": 0.5838615544497898,
421
+ "eval_macro_specificity": 0.9058507118814452,
422
+ "eval_precision": 0.7783473447757774,
423
+ "eval_precision_macro": 0.6018491347401939,
424
+ "eval_recall": 0.7839643652561247,
425
+ "eval_recall_macro": 0.5838615544497898,
426
+ "eval_runtime": 39.509,
427
+ "eval_samples_per_second": 11.365,
428
+ "eval_steps_per_second": 1.443,
429
+ "eval_weighted_fpr": 0.08412836079791847,
430
+ "eval_weighted_sensitivity": 0.7839643652561247,
431
+ "eval_weighted_specificity": 0.839438482269656,
432
+ "step": 3808
433
+ },
434
+ {
435
+ "epoch": 17.857142857142858,
436
+ "grad_norm": 0.0011545266024768353,
437
+ "learning_rate": 2.027529761904762e-05,
438
+ "loss": 0.0071,
439
+ "step": 4000
440
+ },
441
+ {
442
+ "epoch": 18.0,
443
+ "eval_accuracy": 0.799554565701559,
444
+ "eval_f1_macro": 0.5960313624746896,
445
+ "eval_f1_micro": 0.799554565701559,
446
+ "eval_f1_weighted": 0.7840137565459063,
447
+ "eval_loss": 1.873466968536377,
448
+ "eval_macro_fpr": 0.10533282331246058,
449
+ "eval_macro_sensitivity": 0.5916575475399004,
450
+ "eval_macro_specificity": 0.9047142410835605,
451
+ "eval_precision": 0.7783001729348953,
452
+ "eval_precision_macro": 0.6085738092705436,
453
+ "eval_recall": 0.799554565701559,
454
+ "eval_recall_macro": 0.5916575475399004,
455
+ "eval_runtime": 42.6376,
456
+ "eval_samples_per_second": 10.531,
457
+ "eval_steps_per_second": 1.337,
458
+ "eval_weighted_fpr": 0.07712082262210797,
459
+ "eval_weighted_sensitivity": 0.799554565701559,
460
+ "eval_weighted_specificity": 0.819302398632683,
461
+ "step": 4032
462
+ },
463
+ {
464
+ "epoch": 19.0,
465
+ "eval_accuracy": 0.8017817371937639,
466
+ "eval_f1_macro": 0.6000566425748908,
467
+ "eval_f1_micro": 0.8017817371937639,
468
+ "eval_f1_weighted": 0.7894612476993438,
469
+ "eval_loss": 1.8293864727020264,
470
+ "eval_macro_fpr": 0.10248664637782996,
471
+ "eval_macro_sensitivity": 0.5942573589632414,
472
+ "eval_macro_specificity": 0.9081532391165263,
473
+ "eval_precision": 0.783975414299672,
474
+ "eval_precision_macro": 0.6113679316195262,
475
+ "eval_recall": 0.8017817371937639,
476
+ "eval_recall_macro": 0.5942573589632414,
477
+ "eval_runtime": 39.1005,
478
+ "eval_samples_per_second": 11.483,
479
+ "eval_steps_per_second": 1.458,
480
+ "eval_weighted_fpr": 0.07613344739093242,
481
+ "eval_weighted_sensitivity": 0.8017817371937639,
482
+ "eval_weighted_specificity": 0.8308312192723414,
483
+ "step": 4256
484
+ },
485
+ {
486
+ "epoch": 20.0,
487
+ "eval_accuracy": 0.7973273942093542,
488
+ "eval_f1_macro": 0.6285046967011023,
489
+ "eval_f1_micro": 0.7973273942093542,
490
+ "eval_f1_weighted": 0.7941797156806406,
491
+ "eval_loss": 1.8577601909637451,
492
+ "eval_macro_fpr": 0.09902815238438424,
493
+ "eval_macro_sensitivity": 0.6232260717554835,
494
+ "eval_macro_specificity": 0.9117572211656928,
495
+ "eval_precision": 0.7938657405716162,
496
+ "eval_precision_macro": 0.636714448785387,
497
+ "eval_recall": 0.7973273942093542,
498
+ "eval_recall_macro": 0.6232260717554835,
499
+ "eval_runtime": 44.7659,
500
+ "eval_samples_per_second": 10.03,
501
+ "eval_steps_per_second": 1.273,
502
+ "eval_weighted_fpr": 0.07811158798283262,
503
+ "eval_weighted_sensitivity": 0.7973273942093542,
504
+ "eval_weighted_specificity": 0.8497014904534173,
505
+ "step": 4480
506
+ },
507
+ {
508
+ "epoch": 20.089285714285715,
509
+ "grad_norm": 0.0009593501454219222,
510
+ "learning_rate": 1.6555059523809523e-05,
511
+ "loss": 0.0049,
512
+ "step": 4500
513
+ },
514
+ {
515
+ "epoch": 21.0,
516
+ "eval_accuracy": 0.7973273942093542,
517
+ "eval_f1_macro": 0.6285046967011023,
518
+ "eval_f1_micro": 0.7973273942093542,
519
+ "eval_f1_weighted": 0.7941797156806406,
520
+ "eval_loss": 1.8769508600234985,
521
+ "eval_macro_fpr": 0.09902815238438424,
522
+ "eval_macro_sensitivity": 0.6232260717554835,
523
+ "eval_macro_specificity": 0.9117572211656928,
524
+ "eval_precision": 0.7938657405716162,
525
+ "eval_precision_macro": 0.636714448785387,
526
+ "eval_recall": 0.7973273942093542,
527
+ "eval_recall_macro": 0.6232260717554835,
528
+ "eval_runtime": 38.5375,
529
+ "eval_samples_per_second": 11.651,
530
+ "eval_steps_per_second": 1.479,
531
+ "eval_weighted_fpr": 0.07811158798283262,
532
+ "eval_weighted_sensitivity": 0.7973273942093542,
533
+ "eval_weighted_specificity": 0.8497014904534173,
534
+ "step": 4704
535
+ },
536
+ {
537
+ "epoch": 22.0,
538
+ "eval_accuracy": 0.7951002227171492,
539
+ "eval_f1_macro": 0.615484044892805,
540
+ "eval_f1_micro": 0.7951002227171492,
541
+ "eval_f1_weighted": 0.7900289393227489,
542
+ "eval_loss": 1.8931797742843628,
543
+ "eval_macro_fpr": 0.10072490056374342,
544
+ "eval_macro_sensitivity": 0.6118624353918471,
545
+ "eval_macro_specificity": 0.9103064506905846,
546
+ "eval_precision": 0.7876199411756162,
547
+ "eval_precision_macro": 0.6219132429554252,
548
+ "eval_recall": 0.7951002227171492,
549
+ "eval_recall_macro": 0.6118624353918471,
550
+ "eval_runtime": 42.2273,
551
+ "eval_samples_per_second": 10.633,
552
+ "eval_steps_per_second": 1.35,
553
+ "eval_weighted_fpr": 0.07910576096302666,
554
+ "eval_weighted_sensitivity": 0.7951002227171492,
555
+ "eval_weighted_specificity": 0.8461255800451891,
556
+ "step": 4928
557
+ },
558
+ {
559
+ "epoch": 22.321428571428573,
560
+ "grad_norm": 0.000770406040828675,
561
+ "learning_rate": 1.2842261904761904e-05,
562
+ "loss": 0.0015,
563
+ "step": 5000
564
+ },
565
+ {
566
+ "epoch": 23.0,
567
+ "eval_accuracy": 0.799554565701559,
568
+ "eval_f1_macro": 0.6402524959206902,
569
+ "eval_f1_micro": 0.799554565701559,
570
+ "eval_f1_weighted": 0.797093033815778,
571
+ "eval_loss": 1.9834198951721191,
572
+ "eval_macro_fpr": 0.09600706725776412,
573
+ "eval_macro_sensitivity": 0.6388980653686536,
574
+ "eval_macro_specificity": 0.9148594539351842,
575
+ "eval_precision": 0.7965401894377383,
576
+ "eval_precision_macro": 0.6441145177839441,
577
+ "eval_recall": 0.799554565701559,
578
+ "eval_recall_macro": 0.6388980653686536,
579
+ "eval_runtime": 38.7581,
580
+ "eval_samples_per_second": 11.585,
581
+ "eval_steps_per_second": 1.471,
582
+ "eval_weighted_fpr": 0.07712082262210797,
583
+ "eval_weighted_sensitivity": 0.799554565701559,
584
+ "eval_weighted_specificity": 0.8598832500391776,
585
+ "step": 5152
586
+ },
587
+ {
588
+ "epoch": 24.0,
589
+ "eval_accuracy": 0.8017817371937639,
590
+ "eval_f1_macro": 0.6421670386151904,
591
+ "eval_f1_micro": 0.8017817371937639,
592
+ "eval_f1_weighted": 0.7991460242137992,
593
+ "eval_loss": 1.9925564527511597,
594
+ "eval_macro_fpr": 0.0951739011418371,
595
+ "eval_macro_sensitivity": 0.6398633163339046,
596
+ "eval_macro_specificity": 0.9155121954495444,
597
+ "eval_precision": 0.7983578803325663,
598
+ "eval_precision_macro": 0.6467973044624628,
599
+ "eval_recall": 0.8017817371937639,
600
+ "eval_recall_macro": 0.6398633163339046,
601
+ "eval_runtime": 37.0869,
602
+ "eval_samples_per_second": 12.107,
603
+ "eval_steps_per_second": 1.537,
604
+ "eval_weighted_fpr": 0.07613344739093242,
605
+ "eval_weighted_sensitivity": 0.8017817371937639,
606
+ "eval_weighted_specificity": 0.8602670446044138,
607
+ "step": 5376
608
+ },
609
+ {
610
+ "epoch": 24.553571428571427,
611
+ "grad_norm": 0.0005933350184932351,
612
+ "learning_rate": 9.122023809523809e-06,
613
+ "loss": 0.0001,
614
+ "step": 5500
615
+ },
616
+ {
617
+ "epoch": 25.0,
618
+ "eval_accuracy": 0.7973273942093542,
619
+ "eval_f1_macro": 0.601659870749346,
620
+ "eval_f1_micro": 0.7973273942093542,
621
+ "eval_f1_weighted": 0.787079886540708,
622
+ "eval_loss": 1.9771230220794678,
623
+ "eval_macro_fpr": 0.10112219928997805,
624
+ "eval_macro_sensitivity": 0.6024293009587127,
625
+ "eval_macro_specificity": 0.9098239398206653,
626
+ "eval_precision": 0.7789533167935582,
627
+ "eval_precision_macro": 0.6025054936430702,
628
+ "eval_recall": 0.7973273942093542,
629
+ "eval_recall_macro": 0.6024293009587127,
630
+ "eval_runtime": 38.6498,
631
+ "eval_samples_per_second": 11.617,
632
+ "eval_steps_per_second": 1.475,
633
+ "eval_weighted_fpr": 0.07811158798283262,
634
+ "eval_weighted_sensitivity": 0.7973273942093542,
635
+ "eval_weighted_specificity": 0.8419683650733073,
636
+ "step": 5600
637
+ },
638
+ {
639
+ "epoch": 26.0,
640
+ "eval_accuracy": 0.7951002227171492,
641
+ "eval_f1_macro": 0.5997184485767201,
642
+ "eval_f1_micro": 0.7951002227171492,
643
+ "eval_f1_weighted": 0.7850240116367688,
644
+ "eval_loss": 1.9871045351028442,
645
+ "eval_macro_fpr": 0.10196097209702172,
646
+ "eval_macro_sensitivity": 0.6014640499934618,
647
+ "eval_macro_specificity": 0.9091711983063051,
648
+ "eval_precision": 0.7770084890739485,
649
+ "eval_precision_macro": 0.5996376811594203,
650
+ "eval_recall": 0.7951002227171492,
651
+ "eval_recall_macro": 0.6014640499934618,
652
+ "eval_runtime": 39.5666,
653
+ "eval_samples_per_second": 11.348,
654
+ "eval_steps_per_second": 1.441,
655
+ "eval_weighted_fpr": 0.07910576096302666,
656
+ "eval_weighted_sensitivity": 0.7951002227171492,
657
+ "eval_weighted_specificity": 0.841584570508071,
658
+ "step": 5824
659
+ },
660
+ {
661
+ "epoch": 26.785714285714285,
662
+ "grad_norm": 0.0004862051864620298,
663
+ "learning_rate": 5.4017857142857145e-06,
664
+ "loss": 0.0,
665
+ "step": 6000
666
+ },
667
+ {
668
+ "epoch": 27.0,
669
+ "eval_accuracy": 0.8129175946547884,
670
+ "eval_f1_macro": 0.629270395881315,
671
+ "eval_f1_micro": 0.8129175946547884,
672
+ "eval_f1_weighted": 0.8029206434239315,
673
+ "eval_loss": 1.8755978345870972,
674
+ "eval_macro_fpr": 0.09388410519077747,
675
+ "eval_macro_sensitivity": 0.6200309362074068,
676
+ "eval_macro_specificity": 0.9147857582176063,
677
+ "eval_precision": 0.7961023793797019,
678
+ "eval_precision_macro": 0.6440073655073487,
679
+ "eval_recall": 0.8129175946547884,
680
+ "eval_recall_macro": 0.6200309362074068,
681
+ "eval_runtime": 39.542,
682
+ "eval_samples_per_second": 11.355,
683
+ "eval_steps_per_second": 1.442,
684
+ "eval_weighted_fpr": 0.07124681933842239,
685
+ "eval_weighted_sensitivity": 0.8129175946547884,
686
+ "eval_weighted_specificity": 0.8462254382156368,
687
+ "step": 6048
688
+ },
689
+ {
690
+ "epoch": 28.0,
691
+ "eval_accuracy": 0.8151447661469933,
692
+ "eval_f1_macro": 0.6304510128774757,
693
+ "eval_f1_micro": 0.8151447661469933,
694
+ "eval_f1_weighted": 0.8056373445621643,
695
+ "eval_loss": 1.84725821018219,
696
+ "eval_macro_fpr": 0.0937343238778676,
697
+ "eval_macro_sensitivity": 0.6193616267145678,
698
+ "eval_macro_specificity": 0.9151135915162885,
699
+ "eval_precision": 0.7998448359472876,
700
+ "eval_precision_macro": 0.6463282284507336,
701
+ "eval_recall": 0.8151447661469933,
702
+ "eval_recall_macro": 0.6193616267145678,
703
+ "eval_runtime": 38.7745,
704
+ "eval_samples_per_second": 11.58,
705
+ "eval_steps_per_second": 1.47,
706
+ "eval_weighted_fpr": 0.07027942421676546,
707
+ "eval_weighted_sensitivity": 0.8151447661469933,
708
+ "eval_weighted_specificity": 0.8453095999181606,
709
+ "step": 6272
710
+ }
711
+ ],
712
+ "logging_steps": 500,
713
+ "max_steps": 6720,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 30,
716
+ "save_steps": 500,
717
+ "total_flos": 1.3202097382096896e+16,
718
+ "train_batch_size": 8,
719
+ "trial_name": null,
720
+ "trial_params": null
721
+ }
training_checkpoints/checkpoint-6272/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c832ee10aa932bd0cb27acefa6d68ce6a8c58fec9dd1db56a661139c627803cd
3
+ size 5048
training_checkpoints/checkpoint-6272/vocab.txt ADDED
The diff for this file is too large to render. See raw diff