Hugging Face's logo

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

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
cite-text-analysis commited on
Commit
7e44201
·
verified ·
1 Parent(s): aefde96

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. all_runs/checkpoint-2688/added_tokens.json +3 -0
  2. all_runs/checkpoint-2688/config.json +39 -0
  3. all_runs/checkpoint-2688/model.safetensors +3 -0
  4. all_runs/checkpoint-2688/optimizer.pt +3 -0
  5. all_runs/checkpoint-2688/rng_state.pth +3 -0
  6. all_runs/checkpoint-2688/scheduler.pt +3 -0
  7. all_runs/checkpoint-2688/special_tokens_map.json +13 -0
  8. all_runs/checkpoint-2688/tokenizer.json +0 -0
  9. all_runs/checkpoint-2688/tokenizer_config.json +63 -0
  10. all_runs/checkpoint-2688/trainer_state.json +320 -0
  11. all_runs/checkpoint-2688/training_args.bin +3 -0
  12. all_runs/checkpoint-2688/vocab.txt +0 -0
all_runs/checkpoint-2688/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 30522
3
+ }
all_runs/checkpoint-2688/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
+ }
all_runs/checkpoint-2688/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfdbbe36bfb9015e865107eca53d2f74aa4d8bf52282ab8fe02ff75cdf53ddb
3
+ size 437967872
all_runs/checkpoint-2688/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfbef6ffedff3c8be6291a5acb794f725fa5e94bc00803d748372ea7d6160a8
3
+ size 876056826
all_runs/checkpoint-2688/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010aee1fba1ff2a5ee805b56a54b9b54c5c6c133cd12b6e8fba69cf8694cba98
3
+ size 14244
all_runs/checkpoint-2688/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72209cc9d224ed69d8b5ffad6c0580c0a250e0d0278e9e6a2bf9907e6301e43f
3
+ size 1064
all_runs/checkpoint-2688/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
+ }
all_runs/checkpoint-2688/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
all_runs/checkpoint-2688/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
+ }
all_runs/checkpoint-2688/trainer_state.json ADDED
@@ -0,0 +1,320 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6464437798898967,
3
+ "best_model_checkpoint": "case-analysis-bert-base-uncased/checkpoint-1792",
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2688,
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
+ "logging_steps": 500,
312
+ "max_steps": 6720,
313
+ "num_input_tokens_seen": 0,
314
+ "num_train_epochs": 30,
315
+ "save_steps": 500,
316
+ "total_flos": 5658041735184384.0,
317
+ "train_batch_size": 8,
318
+ "trial_name": null,
319
+ "trial_params": null
320
+ }
all_runs/checkpoint-2688/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c832ee10aa932bd0cb27acefa6d68ce6a8c58fec9dd1db56a661139c627803cd
3
+ size 5048
all_runs/checkpoint-2688/vocab.txt ADDED
The diff for this file is too large to render. See raw diff