Hugging Face's logo

xshubhamx
/
bert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
xshubhamx commited on
Commit
367ebec
·
verified ·
1 Parent(s): f6f436e

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. training_checkpoints/checkpoint-8359/config.json +61 -0
  2. training_checkpoints/checkpoint-8359/model.safetensors +3 -0
  3. training_checkpoints/checkpoint-8359/optimizer.pt +3 -0
  4. training_checkpoints/checkpoint-8359/rng_state.pth +3 -0
  5. training_checkpoints/checkpoint-8359/scheduler.pt +3 -0
  6. training_checkpoints/checkpoint-8359/trainer_state.json +419 -0
  7. training_checkpoints/checkpoint-8359/training_args.bin +3 -0
training_checkpoints/checkpoint-8359/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-cased",
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": "Issue",
14
+ "1": "Court Discourse",
15
+ "2": "Conclusion",
16
+ "3": "Precedent Analysis",
17
+ "4": "Section Analysis",
18
+ "5": "Argument by Petitioner",
19
+ "6": "Fact",
20
+ "7": "Argument by Respondent",
21
+ "8": "Ratio",
22
+ "9": "Appellant",
23
+ "10": "Respondent",
24
+ "11": "Argument by Appellant",
25
+ "12": "Petitioner",
26
+ "13": "Judge",
27
+ "14": "Argument by Defendant"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "Appellant": 9,
33
+ "Argument by Appellant": 11,
34
+ "Argument by Defendant": 14,
35
+ "Argument by Petitioner": 5,
36
+ "Argument by Respondent": 7,
37
+ "Conclusion": 2,
38
+ "Court Discourse": 1,
39
+ "Fact": 6,
40
+ "Issue": 0,
41
+ "Judge": 13,
42
+ "Petitioner": 12,
43
+ "Precedent Analysis": 3,
44
+ "Ratio": 8,
45
+ "Respondent": 10,
46
+ "Section Analysis": 4
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
55
+ "problem_type": "single_label_classification",
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.38.2",
58
+ "type_vocab_size": 2,
59
+ "use_cache": true,
60
+ "vocab_size": 28996
61
+ }
training_checkpoints/checkpoint-8359/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22f9e6470e0266015c1413a155a2798763564b6575d4a98f893b1cb858b4ea1
3
+ size 433310756
training_checkpoints/checkpoint-8359/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8afb93c9a199f043986d45d4dd98693312d1a0eb7774c00c766d72788f0bc57
3
+ size 866742522
training_checkpoints/checkpoint-8359/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5349429318360fc4c76080b429f51454962940c8a3b89b17fc10b60149448ec
3
+ size 14244
training_checkpoints/checkpoint-8359/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edaa9ebc2d740541b035051b2e78ee69f2c075609d74967d71a8723f4790eac0
3
+ size 1064
training_checkpoints/checkpoint-8359/trainer_state.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7574114430615071,
3
+ "best_model_checkpoint": "bert-base-cased/checkpoint-8359",
4
+ "epoch": 13.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8359,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.78,
13
+ "grad_norm": 7.705796718597412,
14
+ "learning_rate": 4.742353551062727e-05,
15
+ "loss": 1.2487,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7474825716498839,
21
+ "eval_f1_macro": 0.5695048097890428,
22
+ "eval_f1_micro": 0.7474825716498839,
23
+ "eval_f1_weighted": 0.7283975034665731,
24
+ "eval_loss": 0.8270060420036316,
25
+ "eval_macro_fpr": 0.02522988638938423,
26
+ "eval_macro_sensitivity": 0.5800853178643741,
27
+ "eval_macro_specificity": 0.980226637617229,
28
+ "eval_precision": 0.7315332878692975,
29
+ "eval_precision_macro": 0.594776387201485,
30
+ "eval_recall": 0.7474825716498839,
31
+ "eval_recall_macro": 0.5800853178643741,
32
+ "eval_runtime": 42.2559,
33
+ "eval_samples_per_second": 30.552,
34
+ "eval_steps_per_second": 3.834,
35
+ "eval_weighted_fpr": 0.023561723041341427,
36
+ "eval_weighted_sensitivity": 0.7474825716498839,
37
+ "eval_weighted_specificity": 0.9559169926085502,
38
+ "step": 643
39
+ },
40
+ {
41
+ "epoch": 1.56,
42
+ "grad_norm": 13.48304271697998,
43
+ "learning_rate": 4.48315189217211e-05,
44
+ "loss": 0.7012,
45
+ "step": 1000
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.790859798605732,
50
+ "eval_f1_macro": 0.6824316339324086,
51
+ "eval_f1_micro": 0.790859798605732,
52
+ "eval_f1_weighted": 0.7872863568939508,
53
+ "eval_loss": 0.7202674746513367,
54
+ "eval_macro_fpr": 0.01923285837775677,
55
+ "eval_macro_sensitivity": 0.6952615189922304,
56
+ "eval_macro_specificity": 0.9841762605666529,
57
+ "eval_precision": 0.7909625108875821,
58
+ "eval_precision_macro": 0.6785401739993564,
59
+ "eval_recall": 0.790859798605732,
60
+ "eval_recall_macro": 0.6952615189922304,
61
+ "eval_runtime": 52.4321,
62
+ "eval_samples_per_second": 24.622,
63
+ "eval_steps_per_second": 3.09,
64
+ "eval_weighted_fpr": 0.018538862949739082,
65
+ "eval_weighted_sensitivity": 0.790859798605732,
66
+ "eval_weighted_specificity": 0.9717841098940598,
67
+ "step": 1286
68
+ },
69
+ {
70
+ "epoch": 2.33,
71
+ "grad_norm": 11.586973190307617,
72
+ "learning_rate": 4.223950233281493e-05,
73
+ "loss": 0.5493,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_accuracy": 0.790859798605732,
79
+ "eval_f1_macro": 0.6984873137687091,
80
+ "eval_f1_micro": 0.790859798605732,
81
+ "eval_f1_weighted": 0.7838579936235549,
82
+ "eval_loss": 0.8681920766830444,
83
+ "eval_macro_fpr": 0.019233384024661505,
84
+ "eval_macro_sensitivity": 0.7065002388276227,
85
+ "eval_macro_specificity": 0.9841641637298395,
86
+ "eval_precision": 0.7861165362777838,
87
+ "eval_precision_macro": 0.6958085746565035,
88
+ "eval_recall": 0.790859798605732,
89
+ "eval_recall_macro": 0.7065002388276227,
90
+ "eval_runtime": 57.0976,
91
+ "eval_samples_per_second": 22.61,
92
+ "eval_steps_per_second": 2.837,
93
+ "eval_weighted_fpr": 0.018538862949739082,
94
+ "eval_weighted_sensitivity": 0.790859798605732,
95
+ "eval_weighted_specificity": 0.9716026573418609,
96
+ "step": 1929
97
+ },
98
+ {
99
+ "epoch": 3.11,
100
+ "grad_norm": 7.152871131896973,
101
+ "learning_rate": 3.964748574390876e-05,
102
+ "loss": 0.4285,
103
+ "step": 2000
104
+ },
105
+ {
106
+ "epoch": 3.89,
107
+ "grad_norm": 0.3684868812561035,
108
+ "learning_rate": 3.705546915500259e-05,
109
+ "loss": 0.2971,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 4.0,
114
+ "eval_accuracy": 0.8063516653756778,
115
+ "eval_f1_macro": 0.7144632794324105,
116
+ "eval_f1_micro": 0.8063516653756778,
117
+ "eval_f1_weighted": 0.8039470354467723,
118
+ "eval_loss": 0.988532304763794,
119
+ "eval_macro_fpr": 0.017401205821179152,
120
+ "eval_macro_sensitivity": 0.7227416412915404,
121
+ "eval_macro_specificity": 0.985390840274995,
122
+ "eval_precision": 0.8093102425599888,
123
+ "eval_precision_macro": 0.7202648764248779,
124
+ "eval_recall": 0.8063516653756778,
125
+ "eval_recall_macro": 0.7227416412915404,
126
+ "eval_runtime": 51.556,
127
+ "eval_samples_per_second": 25.041,
128
+ "eval_steps_per_second": 3.142,
129
+ "eval_weighted_fpr": 0.01686454398273071,
130
+ "eval_weighted_sensitivity": 0.8063516653756778,
131
+ "eval_weighted_specificity": 0.9745109387492492,
132
+ "step": 2572
133
+ },
134
+ {
135
+ "epoch": 4.67,
136
+ "grad_norm": 25.46174430847168,
137
+ "learning_rate": 3.447382063245205e-05,
138
+ "loss": 0.2142,
139
+ "step": 3000
140
+ },
141
+ {
142
+ "epoch": 5.0,
143
+ "eval_accuracy": 0.8009295120061968,
144
+ "eval_f1_macro": 0.7039859967430886,
145
+ "eval_f1_micro": 0.8009295120061968,
146
+ "eval_f1_weighted": 0.7982451722945229,
147
+ "eval_loss": 1.1663949489593506,
148
+ "eval_macro_fpr": 0.01786597526694271,
149
+ "eval_macro_sensitivity": 0.7128358984575243,
150
+ "eval_macro_specificity": 0.9851267313119202,
151
+ "eval_precision": 0.806175527772202,
152
+ "eval_precision_macro": 0.7229640343443433,
153
+ "eval_recall": 0.8009295120061968,
154
+ "eval_recall_macro": 0.7128358984575243,
155
+ "eval_runtime": 55.3401,
156
+ "eval_samples_per_second": 23.328,
157
+ "eval_steps_per_second": 2.927,
158
+ "eval_weighted_fpr": 0.017443833570895267,
159
+ "eval_weighted_sensitivity": 0.8009295120061968,
160
+ "eval_weighted_specificity": 0.9759714576726065,
161
+ "step": 3215
162
+ },
163
+ {
164
+ "epoch": 5.44,
165
+ "grad_norm": 31.176374435424805,
166
+ "learning_rate": 3.1881804043545884e-05,
167
+ "loss": 0.1312,
168
+ "step": 3500
169
+ },
170
+ {
171
+ "epoch": 6.0,
172
+ "eval_accuracy": 0.7947327652982185,
173
+ "eval_f1_macro": 0.7297269343170936,
174
+ "eval_f1_micro": 0.7947327652982183,
175
+ "eval_f1_weighted": 0.7930510417554495,
176
+ "eval_loss": 1.1734124422073364,
177
+ "eval_macro_fpr": 0.01886228540171014,
178
+ "eval_macro_sensitivity": 0.7344706268344197,
179
+ "eval_macro_specificity": 0.9845199114147345,
180
+ "eval_precision": 0.7993666538613493,
181
+ "eval_precision_macro": 0.7368333308017974,
182
+ "eval_recall": 0.7947327652982185,
183
+ "eval_recall_macro": 0.7344706268344197,
184
+ "eval_runtime": 54.2173,
185
+ "eval_samples_per_second": 23.812,
186
+ "eval_steps_per_second": 2.988,
187
+ "eval_weighted_fpr": 0.018114703670790894,
188
+ "eval_weighted_sensitivity": 0.7947327652982185,
189
+ "eval_weighted_specificity": 0.9730659059227994,
190
+ "step": 3858
191
+ },
192
+ {
193
+ "epoch": 6.22,
194
+ "grad_norm": 0.013805622234940529,
195
+ "learning_rate": 2.928978745463971e-05,
196
+ "loss": 0.1324,
197
+ "step": 4000
198
+ },
199
+ {
200
+ "epoch": 7.0,
201
+ "grad_norm": 45.571006774902344,
202
+ "learning_rate": 2.669777086573354e-05,
203
+ "loss": 0.0773,
204
+ "step": 4500
205
+ },
206
+ {
207
+ "epoch": 7.0,
208
+ "eval_accuracy": 0.8071262587141751,
209
+ "eval_f1_macro": 0.7367422962853,
210
+ "eval_f1_micro": 0.8071262587141751,
211
+ "eval_f1_weighted": 0.8057267562817543,
212
+ "eval_loss": 1.3176283836364746,
213
+ "eval_macro_fpr": 0.01727673667701498,
214
+ "eval_macro_sensitivity": 0.7466882930886096,
215
+ "eval_macro_specificity": 0.9855569982339322,
216
+ "eval_precision": 0.8086166767985209,
217
+ "eval_precision_macro": 0.735311579931955,
218
+ "eval_recall": 0.8071262587141751,
219
+ "eval_recall_macro": 0.7466882930886096,
220
+ "eval_runtime": 51.2493,
221
+ "eval_samples_per_second": 25.191,
222
+ "eval_steps_per_second": 3.161,
223
+ "eval_weighted_fpr": 0.016782368403316036,
224
+ "eval_weighted_sensitivity": 0.8071262587141751,
225
+ "eval_weighted_specificity": 0.9762287147948076,
226
+ "step": 4501
227
+ },
228
+ {
229
+ "epoch": 7.78,
230
+ "grad_norm": 7.123720169067383,
231
+ "learning_rate": 2.4105754276827372e-05,
232
+ "loss": 0.0424,
233
+ "step": 5000
234
+ },
235
+ {
236
+ "epoch": 8.0,
237
+ "eval_accuracy": 0.8001549186676995,
238
+ "eval_f1_macro": 0.7387953449276546,
239
+ "eval_f1_micro": 0.8001549186676995,
240
+ "eval_f1_weighted": 0.7999879862065452,
241
+ "eval_loss": 1.4781354665756226,
242
+ "eval_macro_fpr": 0.018138810278509995,
243
+ "eval_macro_sensitivity": 0.7444111152957017,
244
+ "eval_macro_specificity": 0.9849391860816767,
245
+ "eval_precision": 0.8033964431023632,
246
+ "eval_precision_macro": 0.7389639382645317,
247
+ "eval_recall": 0.8001549186676995,
248
+ "eval_recall_macro": 0.7444111152957017,
249
+ "eval_runtime": 52.4095,
250
+ "eval_samples_per_second": 24.633,
251
+ "eval_steps_per_second": 3.091,
252
+ "eval_weighted_fpr": 0.017527173913043478,
253
+ "eval_weighted_sensitivity": 0.8001549186676995,
254
+ "eval_weighted_specificity": 0.9739328725574503,
255
+ "step": 5144
256
+ },
257
+ {
258
+ "epoch": 8.55,
259
+ "grad_norm": 0.03194281831383705,
260
+ "learning_rate": 2.1513737687921205e-05,
261
+ "loss": 0.0367,
262
+ "step": 5500
263
+ },
264
+ {
265
+ "epoch": 9.0,
266
+ "eval_accuracy": 0.8071262587141751,
267
+ "eval_f1_macro": 0.7423491139003784,
268
+ "eval_f1_micro": 0.8071262587141751,
269
+ "eval_f1_weighted": 0.8088444168870701,
270
+ "eval_loss": 1.5131187438964844,
271
+ "eval_macro_fpr": 0.017300174163348014,
272
+ "eval_macro_sensitivity": 0.7592458434476786,
273
+ "eval_macro_specificity": 0.9855716076783408,
274
+ "eval_precision": 0.8137740774561909,
275
+ "eval_precision_macro": 0.7324878799156955,
276
+ "eval_recall": 0.8071262587141751,
277
+ "eval_recall_macro": 0.7592458434476786,
278
+ "eval_runtime": 52.5744,
279
+ "eval_samples_per_second": 24.556,
280
+ "eval_steps_per_second": 3.081,
281
+ "eval_weighted_fpr": 0.016782368403316036,
282
+ "eval_weighted_sensitivity": 0.8071262587141751,
283
+ "eval_weighted_specificity": 0.9764478564609359,
284
+ "step": 5787
285
+ },
286
+ {
287
+ "epoch": 9.33,
288
+ "grad_norm": 0.0033086766488850117,
289
+ "learning_rate": 1.8921721099015034e-05,
290
+ "loss": 0.0235,
291
+ "step": 6000
292
+ },
293
+ {
294
+ "epoch": 10.0,
295
+ "eval_accuracy": 0.8024786986831913,
296
+ "eval_f1_macro": 0.7501771263545081,
297
+ "eval_f1_micro": 0.8024786986831914,
298
+ "eval_f1_weighted": 0.8005589551120771,
299
+ "eval_loss": 1.563733696937561,
300
+ "eval_macro_fpr": 0.01788920770051085,
301
+ "eval_macro_sensitivity": 0.7473390413575254,
302
+ "eval_macro_specificity": 0.985071506712455,
303
+ "eval_precision": 0.804221400434388,
304
+ "eval_precision_macro": 0.7677688254577842,
305
+ "eval_recall": 0.8024786986831913,
306
+ "eval_recall_macro": 0.7473390413575254,
307
+ "eval_runtime": 52.1434,
308
+ "eval_samples_per_second": 24.759,
309
+ "eval_steps_per_second": 3.107,
310
+ "eval_weighted_fpr": 0.017277593332881633,
311
+ "eval_weighted_sensitivity": 0.8024786986831913,
312
+ "eval_weighted_specificity": 0.9735939020036336,
313
+ "step": 6430
314
+ },
315
+ {
316
+ "epoch": 10.11,
317
+ "grad_norm": 0.004442194476723671,
318
+ "learning_rate": 1.6329704510108863e-05,
319
+ "loss": 0.0159,
320
+ "step": 6500
321
+ },
322
+ {
323
+ "epoch": 10.89,
324
+ "grad_norm": 0.00508864177390933,
325
+ "learning_rate": 1.374287195438051e-05,
326
+ "loss": 0.0116,
327
+ "step": 7000
328
+ },
329
+ {
330
+ "epoch": 11.0,
331
+ "eval_accuracy": 0.8156467854376452,
332
+ "eval_f1_macro": 0.7458125701384197,
333
+ "eval_f1_micro": 0.8156467854376452,
334
+ "eval_f1_weighted": 0.8136907759956319,
335
+ "eval_loss": 1.5827428102493286,
336
+ "eval_macro_fpr": 0.016436155949102384,
337
+ "eval_macro_sensitivity": 0.7546156066563188,
338
+ "eval_macro_specificity": 0.9861588893089583,
339
+ "eval_precision": 0.815210908552928,
340
+ "eval_precision_macro": 0.7473681531953048,
341
+ "eval_recall": 0.8156467854376452,
342
+ "eval_recall_macro": 0.7546156066563188,
343
+ "eval_runtime": 53.3765,
344
+ "eval_samples_per_second": 24.187,
345
+ "eval_steps_per_second": 3.035,
346
+ "eval_weighted_fpr": 0.01588785046728972,
347
+ "eval_weighted_sensitivity": 0.8156467854376452,
348
+ "eval_weighted_specificity": 0.9767365541967312,
349
+ "step": 7073
350
+ },
351
+ {
352
+ "epoch": 11.66,
353
+ "grad_norm": 0.006264629773795605,
354
+ "learning_rate": 1.115085536547434e-05,
355
+ "loss": 0.0083,
356
+ "step": 7500
357
+ },
358
+ {
359
+ "epoch": 12.0,
360
+ "eval_accuracy": 0.8094500387296669,
361
+ "eval_f1_macro": 0.7518816320472604,
362
+ "eval_f1_micro": 0.8094500387296669,
363
+ "eval_f1_weighted": 0.8081824571315688,
364
+ "eval_loss": 1.6470577716827393,
365
+ "eval_macro_fpr": 0.017214485370541883,
366
+ "eval_macro_sensitivity": 0.7537932995402942,
367
+ "eval_macro_specificity": 0.9855882824907416,
368
+ "eval_precision": 0.8087336966769968,
369
+ "eval_precision_macro": 0.7554313668080346,
370
+ "eval_recall": 0.8094500387296669,
371
+ "eval_recall_macro": 0.7537932995402942,
372
+ "eval_runtime": 53.2505,
373
+ "eval_samples_per_second": 24.244,
374
+ "eval_steps_per_second": 3.042,
375
+ "eval_weighted_fpr": 0.016536703414896478,
376
+ "eval_weighted_sensitivity": 0.8094500387296669,
377
+ "eval_weighted_specificity": 0.9743741986314575,
378
+ "step": 7716
379
+ },
380
+ {
381
+ "epoch": 12.44,
382
+ "grad_norm": 0.004450925160199404,
383
+ "learning_rate": 8.55883877656817e-06,
384
+ "loss": 0.0008,
385
+ "step": 8000
386
+ },
387
+ {
388
+ "epoch": 13.0,
389
+ "eval_accuracy": 0.8048024786986832,
390
+ "eval_f1_macro": 0.7574114430615071,
391
+ "eval_f1_micro": 0.804802478698683,
392
+ "eval_f1_weighted": 0.8046079455513543,
393
+ "eval_loss": 1.7113370895385742,
394
+ "eval_macro_fpr": 0.017527856926064553,
395
+ "eval_macro_sensitivity": 0.7513075576443043,
396
+ "eval_macro_specificity": 0.985248816344572,
397
+ "eval_precision": 0.8075689604651297,
398
+ "eval_precision_macro": 0.7753176434036176,
399
+ "eval_recall": 0.8048024786986832,
400
+ "eval_recall_macro": 0.7513075576443043,
401
+ "eval_runtime": 52.4314,
402
+ "eval_samples_per_second": 24.623,
403
+ "eval_steps_per_second": 3.09,
404
+ "eval_weighted_fpr": 0.017029328287606435,
405
+ "eval_weighted_sensitivity": 0.8048024786986832,
406
+ "eval_weighted_specificity": 0.9739297664698968,
407
+ "step": 8359
408
+ }
409
+ ],
410
+ "logging_steps": 500,
411
+ "max_steps": 9645,
412
+ "num_input_tokens_seen": 0,
413
+ "num_train_epochs": 15,
414
+ "save_steps": 500,
415
+ "total_flos": 1.7576291127822336e+16,
416
+ "train_batch_size": 8,
417
+ "trial_name": null,
418
+ "trial_params": null
419
+ }
training_checkpoints/checkpoint-8359/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15be8b8527640eed95000ae3add7b2970781d1e199e7d110cd9f2593b62d1de0
3
+ size 4920