Hugging Face's logo

xshubhamx
/
distilbert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
xshubhamx commited on
Commit
56b7ecf
·
verified ·
1 Parent(s): c05aaa9

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. training_checkpoints/checkpoint-8359/config.json +60 -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 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Issue",
13
+ "1": "Court Discourse",
14
+ "2": "Conclusion",
15
+ "3": "Precedent Analysis",
16
+ "4": "Section Analysis",
17
+ "5": "Argument by Petitioner",
18
+ "6": "Fact",
19
+ "7": "Argument by Respondent",
20
+ "8": "Ratio",
21
+ "9": "Appellant",
22
+ "10": "Respondent",
23
+ "11": "Argument by Appellant",
24
+ "12": "Petitioner",
25
+ "13": "Judge",
26
+ "14": "Argument by Defendant"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "Appellant": 9,
31
+ "Argument by Appellant": 11,
32
+ "Argument by Defendant": 14,
33
+ "Argument by Petitioner": 5,
34
+ "Argument by Respondent": 7,
35
+ "Conclusion": 2,
36
+ "Court Discourse": 1,
37
+ "Fact": 6,
38
+ "Issue": 0,
39
+ "Judge": 13,
40
+ "Petitioner": 12,
41
+ "Precedent Analysis": 3,
42
+ "Ratio": 8,
43
+ "Respondent": 10,
44
+ "Section Analysis": 4
45
+ },
46
+ "max_position_embeddings": 512,
47
+ "model_type": "distilbert",
48
+ "n_heads": 12,
49
+ "n_layers": 6,
50
+ "output_past": true,
51
+ "pad_token_id": 0,
52
+ "problem_type": "single_label_classification",
53
+ "qa_dropout": 0.1,
54
+ "seq_classif_dropout": 0.2,
55
+ "sinusoidal_pos_embds": false,
56
+ "tie_weights_": true,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.38.2",
59
+ "vocab_size": 28996
60
+ }
training_checkpoints/checkpoint-8359/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a5a3b189bbc353873ca52501f75ac64f35f0b8e3d0942275b7d7cecc981433
3
+ size 263184676
training_checkpoints/checkpoint-8359/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210f45c1645360f0d068ff621dc0452ed62a168191e56e1c2486219b1df5162b
3
+ size 526431418
training_checkpoints/checkpoint-8359/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27207a85e32e1048f8c693f6b475fb818acc14ef3ad6f88f2ab76757907d6b82
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:bd3e5f039a193d0b950e759084de683e76a202476b8a64469f0dacd6e01990a6
3
+ size 1064
training_checkpoints/checkpoint-8359/trainer_state.json ADDED
@@ -0,0 +1,419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7690006775426185,
3
+ "best_model_checkpoint": "distilbert-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": 11.34396743774414,
14
+ "learning_rate": 4.742353551062727e-05,
15
+ "loss": 1.3432,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6785437645236251,
21
+ "eval_f1_macro": 0.450865264188339,
22
+ "eval_f1_micro": 0.6785437645236251,
23
+ "eval_f1_weighted": 0.6411446040191482,
24
+ "eval_loss": 1.0504980087280273,
25
+ "eval_macro_fpr": 0.03503375411204489,
26
+ "eval_macro_sensitivity": 0.4705675985497809,
27
+ "eval_macro_specificity": 0.9745833431049495,
28
+ "eval_precision": 0.6415846986654027,
29
+ "eval_precision_macro": 0.46692292210268815,
30
+ "eval_recall": 0.6785437645236251,
31
+ "eval_recall_macro": 0.4705675985497809,
32
+ "eval_runtime": 14.9327,
33
+ "eval_samples_per_second": 86.455,
34
+ "eval_steps_per_second": 10.849,
35
+ "eval_weighted_fpr": 0.03273128795646344,
36
+ "eval_weighted_sensitivity": 0.6785437645236251,
37
+ "eval_weighted_specificity": 0.9402063820506179,
38
+ "step": 643
39
+ },
40
+ {
41
+ "epoch": 1.56,
42
+ "grad_norm": 6.850409507751465,
43
+ "learning_rate": 4.48315189217211e-05,
44
+ "loss": 0.7893,
45
+ "step": 1000
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.7567776917118513,
50
+ "eval_f1_macro": 0.6741297139182881,
51
+ "eval_f1_micro": 0.7567776917118513,
52
+ "eval_f1_weighted": 0.7569882391398047,
53
+ "eval_loss": 0.7760909795761108,
54
+ "eval_macro_fpr": 0.022738386809368866,
55
+ "eval_macro_sensitivity": 0.6863183524030496,
56
+ "eval_macro_specificity": 0.9818535313100053,
57
+ "eval_precision": 0.7644338909103583,
58
+ "eval_precision_macro": 0.6700405827219709,
59
+ "eval_recall": 0.7567776917118513,
60
+ "eval_recall_macro": 0.6863183524030496,
61
+ "eval_runtime": 27.5305,
62
+ "eval_samples_per_second": 46.893,
63
+ "eval_steps_per_second": 5.884,
64
+ "eval_weighted_fpr": 0.022441395082904516,
65
+ "eval_weighted_sensitivity": 0.7567776917118513,
66
+ "eval_weighted_specificity": 0.9710252779382293,
67
+ "step": 1286
68
+ },
69
+ {
70
+ "epoch": 2.33,
71
+ "grad_norm": 17.8884334564209,
72
+ "learning_rate": 4.224468636599274e-05,
73
+ "loss": 0.591,
74
+ "step": 1500
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_accuracy": 0.7970565453137103,
79
+ "eval_f1_macro": 0.6924048714667931,
80
+ "eval_f1_micro": 0.7970565453137104,
81
+ "eval_f1_weighted": 0.7940018258792189,
82
+ "eval_loss": 0.7662103772163391,
83
+ "eval_macro_fpr": 0.018434710239049988,
84
+ "eval_macro_sensitivity": 0.7035968898255173,
85
+ "eval_macro_specificity": 0.9846945661955441,
86
+ "eval_precision": 0.7950229875204451,
87
+ "eval_precision_macro": 0.6922695973120963,
88
+ "eval_recall": 0.7970565453137103,
89
+ "eval_recall_macro": 0.7035968898255173,
90
+ "eval_runtime": 27.5221,
91
+ "eval_samples_per_second": 46.908,
92
+ "eval_steps_per_second": 5.886,
93
+ "eval_weighted_fpr": 0.017862012544314153,
94
+ "eval_weighted_sensitivity": 0.7970565453137103,
95
+ "eval_weighted_specificity": 0.9733619476194485,
96
+ "step": 1929
97
+ },
98
+ {
99
+ "epoch": 3.11,
100
+ "grad_norm": 25.48836326599121,
101
+ "learning_rate": 3.9652669777086575e-05,
102
+ "loss": 0.4558,
103
+ "step": 2000
104
+ },
105
+ {
106
+ "epoch": 3.89,
107
+ "grad_norm": 0.10837343335151672,
108
+ "learning_rate": 3.7060653188180404e-05,
109
+ "loss": 0.3172,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 4.0,
114
+ "eval_accuracy": 0.7846630518977536,
115
+ "eval_f1_macro": 0.6965077266595138,
116
+ "eval_f1_micro": 0.7846630518977536,
117
+ "eval_f1_weighted": 0.7835732492991442,
118
+ "eval_loss": 0.9907627701759338,
119
+ "eval_macro_fpr": 0.019737942615611816,
120
+ "eval_macro_sensitivity": 0.7113690750069883,
121
+ "eval_macro_specificity": 0.9838692887761689,
122
+ "eval_precision": 0.7919798407971179,
123
+ "eval_precision_macro": 0.7001965157119483,
124
+ "eval_recall": 0.7846630518977536,
125
+ "eval_recall_macro": 0.7113690750069883,
126
+ "eval_runtime": 28.3047,
127
+ "eval_samples_per_second": 45.611,
128
+ "eval_steps_per_second": 5.723,
129
+ "eval_weighted_fpr": 0.01922544951590595,
130
+ "eval_weighted_sensitivity": 0.7846630518977536,
131
+ "eval_weighted_specificity": 0.9733762797447779,
132
+ "step": 2572
133
+ },
134
+ {
135
+ "epoch": 4.67,
136
+ "grad_norm": 10.086819648742676,
137
+ "learning_rate": 3.4468636599274234e-05,
138
+ "loss": 0.2327,
139
+ "step": 3000
140
+ },
141
+ {
142
+ "epoch": 5.0,
143
+ "eval_accuracy": 0.8024786986831913,
144
+ "eval_f1_macro": 0.7542217694865249,
145
+ "eval_f1_micro": 0.8024786986831914,
146
+ "eval_f1_weighted": 0.8002731413534041,
147
+ "eval_loss": 1.095934271812439,
148
+ "eval_macro_fpr": 0.01796508612703405,
149
+ "eval_macro_sensitivity": 0.7457798727455296,
150
+ "eval_macro_specificity": 0.9850233185504806,
151
+ "eval_precision": 0.8055080433590336,
152
+ "eval_precision_macro": 0.7796460767552784,
153
+ "eval_recall": 0.8024786986831913,
154
+ "eval_recall_macro": 0.7457798727455296,
155
+ "eval_runtime": 29.0089,
156
+ "eval_samples_per_second": 44.504,
157
+ "eval_steps_per_second": 5.584,
158
+ "eval_weighted_fpr": 0.017277593332881633,
159
+ "eval_weighted_sensitivity": 0.8024786986831913,
160
+ "eval_weighted_specificity": 0.9728710795740201,
161
+ "step": 3215
162
+ },
163
+ {
164
+ "epoch": 5.44,
165
+ "grad_norm": 4.9467058181762695,
166
+ "learning_rate": 3.187662001036807e-05,
167
+ "loss": 0.1287,
168
+ "step": 3500
169
+ },
170
+ {
171
+ "epoch": 6.0,
172
+ "eval_accuracy": 0.7823392718822618,
173
+ "eval_f1_macro": 0.7378296552561081,
174
+ "eval_f1_micro": 0.7823392718822618,
175
+ "eval_f1_weighted": 0.7845278108269366,
176
+ "eval_loss": 1.3398469686508179,
177
+ "eval_macro_fpr": 0.01983152384734813,
178
+ "eval_macro_sensitivity": 0.7445139014359136,
179
+ "eval_macro_specificity": 0.9836785685773387,
180
+ "eval_precision": 0.793856824379177,
181
+ "eval_precision_macro": 0.7422617173301322,
182
+ "eval_recall": 0.7823392718822618,
183
+ "eval_recall_macro": 0.7445139014359136,
184
+ "eval_runtime": 29.0521,
185
+ "eval_samples_per_second": 44.437,
186
+ "eval_steps_per_second": 5.576,
187
+ "eval_weighted_fpr": 0.019485472574717427,
188
+ "eval_weighted_sensitivity": 0.7823392718822618,
189
+ "eval_weighted_specificity": 0.9728392567778187,
190
+ "step": 3858
191
+ },
192
+ {
193
+ "epoch": 6.22,
194
+ "grad_norm": 0.0396418571472168,
195
+ "learning_rate": 2.928978745463971e-05,
196
+ "loss": 0.1333,
197
+ "step": 4000
198
+ },
199
+ {
200
+ "epoch": 7.0,
201
+ "grad_norm": 0.011019147001206875,
202
+ "learning_rate": 2.669777086573354e-05,
203
+ "loss": 0.0781,
204
+ "step": 4500
205
+ },
206
+ {
207
+ "epoch": 7.0,
208
+ "eval_accuracy": 0.8040278853601859,
209
+ "eval_f1_macro": 0.7394948291147995,
210
+ "eval_f1_micro": 0.8040278853601859,
211
+ "eval_f1_weighted": 0.8051803719315618,
212
+ "eval_loss": 1.3660099506378174,
213
+ "eval_macro_fpr": 0.017669244976744804,
214
+ "eval_macro_sensitivity": 0.7357602105706308,
215
+ "eval_macro_specificity": 0.9851033517726757,
216
+ "eval_precision": 0.8089092327899358,
217
+ "eval_precision_macro": 0.749802849233806,
218
+ "eval_recall": 0.8040278853601859,
219
+ "eval_recall_macro": 0.7357602105706308,
220
+ "eval_runtime": 30.0067,
221
+ "eval_samples_per_second": 43.024,
222
+ "eval_steps_per_second": 5.399,
223
+ "eval_weighted_fpr": 0.017111937774771727,
224
+ "eval_weighted_sensitivity": 0.8040278853601859,
225
+ "eval_weighted_specificity": 0.9725223912299508,
226
+ "step": 4501
227
+ },
228
+ {
229
+ "epoch": 7.78,
230
+ "grad_norm": 0.031754400581121445,
231
+ "learning_rate": 2.4105754276827372e-05,
232
+ "loss": 0.0418,
233
+ "step": 5000
234
+ },
235
+ {
236
+ "epoch": 8.0,
237
+ "eval_accuracy": 0.7931835786212239,
238
+ "eval_f1_macro": 0.7522233296415229,
239
+ "eval_f1_micro": 0.793183578621224,
240
+ "eval_f1_weighted": 0.7952770948203518,
241
+ "eval_loss": 1.5433372259140015,
242
+ "eval_macro_fpr": 0.018712733534049456,
243
+ "eval_macro_sensitivity": 0.7475723354015216,
244
+ "eval_macro_specificity": 0.9843591706386842,
245
+ "eval_precision": 0.8034895810487956,
246
+ "eval_precision_macro": 0.7744609413344056,
247
+ "eval_recall": 0.7931835786212239,
248
+ "eval_recall_macro": 0.7475723354015216,
249
+ "eval_runtime": 29.2062,
250
+ "eval_samples_per_second": 44.203,
251
+ "eval_steps_per_second": 5.547,
252
+ "eval_weighted_fpr": 0.018283914264192288,
253
+ "eval_weighted_sensitivity": 0.7931835786212239,
254
+ "eval_weighted_specificity": 0.9722039809590363,
255
+ "step": 5144
256
+ },
257
+ {
258
+ "epoch": 8.55,
259
+ "grad_norm": 2.0860843658447266,
260
+ "learning_rate": 2.1513737687921205e-05,
261
+ "loss": 0.0348,
262
+ "step": 5500
263
+ },
264
+ {
265
+ "epoch": 9.0,
266
+ "eval_accuracy": 0.8001549186676995,
267
+ "eval_f1_macro": 0.7550679362210817,
268
+ "eval_f1_micro": 0.8001549186676995,
269
+ "eval_f1_weighted": 0.8021422606327335,
270
+ "eval_loss": 1.478803038597107,
271
+ "eval_macro_fpr": 0.01792745394097751,
272
+ "eval_macro_sensitivity": 0.7622450878041167,
273
+ "eval_macro_specificity": 0.9850401508146123,
274
+ "eval_precision": 0.8075773619317457,
275
+ "eval_precision_macro": 0.7552173371804851,
276
+ "eval_recall": 0.8001549186676995,
277
+ "eval_recall_macro": 0.7622450878041167,
278
+ "eval_runtime": 33.6781,
279
+ "eval_samples_per_second": 38.334,
280
+ "eval_steps_per_second": 4.81,
281
+ "eval_weighted_fpr": 0.017527173913043478,
282
+ "eval_weighted_sensitivity": 0.8001549186676995,
283
+ "eval_weighted_specificity": 0.9754473435514873,
284
+ "step": 5787
285
+ },
286
+ {
287
+ "epoch": 9.33,
288
+ "grad_norm": 0.006176074966788292,
289
+ "learning_rate": 1.8926905132192844e-05,
290
+ "loss": 0.0151,
291
+ "step": 6000
292
+ },
293
+ {
294
+ "epoch": 10.0,
295
+ "eval_accuracy": 0.8086754453911696,
296
+ "eval_f1_macro": 0.7565651190513751,
297
+ "eval_f1_micro": 0.8086754453911695,
298
+ "eval_f1_weighted": 0.8082906804975573,
299
+ "eval_loss": 1.6027764081954956,
300
+ "eval_macro_fpr": 0.01723038758385257,
301
+ "eval_macro_sensitivity": 0.7454217824689137,
302
+ "eval_macro_specificity": 0.9854499529194798,
303
+ "eval_precision": 0.8124582873246442,
304
+ "eval_precision_macro": 0.7871547386357372,
305
+ "eval_recall": 0.8086754453911696,
306
+ "eval_recall_macro": 0.7454217824689137,
307
+ "eval_runtime": 28.9189,
308
+ "eval_samples_per_second": 44.642,
309
+ "eval_steps_per_second": 5.602,
310
+ "eval_weighted_fpr": 0.016618448496265894,
311
+ "eval_weighted_sensitivity": 0.8086754453911696,
312
+ "eval_weighted_specificity": 0.9730738484010263,
313
+ "step": 6430
314
+ },
315
+ {
316
+ "epoch": 10.11,
317
+ "grad_norm": 0.0032057820353657007,
318
+ "learning_rate": 1.634007257646449e-05,
319
+ "loss": 0.0137,
320
+ "step": 6500
321
+ },
322
+ {
323
+ "epoch": 10.89,
324
+ "grad_norm": 0.004172870423644781,
325
+ "learning_rate": 1.374805598755832e-05,
326
+ "loss": 0.0101,
327
+ "step": 7000
328
+ },
329
+ {
330
+ "epoch": 11.0,
331
+ "eval_accuracy": 0.8055770720371804,
332
+ "eval_f1_macro": 0.7529798915410706,
333
+ "eval_f1_micro": 0.8055770720371804,
334
+ "eval_f1_weighted": 0.8052019144655751,
335
+ "eval_loss": 1.6393871307373047,
336
+ "eval_macro_fpr": 0.017584182450160902,
337
+ "eval_macro_sensitivity": 0.7523477788032975,
338
+ "eval_macro_specificity": 0.9852864553722823,
339
+ "eval_precision": 0.8064957227029571,
340
+ "eval_precision_macro": 0.7595344178185274,
341
+ "eval_recall": 0.8055770720371804,
342
+ "eval_recall_macro": 0.7523477788032975,
343
+ "eval_runtime": 28.6054,
344
+ "eval_samples_per_second": 45.131,
345
+ "eval_steps_per_second": 5.663,
346
+ "eval_weighted_fpr": 0.01694686381743299,
347
+ "eval_weighted_sensitivity": 0.8055770720371804,
348
+ "eval_weighted_specificity": 0.9737197585470556,
349
+ "step": 7073
350
+ },
351
+ {
352
+ "epoch": 11.66,
353
+ "grad_norm": 0.012132075615227222,
354
+ "learning_rate": 1.1156039398652151e-05,
355
+ "loss": 0.0064,
356
+ "step": 7500
357
+ },
358
+ {
359
+ "epoch": 12.0,
360
+ "eval_accuracy": 0.7916343919442292,
361
+ "eval_f1_macro": 0.7426509271146376,
362
+ "eval_f1_micro": 0.7916343919442292,
363
+ "eval_f1_weighted": 0.7922899194778652,
364
+ "eval_loss": 1.766598105430603,
365
+ "eval_macro_fpr": 0.01896907527478527,
366
+ "eval_macro_sensitivity": 0.743861544114717,
367
+ "eval_macro_specificity": 0.9843007114728505,
368
+ "eval_precision": 0.7983913990955233,
369
+ "eval_precision_macro": 0.7482048478402484,
370
+ "eval_recall": 0.7916343919442292,
371
+ "eval_recall_macro": 0.743861544114717,
372
+ "eval_runtime": 27.9684,
373
+ "eval_samples_per_second": 46.159,
374
+ "eval_steps_per_second": 5.792,
375
+ "eval_weighted_fpr": 0.01845372847636688,
376
+ "eval_weighted_sensitivity": 0.7916343919442292,
377
+ "eval_weighted_specificity": 0.9728762801485283,
378
+ "step": 7716
379
+ },
380
+ {
381
+ "epoch": 12.44,
382
+ "grad_norm": 0.004158047493547201,
383
+ "learning_rate": 8.564022809745984e-06,
384
+ "loss": 0.0028,
385
+ "step": 8000
386
+ },
387
+ {
388
+ "epoch": 13.0,
389
+ "eval_accuracy": 0.8040278853601859,
390
+ "eval_f1_macro": 0.7690006775426185,
391
+ "eval_f1_micro": 0.8040278853601859,
392
+ "eval_f1_weighted": 0.804862852197659,
393
+ "eval_loss": 1.7159548997879028,
394
+ "eval_macro_fpr": 0.017698883208519596,
395
+ "eval_macro_sensitivity": 0.7738902178289151,
396
+ "eval_macro_specificity": 0.9851982512101846,
397
+ "eval_precision": 0.807682530726864,
398
+ "eval_precision_macro": 0.7694025144026188,
399
+ "eval_recall": 0.8040278853601859,
400
+ "eval_recall_macro": 0.7738902178289151,
401
+ "eval_runtime": 29.0,
402
+ "eval_samples_per_second": 44.517,
403
+ "eval_steps_per_second": 5.586,
404
+ "eval_weighted_fpr": 0.017111937774771727,
405
+ "eval_weighted_sensitivity": 0.8040278853601859,
406
+ "eval_weighted_specificity": 0.9739458827925839,
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": 8850078721935360.0,
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 sha256:356040a3afb7d54ef3650956d4142f5170f03ec6b31c34023d7e472253b34365
3
+ size 4920