Hugging Face's logo

NASA-AIML
/
MIKA_BERT_FMEA_NER

Token Classification
Transformers
PyTorch
English
bert
NER
Model card Files
xet
 Community
1
sequoiaandrade commited on
Commit
01715dd
·
1 Parent(s): 853cab7

initial model files

Browse files
Files changed (11) hide show
  1. config.json +72 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +1 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +1 -0
  9. trainer_state.json +520 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models\\Pre-trained-BERT\\checkpoint-318766",
3
+ "architectures": [
4
+ "BertForTokenClassification"
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": "O",
14
+ "1": "B-MOD",
15
+ "2": "I-MOD",
16
+ "3": "L-MOD",
17
+ "4": "B-EFF",
18
+ "5": "I-EFF",
19
+ "6": "L-EFF",
20
+ "7": "B-CAU",
21
+ "8": "I-CAU",
22
+ "9": "L-CAU",
23
+ "10": "B-REC",
24
+ "11": "I-REC",
25
+ "12": "L-REC",
26
+ "13": "B-CON",
27
+ "14": "I-CON",
28
+ "15": "L-CON",
29
+ "16": "U-REC",
30
+ "17": "U-CAU",
31
+ "18": "U-EFF",
32
+ "19": "U-MOD",
33
+ "20": "U-CON"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "B-CAU": 7,
39
+ "B-CON": 13,
40
+ "B-EFF": 4,
41
+ "B-MOD": 1,
42
+ "B-REC": 10,
43
+ "I-CAU": 8,
44
+ "I-CON": 14,
45
+ "I-EFF": 5,
46
+ "I-MOD": 2,
47
+ "I-REC": 11,
48
+ "L-CAU": 9,
49
+ "L-CON": 15,
50
+ "L-EFF": 6,
51
+ "L-MOD": 3,
52
+ "L-REC": 12,
53
+ "O": 0,
54
+ "U-CAU": 17,
55
+ "U-CON": 20,
56
+ "U-EFF": 18,
57
+ "U-MOD": 19,
58
+ "U-REC": 16
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.17.0",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30522
72
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652ae36e9735e0b7c7eaca4098b3bdd9ff12db19779261d59c1786f2558c9fd2
3
+ size 871377765
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a479ad591a8a4c98585c1beff76767241e145986de980cfa923971984d675ee7
3
+ size 435715505
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886507d4fdf5c847b1cfc49d321e65d8ec601e2e0dea1d2479c1c0b6b034ec18
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3ad37a2313e3c608eb034eb4dd8bbc7e56902cf84cab813bb20674cdcb76b7
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "truncation": true, "padding": "max_length", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "models\\Pre-trained-BERT\\checkpoint-318766", "tokenizer_class": "BertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,520 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 1424,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.14,
12
+ "learning_rate": 1.9297752808988766e-05,
13
+ "loss": 2.3997,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "eval_accuracy": 0.6560856864654333,
19
+ "eval_f1": 0.2732362821948488,
20
+ "eval_loss": 2.096482753753662,
21
+ "eval_precision": 0.5434298440979956,
22
+ "eval_recall": 0.1824981301421092,
23
+ "eval_runtime": 2.8754,
24
+ "eval_samples_per_second": 123.811,
25
+ "eval_steps_per_second": 30.953,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 0.28,
30
+ "learning_rate": 1.859550561797753e-05,
31
+ "loss": 1.9889,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.28,
36
+ "eval_accuracy": 0.6641674780915288,
37
+ "eval_f1": 0.23144399303321833,
38
+ "eval_loss": 1.841402530670166,
39
+ "eval_precision": 0.35626471686727634,
40
+ "eval_recall": 0.201949860724234,
41
+ "eval_runtime": 3.0688,
42
+ "eval_samples_per_second": 116.007,
43
+ "eval_steps_per_second": 29.002,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.42,
48
+ "learning_rate": 1.7893258426966292e-05,
49
+ "loss": 1.7798,
50
+ "step": 150
51
+ },
52
+ {
53
+ "epoch": 0.42,
54
+ "eval_accuracy": 0.678286270691334,
55
+ "eval_f1": 0.30889901953592575,
56
+ "eval_loss": 1.7000586986541748,
57
+ "eval_precision": 0.46442073397410666,
58
+ "eval_recall": 0.30013927576601673,
59
+ "eval_runtime": 3.0638,
60
+ "eval_samples_per_second": 116.196,
61
+ "eval_steps_per_second": 29.049,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.56,
66
+ "learning_rate": 1.7191011235955056e-05,
67
+ "loss": 1.6758,
68
+ "step": 200
69
+ },
70
+ {
71
+ "epoch": 0.56,
72
+ "eval_accuracy": 0.6851022395326193,
73
+ "eval_f1": 0.4112622913384574,
74
+ "eval_loss": 1.5615102052688599,
75
+ "eval_precision": 0.5168803704334585,
76
+ "eval_recall": 0.46160794941282746,
77
+ "eval_runtime": 3.0543,
78
+ "eval_samples_per_second": 116.558,
79
+ "eval_steps_per_second": 29.139,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 0.7,
84
+ "learning_rate": 1.648876404494382e-05,
85
+ "loss": 1.5373,
86
+ "step": 250
87
+ },
88
+ {
89
+ "epoch": 0.7,
90
+ "eval_accuracy": 0.7037974683544304,
91
+ "eval_f1": 0.4145163524364727,
92
+ "eval_loss": 1.5320079326629639,
93
+ "eval_precision": 0.4973354384146672,
94
+ "eval_recall": 0.4218608852755194,
95
+ "eval_runtime": 3.106,
96
+ "eval_samples_per_second": 114.618,
97
+ "eval_steps_per_second": 28.654,
98
+ "step": 250
99
+ },
100
+ {
101
+ "epoch": 0.84,
102
+ "learning_rate": 1.5786516853932585e-05,
103
+ "loss": 1.5237,
104
+ "step": 300
105
+ },
106
+ {
107
+ "epoch": 0.84,
108
+ "eval_accuracy": 0.6741966893865629,
109
+ "eval_f1": 0.4215682986210665,
110
+ "eval_loss": 1.436463713645935,
111
+ "eval_precision": 0.4890496360861274,
112
+ "eval_recall": 0.5289735099337748,
113
+ "eval_runtime": 3.3008,
114
+ "eval_samples_per_second": 107.852,
115
+ "eval_steps_per_second": 26.963,
116
+ "step": 300
117
+ },
118
+ {
119
+ "epoch": 0.98,
120
+ "learning_rate": 1.508426966292135e-05,
121
+ "loss": 1.4836,
122
+ "step": 350
123
+ },
124
+ {
125
+ "epoch": 0.98,
126
+ "eval_accuracy": 0.7168451801363194,
127
+ "eval_f1": 0.4672566121066839,
128
+ "eval_loss": 1.3614311218261719,
129
+ "eval_precision": 0.48757191926720095,
130
+ "eval_recall": 0.49944812362030905,
131
+ "eval_runtime": 3.0542,
132
+ "eval_samples_per_second": 116.561,
133
+ "eval_steps_per_second": 29.14,
134
+ "step": 350
135
+ },
136
+ {
137
+ "epoch": 1.12,
138
+ "learning_rate": 1.4382022471910113e-05,
139
+ "loss": 1.2214,
140
+ "step": 400
141
+ },
142
+ {
143
+ "epoch": 1.12,
144
+ "eval_accuracy": 0.6756572541382668,
145
+ "eval_f1": 0.46131327709157666,
146
+ "eval_loss": 1.359670877456665,
147
+ "eval_precision": 0.446314989587013,
148
+ "eval_recall": 0.5764348785871964,
149
+ "eval_runtime": 3.229,
150
+ "eval_samples_per_second": 110.251,
151
+ "eval_steps_per_second": 27.563,
152
+ "step": 400
153
+ },
154
+ {
155
+ "epoch": 1.26,
156
+ "learning_rate": 1.3679775280898877e-05,
157
+ "loss": 1.1844,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 1.26,
162
+ "eval_accuracy": 0.6653359298928919,
163
+ "eval_f1": 0.47653942777539116,
164
+ "eval_loss": 1.3439290523529053,
165
+ "eval_precision": 0.4441930828791319,
166
+ "eval_recall": 0.5929911699779249,
167
+ "eval_runtime": 3.2134,
168
+ "eval_samples_per_second": 110.785,
169
+ "eval_steps_per_second": 27.696,
170
+ "step": 450
171
+ },
172
+ {
173
+ "epoch": 1.4,
174
+ "learning_rate": 1.2977528089887642e-05,
175
+ "loss": 1.2122,
176
+ "step": 500
177
+ },
178
+ {
179
+ "epoch": 1.4,
180
+ "eval_accuracy": 0.7283349561830574,
181
+ "eval_f1": 0.49999878403851467,
182
+ "eval_loss": 1.279309630393982,
183
+ "eval_precision": 0.5213615961013602,
184
+ "eval_recall": 0.5292494481236203,
185
+ "eval_runtime": 3.3746,
186
+ "eval_samples_per_second": 105.495,
187
+ "eval_steps_per_second": 26.374,
188
+ "step": 500
189
+ },
190
+ {
191
+ "epoch": 1.54,
192
+ "learning_rate": 1.2275280898876405e-05,
193
+ "loss": 1.1619,
194
+ "step": 550
195
+ },
196
+ {
197
+ "epoch": 1.54,
198
+ "eval_accuracy": 0.7230769230769231,
199
+ "eval_f1": 0.4887836337789245,
200
+ "eval_loss": 1.3024553060531616,
201
+ "eval_precision": 0.5019528496497354,
202
+ "eval_recall": 0.5135209713024282,
203
+ "eval_runtime": 3.4149,
204
+ "eval_samples_per_second": 104.248,
205
+ "eval_steps_per_second": 26.062,
206
+ "step": 550
207
+ },
208
+ {
209
+ "epoch": 1.69,
210
+ "learning_rate": 1.157303370786517e-05,
211
+ "loss": 1.0476,
212
+ "step": 600
213
+ },
214
+ {
215
+ "epoch": 1.69,
216
+ "eval_accuracy": 0.7195715676728335,
217
+ "eval_f1": 0.5047823749536667,
218
+ "eval_loss": 1.2519958019256592,
219
+ "eval_precision": 0.4975374148688318,
220
+ "eval_recall": 0.5524282560706402,
221
+ "eval_runtime": 3.0914,
222
+ "eval_samples_per_second": 115.16,
223
+ "eval_steps_per_second": 28.79,
224
+ "step": 600
225
+ },
226
+ {
227
+ "epoch": 1.83,
228
+ "learning_rate": 1.0870786516853932e-05,
229
+ "loss": 1.1271,
230
+ "step": 650
231
+ },
232
+ {
233
+ "epoch": 1.83,
234
+ "eval_accuracy": 0.7352482960077896,
235
+ "eval_f1": 0.5283455171867876,
236
+ "eval_loss": 1.233576774597168,
237
+ "eval_precision": 0.5226202101961099,
238
+ "eval_recall": 0.5400110375275938,
239
+ "eval_runtime": 2.9844,
240
+ "eval_samples_per_second": 119.289,
241
+ "eval_steps_per_second": 29.822,
242
+ "step": 650
243
+ },
244
+ {
245
+ "epoch": 1.97,
246
+ "learning_rate": 1.0168539325842697e-05,
247
+ "loss": 1.065,
248
+ "step": 700
249
+ },
250
+ {
251
+ "epoch": 1.97,
252
+ "eval_accuracy": 0.7147030185004869,
253
+ "eval_f1": 0.526531014037714,
254
+ "eval_loss": 1.2058743238449097,
255
+ "eval_precision": 0.4963744012861858,
256
+ "eval_recall": 0.5905077262693157,
257
+ "eval_runtime": 2.9747,
258
+ "eval_samples_per_second": 119.675,
259
+ "eval_steps_per_second": 29.919,
260
+ "step": 700
261
+ },
262
+ {
263
+ "epoch": 2.11,
264
+ "learning_rate": 9.466292134831461e-06,
265
+ "loss": 0.9841,
266
+ "step": 750
267
+ },
268
+ {
269
+ "epoch": 2.11,
270
+ "eval_accuracy": 0.7189873417721518,
271
+ "eval_f1": 0.5335199131439152,
272
+ "eval_loss": 1.2104876041412354,
273
+ "eval_precision": 0.497289342239156,
274
+ "eval_recall": 0.6012693156732892,
275
+ "eval_runtime": 2.9664,
276
+ "eval_samples_per_second": 120.012,
277
+ "eval_steps_per_second": 30.003,
278
+ "step": 750
279
+ },
280
+ {
281
+ "epoch": 2.25,
282
+ "learning_rate": 8.764044943820226e-06,
283
+ "loss": 0.8402,
284
+ "step": 800
285
+ },
286
+ {
287
+ "epoch": 2.25,
288
+ "eval_accuracy": 0.7241480038948394,
289
+ "eval_f1": 0.5318695086433913,
290
+ "eval_loss": 1.2313593626022339,
291
+ "eval_precision": 0.49658531359956104,
292
+ "eval_recall": 0.5869205298013245,
293
+ "eval_runtime": 3.0358,
294
+ "eval_samples_per_second": 117.269,
295
+ "eval_steps_per_second": 29.317,
296
+ "step": 800
297
+ },
298
+ {
299
+ "epoch": 2.39,
300
+ "learning_rate": 8.06179775280899e-06,
301
+ "loss": 0.8774,
302
+ "step": 850
303
+ },
304
+ {
305
+ "epoch": 2.39,
306
+ "eval_accuracy": 0.7349561830574489,
307
+ "eval_f1": 0.5437299456127834,
308
+ "eval_loss": 1.232950210571289,
309
+ "eval_precision": 0.5219091313104574,
310
+ "eval_recall": 0.5800220750551877,
311
+ "eval_runtime": 2.9613,
312
+ "eval_samples_per_second": 120.219,
313
+ "eval_steps_per_second": 30.055,
314
+ "step": 850
315
+ },
316
+ {
317
+ "epoch": 2.53,
318
+ "learning_rate": 7.359550561797754e-06,
319
+ "loss": 0.8705,
320
+ "step": 900
321
+ },
322
+ {
323
+ "epoch": 2.53,
324
+ "eval_accuracy": 0.736222005842259,
325
+ "eval_f1": 0.5357813426509713,
326
+ "eval_loss": 1.23160719871521,
327
+ "eval_precision": 0.5233646751377105,
328
+ "eval_recall": 0.5629139072847682,
329
+ "eval_runtime": 2.9653,
330
+ "eval_samples_per_second": 120.057,
331
+ "eval_steps_per_second": 30.014,
332
+ "step": 900
333
+ },
334
+ {
335
+ "epoch": 2.67,
336
+ "learning_rate": 6.6573033707865175e-06,
337
+ "loss": 0.8113,
338
+ "step": 950
339
+ },
340
+ {
341
+ "epoch": 2.67,
342
+ "eval_accuracy": 0.7201557935735151,
343
+ "eval_f1": 0.537801212068117,
344
+ "eval_loss": 1.2007496356964111,
345
+ "eval_precision": 0.4931233755174561,
346
+ "eval_recall": 0.6128587196467992,
347
+ "eval_runtime": 2.9774,
348
+ "eval_samples_per_second": 119.567,
349
+ "eval_steps_per_second": 29.892,
350
+ "step": 950
351
+ },
352
+ {
353
+ "epoch": 2.81,
354
+ "learning_rate": 5.955056179775281e-06,
355
+ "loss": 0.838,
356
+ "step": 1000
357
+ },
358
+ {
359
+ "epoch": 2.81,
360
+ "eval_accuracy": 0.7356377799415774,
361
+ "eval_f1": 0.5536859104767312,
362
+ "eval_loss": 1.2019802331924438,
363
+ "eval_precision": 0.5212984586666464,
364
+ "eval_recall": 0.6026490066225165,
365
+ "eval_runtime": 2.9737,
366
+ "eval_samples_per_second": 119.715,
367
+ "eval_steps_per_second": 29.929,
368
+ "step": 1000
369
+ },
370
+ {
371
+ "epoch": 2.95,
372
+ "learning_rate": 5.252808988764046e-06,
373
+ "loss": 0.8193,
374
+ "step": 1050
375
+ },
376
+ {
377
+ "epoch": 2.95,
378
+ "eval_accuracy": 0.7207400194741966,
379
+ "eval_f1": 0.5384993944708429,
380
+ "eval_loss": 1.1946783065795898,
381
+ "eval_precision": 0.5114682731180041,
382
+ "eval_recall": 0.6004415011037527,
383
+ "eval_runtime": 2.9881,
384
+ "eval_samples_per_second": 119.139,
385
+ "eval_steps_per_second": 29.785,
386
+ "step": 1050
387
+ },
388
+ {
389
+ "epoch": 3.09,
390
+ "learning_rate": 4.550561797752809e-06,
391
+ "loss": 0.7141,
392
+ "step": 1100
393
+ },
394
+ {
395
+ "epoch": 3.09,
396
+ "eval_accuracy": 0.7366114897760467,
397
+ "eval_f1": 0.5502255793929967,
398
+ "eval_loss": 1.2296370267868042,
399
+ "eval_precision": 0.5259775856114555,
400
+ "eval_recall": 0.5963024282560706,
401
+ "eval_runtime": 3.0151,
402
+ "eval_samples_per_second": 118.071,
403
+ "eval_steps_per_second": 29.518,
404
+ "step": 1100
405
+ },
406
+ {
407
+ "epoch": 3.23,
408
+ "learning_rate": 3.848314606741573e-06,
409
+ "loss": 0.6905,
410
+ "step": 1150
411
+ },
412
+ {
413
+ "epoch": 3.23,
414
+ "eval_accuracy": 0.7345666991236611,
415
+ "eval_f1": 0.5571197569439074,
416
+ "eval_loss": 1.2248950004577637,
417
+ "eval_precision": 0.5197886755754393,
418
+ "eval_recall": 0.6109271523178808,
419
+ "eval_runtime": 3.0012,
420
+ "eval_samples_per_second": 118.617,
421
+ "eval_steps_per_second": 29.654,
422
+ "step": 1150
423
+ },
424
+ {
425
+ "epoch": 3.37,
426
+ "learning_rate": 3.146067415730337e-06,
427
+ "loss": 0.6951,
428
+ "step": 1200
429
+ },
430
+ {
431
+ "epoch": 3.37,
432
+ "eval_accuracy": 0.7339824732229796,
433
+ "eval_f1": 0.5589116173956266,
434
+ "eval_loss": 1.229973316192627,
435
+ "eval_precision": 0.5182250638435781,
436
+ "eval_recall": 0.6103752759381899,
437
+ "eval_runtime": 2.9574,
438
+ "eval_samples_per_second": 120.376,
439
+ "eval_steps_per_second": 30.094,
440
+ "step": 1200
441
+ },
442
+ {
443
+ "epoch": 3.51,
444
+ "learning_rate": 2.4438202247191012e-06,
445
+ "loss": 0.6387,
446
+ "step": 1250
447
+ },
448
+ {
449
+ "epoch": 3.51,
450
+ "eval_accuracy": 0.7345666991236611,
451
+ "eval_f1": 0.5571000509958351,
452
+ "eval_loss": 1.2234023809432983,
453
+ "eval_precision": 0.5270142770488044,
454
+ "eval_recall": 0.6084437086092715,
455
+ "eval_runtime": 2.9722,
456
+ "eval_samples_per_second": 119.776,
457
+ "eval_steps_per_second": 29.944,
458
+ "step": 1250
459
+ },
460
+ {
461
+ "epoch": 3.65,
462
+ "learning_rate": 1.7415730337078653e-06,
463
+ "loss": 0.6742,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 3.65,
468
+ "eval_accuracy": 0.7401168451801363,
469
+ "eval_f1": 0.5594133884864436,
470
+ "eval_loss": 1.2352250814437866,
471
+ "eval_precision": 0.5322645232058062,
472
+ "eval_recall": 0.5965783664459161,
473
+ "eval_runtime": 2.9614,
474
+ "eval_samples_per_second": 120.215,
475
+ "eval_steps_per_second": 30.054,
476
+ "step": 1300
477
+ },
478
+ {
479
+ "epoch": 3.79,
480
+ "learning_rate": 1.0393258426966294e-06,
481
+ "loss": 0.6565,
482
+ "step": 1350
483
+ },
484
+ {
485
+ "epoch": 3.79,
486
+ "eval_accuracy": 0.7366114897760467,
487
+ "eval_f1": 0.5585737547750994,
488
+ "eval_loss": 1.2389932870864868,
489
+ "eval_precision": 0.5244359046194068,
490
+ "eval_recall": 0.6026490066225165,
491
+ "eval_runtime": 2.9582,
492
+ "eval_samples_per_second": 120.344,
493
+ "eval_steps_per_second": 30.086,
494
+ "step": 1350
495
+ },
496
+ {
497
+ "epoch": 3.93,
498
+ "learning_rate": 3.3707865168539325e-07,
499
+ "loss": 0.675,
500
+ "step": 1400
501
+ },
502
+ {
503
+ "epoch": 3.93,
504
+ "eval_accuracy": 0.7382667964946446,
505
+ "eval_f1": 0.5614680191047273,
506
+ "eval_loss": 1.2423402070999146,
507
+ "eval_precision": 0.5289138247855666,
508
+ "eval_recall": 0.6056843267108167,
509
+ "eval_runtime": 2.9515,
510
+ "eval_samples_per_second": 120.618,
511
+ "eval_steps_per_second": 30.154,
512
+ "step": 1400
513
+ }
514
+ ],
515
+ "max_steps": 1424,
516
+ "num_train_epochs": 4,
517
+ "total_flos": 133980467748696.0,
518
+ "trial_name": null,
519
+ "trial_params": null
520
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625d52990db3df9613eb5d9bea850c39676787219069782d02fe01d1d938aec2
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff