Hugging Face's logo

hkust-nlp
/
SynCSE-partial-RoBERTa-large

Feature Extraction
Transformers
PyTorch
English
roberta
RoBERTa
Model card Files
xet
Community
2
leoozy commited on
Commit
b204005
·
1 Parent(s): b6bc9bd

init

Browse files
Files changed (12) hide show
  1. config.json +26 -0
  2. eval_results.txt +12 -0
  3. merges.txt +0 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer_config.json +1 -0
  9. train_results.txt +3 -0
  10. trainer_state.json +467 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "result/my-sup-simcse-roberta-large_filtered_final_nli_pos_neg",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.2.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
eval_results.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch = 3.0
2
+ eval_CR = 92.03
3
+ eval_MPQA = 90.02
4
+ eval_MR = 85.79
5
+ eval_MRPC = 75.88
6
+ eval_SST2 = 90.6
7
+ eval_SUBJ = 93.83
8
+ eval_TREC = 78.45
9
+ eval_avg_sts = 0.8592572635193997
10
+ eval_avg_transfer = 86.65714285714286
11
+ eval_sickr_spearman = 0.8466042631732152
12
+ eval_stsb_spearman = 0.8719102638655841
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae3fe96516ed00bf22599553563a6daa3226da88d861de5bf978adf75d664d0
3
+ size 3263697285
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32eb1d605815d67e24686f79cf1a7006ad27d1c346994a11dfd54b0e928f6a4
3
+ size 1631864773
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4f584307c0f1a756d7cd99433942d99175ca67c41442a5649863e39c6ca8c9
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "roberta-large"}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 3580.3029
3
+ train_samples_per_second = 0.431
trainer_state.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8592572635193997,
3
+ "best_model_checkpoint": "result/my-sup-simcse-roberta-large_filtered_final_nli_pos_neg",
4
+ "epoch": 3.0,
5
+ "global_step": 1542,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "eval_avg_sts": 0.38903997598842077,
13
+ "eval_sickr_spearman": 0.3422475345413293,
14
+ "eval_stsb_spearman": 0.4358324174355123,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "eval_avg_sts": 0.7948315851126678,
20
+ "eval_sickr_spearman": 0.7633529637036648,
21
+ "eval_stsb_spearman": 0.8263102065216709,
22
+ "step": 50
23
+ },
24
+ {
25
+ "epoch": 0.15,
26
+ "eval_avg_sts": 0.832614438173249,
27
+ "eval_sickr_spearman": 0.8162565802271669,
28
+ "eval_stsb_spearman": 0.848972296119331,
29
+ "step": 75
30
+ },
31
+ {
32
+ "epoch": 0.19,
33
+ "eval_avg_sts": 0.837867574586473,
34
+ "eval_sickr_spearman": 0.8242750363945497,
35
+ "eval_stsb_spearman": 0.8514601127783963,
36
+ "step": 100
37
+ },
38
+ {
39
+ "epoch": 0.24,
40
+ "eval_avg_sts": 0.8359050915516192,
41
+ "eval_sickr_spearman": 0.8232498125343531,
42
+ "eval_stsb_spearman": 0.8485603705688852,
43
+ "step": 125
44
+ },
45
+ {
46
+ "epoch": 0.29,
47
+ "eval_avg_sts": 0.8396735422853538,
48
+ "eval_sickr_spearman": 0.8239864175060081,
49
+ "eval_stsb_spearman": 0.8553606670646995,
50
+ "step": 150
51
+ },
52
+ {
53
+ "epoch": 0.34,
54
+ "eval_avg_sts": 0.8406033233672054,
55
+ "eval_sickr_spearman": 0.8250130822992476,
56
+ "eval_stsb_spearman": 0.8561935644351634,
57
+ "step": 175
58
+ },
59
+ {
60
+ "epoch": 0.39,
61
+ "eval_avg_sts": 0.8400202980074645,
62
+ "eval_sickr_spearman": 0.8286637822262545,
63
+ "eval_stsb_spearman": 0.8513768137886746,
64
+ "step": 200
65
+ },
66
+ {
67
+ "epoch": 0.44,
68
+ "eval_avg_sts": 0.8503413783622236,
69
+ "eval_sickr_spearman": 0.8387088626877169,
70
+ "eval_stsb_spearman": 0.8619738940367302,
71
+ "step": 225
72
+ },
73
+ {
74
+ "epoch": 0.49,
75
+ "eval_avg_sts": 0.8511101105456758,
76
+ "eval_sickr_spearman": 0.8356727207036109,
77
+ "eval_stsb_spearman": 0.8665475003877408,
78
+ "step": 250
79
+ },
80
+ {
81
+ "epoch": 0.54,
82
+ "eval_avg_sts": 0.8567862839908125,
83
+ "eval_sickr_spearman": 0.8444381565605592,
84
+ "eval_stsb_spearman": 0.8691344114210658,
85
+ "step": 275
86
+ },
87
+ {
88
+ "epoch": 0.58,
89
+ "eval_avg_sts": 0.8538836668779227,
90
+ "eval_sickr_spearman": 0.841704130204499,
91
+ "eval_stsb_spearman": 0.8660632035513465,
92
+ "step": 300
93
+ },
94
+ {
95
+ "epoch": 0.63,
96
+ "eval_avg_sts": 0.8545681159942804,
97
+ "eval_sickr_spearman": 0.8441892593929071,
98
+ "eval_stsb_spearman": 0.8649469725956536,
99
+ "step": 325
100
+ },
101
+ {
102
+ "epoch": 0.68,
103
+ "eval_avg_sts": 0.8511207304405305,
104
+ "eval_sickr_spearman": 0.8412596503917908,
105
+ "eval_stsb_spearman": 0.8609818104892701,
106
+ "step": 350
107
+ },
108
+ {
109
+ "epoch": 0.73,
110
+ "eval_avg_sts": 0.8536184034220342,
111
+ "eval_sickr_spearman": 0.8376980001268504,
112
+ "eval_stsb_spearman": 0.869538806717218,
113
+ "step": 375
114
+ },
115
+ {
116
+ "epoch": 0.78,
117
+ "eval_avg_sts": 0.8525588625627976,
118
+ "eval_sickr_spearman": 0.8385172185929789,
119
+ "eval_stsb_spearman": 0.8666005065326163,
120
+ "step": 400
121
+ },
122
+ {
123
+ "epoch": 0.83,
124
+ "eval_avg_sts": 0.855131044041153,
125
+ "eval_sickr_spearman": 0.845190419671283,
126
+ "eval_stsb_spearman": 0.8650716684110231,
127
+ "step": 425
128
+ },
129
+ {
130
+ "epoch": 0.88,
131
+ "eval_avg_sts": 0.8541681429669479,
132
+ "eval_sickr_spearman": 0.8433326727298597,
133
+ "eval_stsb_spearman": 0.8650036132040362,
134
+ "step": 450
135
+ },
136
+ {
137
+ "epoch": 0.92,
138
+ "eval_avg_sts": 0.8558873351170334,
139
+ "eval_sickr_spearman": 0.8422996678312301,
140
+ "eval_stsb_spearman": 0.8694750024028367,
141
+ "step": 475
142
+ },
143
+ {
144
+ "epoch": 0.97,
145
+ "learning_rate": 6.7574578469520115e-06,
146
+ "loss": 0.6522,
147
+ "step": 500
148
+ },
149
+ {
150
+ "epoch": 0.97,
151
+ "eval_avg_sts": 0.8545521189776211,
152
+ "eval_sickr_spearman": 0.8421153724950121,
153
+ "eval_stsb_spearman": 0.8669888654602301,
154
+ "step": 500
155
+ },
156
+ {
157
+ "epoch": 1.02,
158
+ "eval_avg_sts": 0.8572413202932077,
159
+ "eval_sickr_spearman": 0.8456393663764249,
160
+ "eval_stsb_spearman": 0.8688432742099903,
161
+ "step": 525
162
+ },
163
+ {
164
+ "epoch": 1.07,
165
+ "eval_avg_sts": 0.8530206397139759,
166
+ "eval_sickr_spearman": 0.8416999514986739,
167
+ "eval_stsb_spearman": 0.8643413279292779,
168
+ "step": 550
169
+ },
170
+ {
171
+ "epoch": 1.12,
172
+ "eval_avg_sts": 0.8539449812014897,
173
+ "eval_sickr_spearman": 0.8428747442087487,
174
+ "eval_stsb_spearman": 0.8650152181942306,
175
+ "step": 575
176
+ },
177
+ {
178
+ "epoch": 1.17,
179
+ "eval_avg_sts": 0.8554613984004424,
180
+ "eval_sickr_spearman": 0.8447085236305545,
181
+ "eval_stsb_spearman": 0.8662142731703305,
182
+ "step": 600
183
+ },
184
+ {
185
+ "epoch": 1.22,
186
+ "eval_avg_sts": 0.8558245678668116,
187
+ "eval_sickr_spearman": 0.846121406510458,
188
+ "eval_stsb_spearman": 0.8655277292231652,
189
+ "step": 625
190
+ },
191
+ {
192
+ "epoch": 1.26,
193
+ "eval_avg_sts": 0.8548715982555288,
194
+ "eval_sickr_spearman": 0.8424131172928271,
195
+ "eval_stsb_spearman": 0.8673300792182305,
196
+ "step": 650
197
+ },
198
+ {
199
+ "epoch": 1.31,
200
+ "eval_avg_sts": 0.8578462484095313,
201
+ "eval_sickr_spearman": 0.8463831279821943,
202
+ "eval_stsb_spearman": 0.8693093688368684,
203
+ "step": 675
204
+ },
205
+ {
206
+ "epoch": 1.36,
207
+ "eval_avg_sts": 0.8569757520330985,
208
+ "eval_sickr_spearman": 0.8444606831471337,
209
+ "eval_stsb_spearman": 0.8694908209190633,
210
+ "step": 700
211
+ },
212
+ {
213
+ "epoch": 1.41,
214
+ "eval_avg_sts": 0.8566543148971089,
215
+ "eval_sickr_spearman": 0.8443323440440912,
216
+ "eval_stsb_spearman": 0.8689762857501264,
217
+ "step": 725
218
+ },
219
+ {
220
+ "epoch": 1.46,
221
+ "eval_avg_sts": 0.8559571122998568,
222
+ "eval_sickr_spearman": 0.843302221011548,
223
+ "eval_stsb_spearman": 0.8686120035881657,
224
+ "step": 750
225
+ },
226
+ {
227
+ "epoch": 1.51,
228
+ "eval_avg_sts": 0.8564558623479355,
229
+ "eval_sickr_spearman": 0.8421180142055913,
230
+ "eval_stsb_spearman": 0.8707937104902796,
231
+ "step": 775
232
+ },
233
+ {
234
+ "epoch": 1.56,
235
+ "eval_avg_sts": 0.858434934817754,
236
+ "eval_sickr_spearman": 0.8465295267793775,
237
+ "eval_stsb_spearman": 0.8703403428561304,
238
+ "step": 800
239
+ },
240
+ {
241
+ "epoch": 1.61,
242
+ "eval_avg_sts": 0.8568722246962146,
243
+ "eval_sickr_spearman": 0.8450603514485886,
244
+ "eval_stsb_spearman": 0.8686840979438405,
245
+ "step": 825
246
+ },
247
+ {
248
+ "epoch": 1.65,
249
+ "eval_avg_sts": 0.8549889262613304,
250
+ "eval_sickr_spearman": 0.8409472080769357,
251
+ "eval_stsb_spearman": 0.869030644445725,
252
+ "step": 850
253
+ },
254
+ {
255
+ "epoch": 1.7,
256
+ "eval_avg_sts": 0.8573504810509991,
257
+ "eval_sickr_spearman": 0.8454733228587534,
258
+ "eval_stsb_spearman": 0.8692276392432446,
259
+ "step": 875
260
+ },
261
+ {
262
+ "epoch": 1.75,
263
+ "eval_avg_sts": 0.8559678018004105,
264
+ "eval_sickr_spearman": 0.8426885276284731,
265
+ "eval_stsb_spearman": 0.869247075972348,
266
+ "step": 900
267
+ },
268
+ {
269
+ "epoch": 1.8,
270
+ "eval_avg_sts": 0.8592572635193997,
271
+ "eval_sickr_spearman": 0.8466042631732152,
272
+ "eval_stsb_spearman": 0.8719102638655841,
273
+ "step": 925
274
+ },
275
+ {
276
+ "epoch": 1.85,
277
+ "eval_avg_sts": 0.8565383373902099,
278
+ "eval_sickr_spearman": 0.8425774316908469,
279
+ "eval_stsb_spearman": 0.8704992430895729,
280
+ "step": 950
281
+ },
282
+ {
283
+ "epoch": 1.9,
284
+ "eval_avg_sts": 0.8575761402637414,
285
+ "eval_sickr_spearman": 0.843271529137729,
286
+ "eval_stsb_spearman": 0.8718807513897538,
287
+ "step": 975
288
+ },
289
+ {
290
+ "epoch": 1.95,
291
+ "learning_rate": 3.5149156939040206e-06,
292
+ "loss": 0.2665,
293
+ "step": 1000
294
+ },
295
+ {
296
+ "epoch": 1.95,
297
+ "eval_avg_sts": 0.8545158625377212,
298
+ "eval_sickr_spearman": 0.842564943604473,
299
+ "eval_stsb_spearman": 0.8664667814709694,
300
+ "step": 1000
301
+ },
302
+ {
303
+ "epoch": 1.99,
304
+ "eval_avg_sts": 0.8591698955083712,
305
+ "eval_sickr_spearman": 0.8463661249722851,
306
+ "eval_stsb_spearman": 0.8719736660444573,
307
+ "step": 1025
308
+ },
309
+ {
310
+ "epoch": 2.04,
311
+ "eval_avg_sts": 0.8581627640843799,
312
+ "eval_sickr_spearman": 0.8440300843227411,
313
+ "eval_stsb_spearman": 0.8722954438460186,
314
+ "step": 1050
315
+ },
316
+ {
317
+ "epoch": 2.09,
318
+ "eval_avg_sts": 0.8582253078870739,
319
+ "eval_sickr_spearman": 0.84485866885365,
320
+ "eval_stsb_spearman": 0.8715919469204976,
321
+ "step": 1075
322
+ },
323
+ {
324
+ "epoch": 2.14,
325
+ "eval_avg_sts": 0.8584444810228428,
326
+ "eval_sickr_spearman": 0.8451566057758707,
327
+ "eval_stsb_spearman": 0.8717323562698148,
328
+ "step": 1100
329
+ },
330
+ {
331
+ "epoch": 2.19,
332
+ "eval_avg_sts": 0.8579360448028752,
333
+ "eval_sickr_spearman": 0.845280862235291,
334
+ "eval_stsb_spearman": 0.8705912273704595,
335
+ "step": 1125
336
+ },
337
+ {
338
+ "epoch": 2.24,
339
+ "eval_avg_sts": 0.8587806706442964,
340
+ "eval_sickr_spearman": 0.8453484900261158,
341
+ "eval_stsb_spearman": 0.8722128512624772,
342
+ "step": 1150
343
+ },
344
+ {
345
+ "epoch": 2.29,
346
+ "eval_avg_sts": 0.8587164541843216,
347
+ "eval_sickr_spearman": 0.8441751862801856,
348
+ "eval_stsb_spearman": 0.8732577220884576,
349
+ "step": 1175
350
+ },
351
+ {
352
+ "epoch": 2.33,
353
+ "eval_avg_sts": 0.8553970686859056,
354
+ "eval_sickr_spearman": 0.8400229936230637,
355
+ "eval_stsb_spearman": 0.8707711437487474,
356
+ "step": 1200
357
+ },
358
+ {
359
+ "epoch": 2.38,
360
+ "eval_avg_sts": 0.8582483701862629,
361
+ "eval_sickr_spearman": 0.844513421296513,
362
+ "eval_stsb_spearman": 0.8719833190760128,
363
+ "step": 1225
364
+ },
365
+ {
366
+ "epoch": 2.43,
367
+ "eval_avg_sts": 0.8590849115354441,
368
+ "eval_sickr_spearman": 0.8454768291291586,
369
+ "eval_stsb_spearman": 0.8726929939417296,
370
+ "step": 1250
371
+ },
372
+ {
373
+ "epoch": 2.48,
374
+ "eval_avg_sts": 0.8568280119545071,
375
+ "eval_sickr_spearman": 0.8431880991145311,
376
+ "eval_stsb_spearman": 0.870467924794483,
377
+ "step": 1275
378
+ },
379
+ {
380
+ "epoch": 2.53,
381
+ "eval_avg_sts": 0.8571144935641057,
382
+ "eval_sickr_spearman": 0.8426291131559942,
383
+ "eval_stsb_spearman": 0.8715998739722173,
384
+ "step": 1300
385
+ },
386
+ {
387
+ "epoch": 2.58,
388
+ "eval_avg_sts": 0.8560020316748019,
389
+ "eval_sickr_spearman": 0.8417059073552523,
390
+ "eval_stsb_spearman": 0.8702981559943516,
391
+ "step": 1325
392
+ },
393
+ {
394
+ "epoch": 2.63,
395
+ "eval_avg_sts": 0.8565539872110424,
396
+ "eval_sickr_spearman": 0.8419177245125944,
397
+ "eval_stsb_spearman": 0.8711902499094905,
398
+ "step": 1350
399
+ },
400
+ {
401
+ "epoch": 2.68,
402
+ "eval_avg_sts": 0.8583649723369124,
403
+ "eval_sickr_spearman": 0.8444052552560741,
404
+ "eval_stsb_spearman": 0.8723246894177509,
405
+ "step": 1375
406
+ },
407
+ {
408
+ "epoch": 2.72,
409
+ "eval_avg_sts": 0.8579980787413095,
410
+ "eval_sickr_spearman": 0.8443179827447611,
411
+ "eval_stsb_spearman": 0.871678174737858,
412
+ "step": 1400
413
+ },
414
+ {
415
+ "epoch": 2.77,
416
+ "eval_avg_sts": 0.8568025047431966,
417
+ "eval_sickr_spearman": 0.8429390098224729,
418
+ "eval_stsb_spearman": 0.8706659996639204,
419
+ "step": 1425
420
+ },
421
+ {
422
+ "epoch": 2.82,
423
+ "eval_avg_sts": 0.8568593888645377,
424
+ "eval_sickr_spearman": 0.8429925645005764,
425
+ "eval_stsb_spearman": 0.8707262132284992,
426
+ "step": 1450
427
+ },
428
+ {
429
+ "epoch": 2.87,
430
+ "eval_avg_sts": 0.8568385750256056,
431
+ "eval_sickr_spearman": 0.8429098549439,
432
+ "eval_stsb_spearman": 0.870767295107311,
433
+ "step": 1475
434
+ },
435
+ {
436
+ "epoch": 2.92,
437
+ "learning_rate": 2.7237354085603116e-07,
438
+ "loss": 0.2438,
439
+ "step": 1500
440
+ },
441
+ {
442
+ "epoch": 2.92,
443
+ "eval_avg_sts": 0.8568328584730116,
444
+ "eval_sickr_spearman": 0.8430229681877869,
445
+ "eval_stsb_spearman": 0.8706427487582363,
446
+ "step": 1500
447
+ },
448
+ {
449
+ "epoch": 2.97,
450
+ "eval_avg_sts": 0.8572096542762062,
451
+ "eval_sickr_spearman": 0.8438662022046343,
452
+ "eval_stsb_spearman": 0.8705531063477782,
453
+ "step": 1525
454
+ },
455
+ {
456
+ "epoch": 3.0,
457
+ "step": 1542,
458
+ "train_runtime": 3580.3029,
459
+ "train_samples_per_second": 0.431
460
+ }
461
+ ],
462
+ "max_steps": 1542,
463
+ "num_train_epochs": 3,
464
+ "total_flos": 370635120359073792,
465
+ "trial_name": null,
466
+ "trial_params": null
467
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f382bbd67a9e293c809c1aba183765f62ceb4dfc6e670b0088bd3fcd5338fcdb
3
+ size 2107
vocab.json ADDED
The diff for this file is too large to render. See raw diff