Darkester commited on
Commit
8b535c8
·
verified ·
1 Parent(s): 9cc828e

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_size": 64,
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "ebert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.53.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 119547
25
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5dbf40648cadaa64feb3a3dbba2b70c860b5f6e32700b84d100447c6a42cf3
3
+ size 1086295716
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f0ea5645a05c895abfba15fcb7c9be12427630c761e6a6a673057b5d1fbacd
3
+ size 2168019642
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78705d25b8af2d4a44bb6977dce6e9e51ec137a339756172d01664bdf285e878
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd88c1400734381e4f63d3ace0ea9a85534c65976e4e34bd6f4e74b7cb7c880b
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31966e707040467dd52464de7d7775a18228931240c31cac337340f6da7f01d
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 7092,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.021150592216582064,
14
+ "grad_norm": 8.332942008972168,
15
+ "learning_rate": 1.6000000000000003e-05,
16
+ "loss": 11.4949,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.04230118443316413,
21
+ "grad_norm": 6.6360764503479,
22
+ "learning_rate": 3.266666666666667e-05,
23
+ "loss": 9.8459,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.06345177664974619,
28
+ "grad_norm": 8.05850601196289,
29
+ "learning_rate": 4.933333333333334e-05,
30
+ "loss": 8.5587,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.08460236886632826,
35
+ "grad_norm": 8.233019828796387,
36
+ "learning_rate": 4.9654278305963706e-05,
37
+ "loss": 7.976,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.10575296108291032,
42
+ "grad_norm": 7.412795066833496,
43
+ "learning_rate": 4.929415154134255e-05,
44
+ "loss": 7.5136,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.12690355329949238,
49
+ "grad_norm": 8.026376724243164,
50
+ "learning_rate": 4.893402477672141e-05,
51
+ "loss": 7.2849,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.14805414551607446,
56
+ "grad_norm": 13.290921211242676,
57
+ "learning_rate": 4.857389801210026e-05,
58
+ "loss": 7.1981,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.1692047377326565,
63
+ "grad_norm": 9.613779067993164,
64
+ "learning_rate": 4.821377124747912e-05,
65
+ "loss": 6.9762,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.19035532994923857,
70
+ "grad_norm": 10.849081993103027,
71
+ "learning_rate": 4.785364448285797e-05,
72
+ "loss": 6.986,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.21150592216582065,
77
+ "grad_norm": 9.172639846801758,
78
+ "learning_rate": 4.7493517718236826e-05,
79
+ "loss": 6.9641,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.2326565143824027,
84
+ "grad_norm": 13.746626853942871,
85
+ "learning_rate": 4.713339095361568e-05,
86
+ "loss": 6.7526,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 0.25380710659898476,
91
+ "grad_norm": 9.715788841247559,
92
+ "learning_rate": 4.677326418899453e-05,
93
+ "loss": 6.7382,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 0.2749576988155668,
98
+ "grad_norm": 8.96385383605957,
99
+ "learning_rate": 4.641313742437338e-05,
100
+ "loss": 6.6046,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 0.2961082910321489,
105
+ "grad_norm": 7.643514156341553,
106
+ "learning_rate": 4.605301065975223e-05,
107
+ "loss": 6.4929,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 0.31725888324873097,
112
+ "grad_norm": 8.421730041503906,
113
+ "learning_rate": 4.569288389513109e-05,
114
+ "loss": 6.4243,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 0.338409475465313,
119
+ "grad_norm": 21.085466384887695,
120
+ "learning_rate": 4.533275713050994e-05,
121
+ "loss": 6.3454,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 0.3595600676818951,
126
+ "grad_norm": 9.470216751098633,
127
+ "learning_rate": 4.4972630365888796e-05,
128
+ "loss": 6.2785,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 0.38071065989847713,
133
+ "grad_norm": 9.164347648620605,
134
+ "learning_rate": 4.461250360126765e-05,
135
+ "loss": 6.4042,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 0.40186125211505924,
140
+ "grad_norm": 8.708257675170898,
141
+ "learning_rate": 4.4252376836646505e-05,
142
+ "loss": 6.1933,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 0.4230118443316413,
147
+ "grad_norm": 10.921855926513672,
148
+ "learning_rate": 4.3892250072025356e-05,
149
+ "loss": 5.9611,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 0.8883248730964467,
154
+ "grad_norm": 6.086740493774414,
155
+ "learning_rate": 3.677856301531213e-05,
156
+ "loss": 5.9772,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 0.9306260575296108,
161
+ "grad_norm": 5.576613426208496,
162
+ "learning_rate": 3.604240282685513e-05,
163
+ "loss": 5.8948,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 0.9729272419627749,
168
+ "grad_norm": 6.084731578826904,
169
+ "learning_rate": 3.530624263839812e-05,
170
+ "loss": 5.8356,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 1.015228426395939,
175
+ "grad_norm": 6.4574198722839355,
176
+ "learning_rate": 3.457008244994111e-05,
177
+ "loss": 5.8376,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 1.0575296108291032,
182
+ "grad_norm": 6.7739691734313965,
183
+ "learning_rate": 3.38339222614841e-05,
184
+ "loss": 5.7059,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 1.0998307952622675,
189
+ "grad_norm": 6.258169174194336,
190
+ "learning_rate": 3.30977620730271e-05,
191
+ "loss": 5.7126,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 1.1421319796954315,
196
+ "grad_norm": 6.656664848327637,
197
+ "learning_rate": 3.236160188457009e-05,
198
+ "loss": 5.6466,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 1.1844331641285957,
203
+ "grad_norm": 9.155718803405762,
204
+ "learning_rate": 3.162544169611308e-05,
205
+ "loss": 5.5292,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 1.2267343485617597,
210
+ "grad_norm": 6.5999345779418945,
211
+ "learning_rate": 3.088928150765606e-05,
212
+ "loss": 5.4244,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 1.2690355329949239,
217
+ "grad_norm": 7.881080150604248,
218
+ "learning_rate": 3.0153121319199055e-05,
219
+ "loss": 5.4133,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 1.3113367174280879,
224
+ "grad_norm": 6.419029235839844,
225
+ "learning_rate": 2.941696113074205e-05,
226
+ "loss": 5.42,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 1.353637901861252,
231
+ "grad_norm": 7.26897668838501,
232
+ "learning_rate": 2.868080094228504e-05,
233
+ "loss": 5.3998,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 1.3959390862944163,
238
+ "grad_norm": 7.908596515655518,
239
+ "learning_rate": 2.7944640753828033e-05,
240
+ "loss": 5.3602,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 1.4382402707275803,
245
+ "grad_norm": 6.74896240234375,
246
+ "learning_rate": 2.7208480565371023e-05,
247
+ "loss": 5.341,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 1.4805414551607445,
252
+ "grad_norm": 6.694516658782959,
253
+ "learning_rate": 2.6472320376914017e-05,
254
+ "loss": 5.3151,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 1.5228426395939088,
259
+ "grad_norm": 8.561161994934082,
260
+ "learning_rate": 2.5736160188457007e-05,
261
+ "loss": 5.242,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 1.5651438240270727,
266
+ "grad_norm": 6.73771333694458,
267
+ "learning_rate": 2.5e-05,
268
+ "loss": 5.3066,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 1.6074450084602367,
273
+ "grad_norm": 5.139662265777588,
274
+ "learning_rate": 2.4263839811542995e-05,
275
+ "loss": 5.2239,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 1.649746192893401,
280
+ "grad_norm": 9.075642585754395,
281
+ "learning_rate": 2.3527679623085985e-05,
282
+ "loss": 5.2235,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 1.6920473773265652,
287
+ "grad_norm": 7.239570140838623,
288
+ "learning_rate": 2.279151943462898e-05,
289
+ "loss": 5.1589,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 1.7343485617597292,
294
+ "grad_norm": 6.387134552001953,
295
+ "learning_rate": 2.205535924617197e-05,
296
+ "loss": 5.0827,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 1.7766497461928934,
301
+ "grad_norm": 6.9777913093566895,
302
+ "learning_rate": 2.131919905771496e-05,
303
+ "loss": 5.0286,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 1.8189509306260576,
308
+ "grad_norm": 6.586590766906738,
309
+ "learning_rate": 2.058303886925795e-05,
310
+ "loss": 5.0558,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 1.8612521150592216,
315
+ "grad_norm": 8.922995567321777,
316
+ "learning_rate": 1.9846878680800944e-05,
317
+ "loss": 5.0571,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 1.9035532994923858,
322
+ "grad_norm": 15.648545265197754,
323
+ "learning_rate": 1.9110718492343934e-05,
324
+ "loss": 5.0074,
325
+ "step": 4500
326
+ },
327
+ {
328
+ "epoch": 1.94585448392555,
329
+ "grad_norm": 9.67465877532959,
330
+ "learning_rate": 1.8374558303886928e-05,
331
+ "loss": 4.9584,
332
+ "step": 4600
333
+ },
334
+ {
335
+ "epoch": 1.988155668358714,
336
+ "grad_norm": 8.49885082244873,
337
+ "learning_rate": 1.7638398115429918e-05,
338
+ "loss": 4.9303,
339
+ "step": 4700
340
+ },
341
+ {
342
+ "epoch": 2.030456852791878,
343
+ "grad_norm": 7.5250396728515625,
344
+ "learning_rate": 1.690223792697291e-05,
345
+ "loss": 4.8864,
346
+ "step": 4800
347
+ },
348
+ {
349
+ "epoch": 2.0727580372250425,
350
+ "grad_norm": 6.662505626678467,
351
+ "learning_rate": 1.6166077738515902e-05,
352
+ "loss": 4.8241,
353
+ "step": 4900
354
+ },
355
+ {
356
+ "epoch": 2.1150592216582065,
357
+ "grad_norm": 13.685736656188965,
358
+ "learning_rate": 1.5429917550058892e-05,
359
+ "loss": 4.8014,
360
+ "step": 5000
361
+ },
362
+ {
363
+ "epoch": 2.1573604060913705,
364
+ "grad_norm": 6.445871353149414,
365
+ "learning_rate": 1.4693757361601884e-05,
366
+ "loss": 4.8768,
367
+ "step": 5100
368
+ },
369
+ {
370
+ "epoch": 2.199661590524535,
371
+ "grad_norm": 6.524866580963135,
372
+ "learning_rate": 1.3957597173144876e-05,
373
+ "loss": 4.8566,
374
+ "step": 5200
375
+ },
376
+ {
377
+ "epoch": 2.241962774957699,
378
+ "grad_norm": 8.739165306091309,
379
+ "learning_rate": 1.3221436984687868e-05,
380
+ "loss": 4.7029,
381
+ "step": 5300
382
+ },
383
+ {
384
+ "epoch": 2.284263959390863,
385
+ "grad_norm": 10.373656272888184,
386
+ "learning_rate": 1.248527679623086e-05,
387
+ "loss": 4.7585,
388
+ "step": 5400
389
+ },
390
+ {
391
+ "epoch": 2.326565143824027,
392
+ "grad_norm": 9.050317764282227,
393
+ "learning_rate": 1.1749116607773852e-05,
394
+ "loss": 4.7496,
395
+ "step": 5500
396
+ },
397
+ {
398
+ "epoch": 2.3688663282571913,
399
+ "grad_norm": 7.840747356414795,
400
+ "learning_rate": 1.1012956419316844e-05,
401
+ "loss": 4.7871,
402
+ "step": 5600
403
+ },
404
+ {
405
+ "epoch": 2.4111675126903553,
406
+ "grad_norm": 7.422430515289307,
407
+ "learning_rate": 1.0276796230859835e-05,
408
+ "loss": 4.7949,
409
+ "step": 5700
410
+ },
411
+ {
412
+ "epoch": 2.4534686971235193,
413
+ "grad_norm": 6.53894567489624,
414
+ "learning_rate": 9.540636042402827e-06,
415
+ "loss": 4.7628,
416
+ "step": 5800
417
+ },
418
+ {
419
+ "epoch": 2.495769881556684,
420
+ "grad_norm": 10.329708099365234,
421
+ "learning_rate": 8.804475853945819e-06,
422
+ "loss": 4.6616,
423
+ "step": 5900
424
+ },
425
+ {
426
+ "epoch": 2.5380710659898478,
427
+ "grad_norm": 8.34196949005127,
428
+ "learning_rate": 8.06831566548881e-06,
429
+ "loss": 4.8091,
430
+ "step": 6000
431
+ },
432
+ {
433
+ "epoch": 2.5803722504230118,
434
+ "grad_norm": 6.8171706199646,
435
+ "learning_rate": 7.332155477031802e-06,
436
+ "loss": 4.6833,
437
+ "step": 6100
438
+ },
439
+ {
440
+ "epoch": 2.6226734348561758,
441
+ "grad_norm": 6.502234935760498,
442
+ "learning_rate": 6.595995288574794e-06,
443
+ "loss": 4.579,
444
+ "step": 6200
445
+ },
446
+ {
447
+ "epoch": 2.66497461928934,
448
+ "grad_norm": 9.155757904052734,
449
+ "learning_rate": 5.859835100117786e-06,
450
+ "loss": 4.6477,
451
+ "step": 6300
452
+ },
453
+ {
454
+ "epoch": 2.707275803722504,
455
+ "grad_norm": 6.970887660980225,
456
+ "learning_rate": 5.123674911660778e-06,
457
+ "loss": 4.6742,
458
+ "step": 6400
459
+ },
460
+ {
461
+ "epoch": 2.749576988155668,
462
+ "grad_norm": 11.221705436706543,
463
+ "learning_rate": 4.387514723203769e-06,
464
+ "loss": 4.6385,
465
+ "step": 6500
466
+ },
467
+ {
468
+ "epoch": 2.7918781725888326,
469
+ "grad_norm": 10.325379371643066,
470
+ "learning_rate": 3.6513545347467615e-06,
471
+ "loss": 4.7299,
472
+ "step": 6600
473
+ },
474
+ {
475
+ "epoch": 2.8341793570219966,
476
+ "grad_norm": 6.159130573272705,
477
+ "learning_rate": 2.9151943462897527e-06,
478
+ "loss": 4.6718,
479
+ "step": 6700
480
+ },
481
+ {
482
+ "epoch": 2.8764805414551606,
483
+ "grad_norm": 7.569215774536133,
484
+ "learning_rate": 2.1790341578327443e-06,
485
+ "loss": 4.6594,
486
+ "step": 6800
487
+ },
488
+ {
489
+ "epoch": 2.9187817258883246,
490
+ "grad_norm": 7.764076232910156,
491
+ "learning_rate": 1.4428739693757363e-06,
492
+ "loss": 4.6538,
493
+ "step": 6900
494
+ },
495
+ {
496
+ "epoch": 2.961082910321489,
497
+ "grad_norm": 7.675158977508545,
498
+ "learning_rate": 7.067137809187279e-07,
499
+ "loss": 4.6145,
500
+ "step": 7000
501
+ }
502
+ ],
503
+ "logging_steps": 100,
504
+ "max_steps": 7092,
505
+ "num_input_tokens_seen": 0,
506
+ "num_train_epochs": 3,
507
+ "save_steps": 500,
508
+ "stateful_callbacks": {
509
+ "TrainerControl": {
510
+ "args": {
511
+ "should_epoch_stop": false,
512
+ "should_evaluate": false,
513
+ "should_log": false,
514
+ "should_save": true,
515
+ "should_training_stop": true
516
+ },
517
+ "attributes": {}
518
+ }
519
+ },
520
+ "total_flos": 9190341574201800.0,
521
+ "train_batch_size": 16,
522
+ "trial_name": null,
523
+ "trial_params": null
524
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267e2a546da9861afed3435f03ad75bfb33b1ba2a97a6238560a077b213f15e4
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff