ssktora commited on
Commit
4b109fe
·
verified ·
1 Parent(s): bf8fe63

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/e5-base-v2",
3
+ "architectures": [
4
+ "BertModel"
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4053d9d9196685ed2870cd51e87b7d2ad5a072fe22c77f103b0ba7f8df591fe
3
+ size 871297978
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf1d50b805bda9b1a21c0e9cf6bb0d8dbfab8a35b5e049af14ca236434bb8a2
3
+ size 437996134
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de83bb328e11c8dfa0798341e424e9c37512bcf68b25fd7a633b7a28c98bed1e
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71250b1eeb280ca5e6470f7bf0e5fd0c540c546e13341ebfd57b349a88d4d118
3
+ size 1064
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,754 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1032,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11627906976744186,
13
+ "grad_norm": 162.22909545898438,
14
+ "learning_rate": 1e-05,
15
+ "loss": 9.4382,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.23255813953488372,
20
+ "grad_norm": 109.6602554321289,
21
+ "learning_rate": 1e-05,
22
+ "loss": 5.5594,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.3488372093023256,
27
+ "grad_norm": 73.43177795410156,
28
+ "learning_rate": 1e-05,
29
+ "loss": 4.4092,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.46511627906976744,
34
+ "grad_norm": 75.74944305419922,
35
+ "learning_rate": 1e-05,
36
+ "loss": 3.6368,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.5813953488372093,
41
+ "grad_norm": 57.57658386230469,
42
+ "learning_rate": 1e-05,
43
+ "loss": 3.114,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.6976744186046512,
48
+ "grad_norm": 52.32157516479492,
49
+ "learning_rate": 1e-05,
50
+ "loss": 2.7366,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.813953488372093,
55
+ "grad_norm": 41.23809051513672,
56
+ "learning_rate": 1e-05,
57
+ "loss": 2.4022,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.9302325581395349,
62
+ "grad_norm": 31.800251007080078,
63
+ "learning_rate": 1e-05,
64
+ "loss": 2.0051,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.0465116279069768,
69
+ "grad_norm": 26.52857780456543,
70
+ "learning_rate": 1e-05,
71
+ "loss": 1.9384,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.1627906976744187,
76
+ "grad_norm": 26.575422286987305,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.6908,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.2790697674418605,
83
+ "grad_norm": 29.795541763305664,
84
+ "learning_rate": 1e-05,
85
+ "loss": 1.7549,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.3953488372093024,
90
+ "grad_norm": 26.20801544189453,
91
+ "learning_rate": 1e-05,
92
+ "loss": 1.726,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.5116279069767442,
97
+ "grad_norm": 25.925037384033203,
98
+ "learning_rate": 1e-05,
99
+ "loss": 1.5931,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.627906976744186,
104
+ "grad_norm": 21.952207565307617,
105
+ "learning_rate": 1e-05,
106
+ "loss": 1.5177,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.744186046511628,
111
+ "grad_norm": 20.719099044799805,
112
+ "learning_rate": 1e-05,
113
+ "loss": 1.4571,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.8604651162790697,
118
+ "grad_norm": 24.09259796142578,
119
+ "learning_rate": 1e-05,
120
+ "loss": 1.4532,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.9767441860465116,
125
+ "grad_norm": 24.448028564453125,
126
+ "learning_rate": 1e-05,
127
+ "loss": 1.4986,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.0930232558139537,
132
+ "grad_norm": 22.016250610351562,
133
+ "learning_rate": 1e-05,
134
+ "loss": 1.4055,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.2093023255813953,
139
+ "grad_norm": 20.63897705078125,
140
+ "learning_rate": 1e-05,
141
+ "loss": 1.372,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.3255813953488373,
146
+ "grad_norm": 21.750511169433594,
147
+ "learning_rate": 1e-05,
148
+ "loss": 1.2778,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.441860465116279,
153
+ "grad_norm": 17.93790054321289,
154
+ "learning_rate": 1e-05,
155
+ "loss": 1.1429,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.558139534883721,
160
+ "grad_norm": 21.550539016723633,
161
+ "learning_rate": 1e-05,
162
+ "loss": 1.3493,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 2.6744186046511627,
167
+ "grad_norm": 19.731670379638672,
168
+ "learning_rate": 1e-05,
169
+ "loss": 1.3463,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 2.7906976744186047,
174
+ "grad_norm": 18.02971649169922,
175
+ "learning_rate": 1e-05,
176
+ "loss": 1.2573,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 2.9069767441860463,
181
+ "grad_norm": 15.913904190063477,
182
+ "learning_rate": 1e-05,
183
+ "loss": 1.118,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 3.0232558139534884,
188
+ "grad_norm": 17.03731918334961,
189
+ "learning_rate": 1e-05,
190
+ "loss": 1.0932,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 3.13953488372093,
195
+ "grad_norm": 17.971464157104492,
196
+ "learning_rate": 1e-05,
197
+ "loss": 1.0658,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 3.255813953488372,
202
+ "grad_norm": 17.673015594482422,
203
+ "learning_rate": 1e-05,
204
+ "loss": 1.0964,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 3.3720930232558137,
209
+ "grad_norm": 16.616573333740234,
210
+ "learning_rate": 1e-05,
211
+ "loss": 0.9985,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 3.488372093023256,
216
+ "grad_norm": 16.42450714111328,
217
+ "learning_rate": 1e-05,
218
+ "loss": 1.0289,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 3.604651162790698,
223
+ "grad_norm": 17.35304069519043,
224
+ "learning_rate": 1e-05,
225
+ "loss": 1.1264,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 3.7209302325581395,
230
+ "grad_norm": 19.017826080322266,
231
+ "learning_rate": 1e-05,
232
+ "loss": 0.9595,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 3.8372093023255816,
237
+ "grad_norm": 16.556474685668945,
238
+ "learning_rate": 1e-05,
239
+ "loss": 0.9219,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 3.953488372093023,
244
+ "grad_norm": 15.173291206359863,
245
+ "learning_rate": 1e-05,
246
+ "loss": 1.1163,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 4.069767441860465,
251
+ "grad_norm": 16.664445877075195,
252
+ "learning_rate": 1e-05,
253
+ "loss": 0.9871,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 4.186046511627907,
258
+ "grad_norm": 20.264657974243164,
259
+ "learning_rate": 1e-05,
260
+ "loss": 0.9176,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 4.3023255813953485,
265
+ "grad_norm": 17.321226119995117,
266
+ "learning_rate": 1e-05,
267
+ "loss": 1.0307,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 4.4186046511627906,
272
+ "grad_norm": 17.926849365234375,
273
+ "learning_rate": 1e-05,
274
+ "loss": 0.9616,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 4.534883720930233,
279
+ "grad_norm": 16.469615936279297,
280
+ "learning_rate": 1e-05,
281
+ "loss": 1.0942,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 4.651162790697675,
286
+ "grad_norm": 14.785341262817383,
287
+ "learning_rate": 1e-05,
288
+ "loss": 0.852,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 4.767441860465116,
293
+ "grad_norm": 17.121408462524414,
294
+ "learning_rate": 1e-05,
295
+ "loss": 0.8726,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 4.883720930232558,
300
+ "grad_norm": 18.588102340698242,
301
+ "learning_rate": 1e-05,
302
+ "loss": 0.9815,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 5.0,
307
+ "grad_norm": 15.290245056152344,
308
+ "learning_rate": 1e-05,
309
+ "loss": 0.9589,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 5.116279069767442,
314
+ "grad_norm": 13.455266952514648,
315
+ "learning_rate": 1e-05,
316
+ "loss": 0.8205,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 5.232558139534884,
321
+ "grad_norm": 15.469796180725098,
322
+ "learning_rate": 1e-05,
323
+ "loss": 0.8461,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 5.348837209302325,
328
+ "grad_norm": 16.993955612182617,
329
+ "learning_rate": 1e-05,
330
+ "loss": 0.945,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 5.465116279069767,
335
+ "grad_norm": 16.548734664916992,
336
+ "learning_rate": 1e-05,
337
+ "loss": 0.7808,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 5.5813953488372094,
342
+ "grad_norm": 14.921213150024414,
343
+ "learning_rate": 1e-05,
344
+ "loss": 0.8232,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 5.6976744186046515,
349
+ "grad_norm": 18.470462799072266,
350
+ "learning_rate": 1e-05,
351
+ "loss": 0.887,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 5.813953488372093,
356
+ "grad_norm": 16.767337799072266,
357
+ "learning_rate": 1e-05,
358
+ "loss": 0.8067,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 5.930232558139535,
363
+ "grad_norm": 16.37430763244629,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.8454,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 6.046511627906977,
370
+ "grad_norm": 15.098798751831055,
371
+ "learning_rate": 1e-05,
372
+ "loss": 0.8504,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 6.162790697674419,
377
+ "grad_norm": 16.88681411743164,
378
+ "learning_rate": 1e-05,
379
+ "loss": 0.8148,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 6.27906976744186,
384
+ "grad_norm": 15.40526008605957,
385
+ "learning_rate": 1e-05,
386
+ "loss": 0.7982,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 6.395348837209302,
391
+ "grad_norm": 14.77994155883789,
392
+ "learning_rate": 1e-05,
393
+ "loss": 0.7612,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 6.511627906976744,
398
+ "grad_norm": 15.243223190307617,
399
+ "learning_rate": 1e-05,
400
+ "loss": 0.7741,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 6.627906976744186,
405
+ "grad_norm": 14.519372940063477,
406
+ "learning_rate": 1e-05,
407
+ "loss": 0.6861,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 6.7441860465116275,
412
+ "grad_norm": 13.514432907104492,
413
+ "learning_rate": 1e-05,
414
+ "loss": 0.7786,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 6.8604651162790695,
419
+ "grad_norm": 13.639241218566895,
420
+ "learning_rate": 1e-05,
421
+ "loss": 0.7933,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 6.976744186046512,
426
+ "grad_norm": 15.201960563659668,
427
+ "learning_rate": 1e-05,
428
+ "loss": 0.7154,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 7.093023255813954,
433
+ "grad_norm": 16.276689529418945,
434
+ "learning_rate": 1e-05,
435
+ "loss": 0.7276,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 7.209302325581396,
440
+ "grad_norm": 11.82265567779541,
441
+ "learning_rate": 1e-05,
442
+ "loss": 0.6166,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 7.325581395348837,
447
+ "grad_norm": 13.033476829528809,
448
+ "learning_rate": 1e-05,
449
+ "loss": 0.7069,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 7.441860465116279,
454
+ "grad_norm": 12.694133758544922,
455
+ "learning_rate": 1e-05,
456
+ "loss": 0.6772,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 7.558139534883721,
461
+ "grad_norm": 14.658044815063477,
462
+ "learning_rate": 1e-05,
463
+ "loss": 0.6901,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 7.674418604651163,
468
+ "grad_norm": 15.671820640563965,
469
+ "learning_rate": 1e-05,
470
+ "loss": 0.7091,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 7.790697674418604,
475
+ "grad_norm": 15.919020652770996,
476
+ "learning_rate": 1e-05,
477
+ "loss": 0.6933,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 7.906976744186046,
482
+ "grad_norm": 15.156649589538574,
483
+ "learning_rate": 1e-05,
484
+ "loss": 0.6517,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 8.023255813953488,
489
+ "grad_norm": 14.811256408691406,
490
+ "learning_rate": 1e-05,
491
+ "loss": 0.802,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 8.13953488372093,
496
+ "grad_norm": 18.02135467529297,
497
+ "learning_rate": 1e-05,
498
+ "loss": 0.6436,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 8.255813953488373,
503
+ "grad_norm": 11.791200637817383,
504
+ "learning_rate": 1e-05,
505
+ "loss": 0.6444,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 8.372093023255815,
510
+ "grad_norm": 14.757254600524902,
511
+ "learning_rate": 1e-05,
512
+ "loss": 0.5747,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 8.488372093023255,
517
+ "grad_norm": 17.326885223388672,
518
+ "learning_rate": 1e-05,
519
+ "loss": 0.6305,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 8.604651162790697,
524
+ "grad_norm": 16.550268173217773,
525
+ "learning_rate": 1e-05,
526
+ "loss": 0.58,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 8.720930232558139,
531
+ "grad_norm": 14.392647743225098,
532
+ "learning_rate": 1e-05,
533
+ "loss": 0.6368,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 8.837209302325581,
538
+ "grad_norm": 15.439419746398926,
539
+ "learning_rate": 1e-05,
540
+ "loss": 0.668,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 8.953488372093023,
545
+ "grad_norm": 14.418160438537598,
546
+ "learning_rate": 1e-05,
547
+ "loss": 0.6291,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 9.069767441860465,
552
+ "grad_norm": 13.218732833862305,
553
+ "learning_rate": 1e-05,
554
+ "loss": 0.529,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 9.186046511627907,
559
+ "grad_norm": 11.861743927001953,
560
+ "learning_rate": 1e-05,
561
+ "loss": 0.5567,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 9.30232558139535,
566
+ "grad_norm": 12.759491920471191,
567
+ "learning_rate": 1e-05,
568
+ "loss": 0.5471,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 9.418604651162791,
573
+ "grad_norm": 12.820395469665527,
574
+ "learning_rate": 1e-05,
575
+ "loss": 0.5643,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 9.534883720930232,
580
+ "grad_norm": 15.919899940490723,
581
+ "learning_rate": 1e-05,
582
+ "loss": 0.5957,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 9.651162790697674,
587
+ "grad_norm": 14.782742500305176,
588
+ "learning_rate": 1e-05,
589
+ "loss": 0.5437,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 9.767441860465116,
594
+ "grad_norm": 13.997867584228516,
595
+ "learning_rate": 1e-05,
596
+ "loss": 0.6032,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 9.883720930232558,
601
+ "grad_norm": 14.28197193145752,
602
+ "learning_rate": 1e-05,
603
+ "loss": 0.6311,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 10.0,
608
+ "grad_norm": 11.02239990234375,
609
+ "learning_rate": 1e-05,
610
+ "loss": 0.546,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 10.116279069767442,
615
+ "grad_norm": 14.239473342895508,
616
+ "learning_rate": 1e-05,
617
+ "loss": 0.4989,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 10.232558139534884,
622
+ "grad_norm": 13.41135025024414,
623
+ "learning_rate": 1e-05,
624
+ "loss": 0.5015,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 10.348837209302326,
629
+ "grad_norm": 14.583046913146973,
630
+ "learning_rate": 1e-05,
631
+ "loss": 0.54,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 10.465116279069768,
636
+ "grad_norm": 15.78074836730957,
637
+ "learning_rate": 1e-05,
638
+ "loss": 0.5602,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 10.581395348837209,
643
+ "grad_norm": 12.417160034179688,
644
+ "learning_rate": 1e-05,
645
+ "loss": 0.4988,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 10.69767441860465,
650
+ "grad_norm": 14.191791534423828,
651
+ "learning_rate": 1e-05,
652
+ "loss": 0.6066,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 10.813953488372093,
657
+ "grad_norm": 15.347858428955078,
658
+ "learning_rate": 1e-05,
659
+ "loss": 0.5065,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 10.930232558139535,
664
+ "grad_norm": 12.459039688110352,
665
+ "learning_rate": 1e-05,
666
+ "loss": 0.5716,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 11.046511627906977,
671
+ "grad_norm": 9.841126441955566,
672
+ "learning_rate": 1e-05,
673
+ "loss": 0.4517,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 11.162790697674419,
678
+ "grad_norm": 12.673447608947754,
679
+ "learning_rate": 1e-05,
680
+ "loss": 0.5524,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 11.279069767441861,
685
+ "grad_norm": 14.562691688537598,
686
+ "learning_rate": 1e-05,
687
+ "loss": 0.464,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 11.395348837209303,
692
+ "grad_norm": 12.976771354675293,
693
+ "learning_rate": 1e-05,
694
+ "loss": 0.4795,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 11.511627906976745,
699
+ "grad_norm": 10.579855918884277,
700
+ "learning_rate": 1e-05,
701
+ "loss": 0.482,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 11.627906976744185,
706
+ "grad_norm": 14.409245491027832,
707
+ "learning_rate": 1e-05,
708
+ "loss": 0.5431,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 11.744186046511627,
713
+ "grad_norm": 13.707283020019531,
714
+ "learning_rate": 1e-05,
715
+ "loss": 0.4543,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 11.86046511627907,
720
+ "grad_norm": 14.802945137023926,
721
+ "learning_rate": 1e-05,
722
+ "loss": 0.4466,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 11.976744186046512,
727
+ "grad_norm": 11.310287475585938,
728
+ "learning_rate": 1e-05,
729
+ "loss": 0.4737,
730
+ "step": 1030
731
+ }
732
+ ],
733
+ "logging_steps": 10,
734
+ "max_steps": 2580,
735
+ "num_input_tokens_seen": 0,
736
+ "num_train_epochs": 30,
737
+ "save_steps": 500,
738
+ "stateful_callbacks": {
739
+ "TrainerControl": {
740
+ "args": {
741
+ "should_epoch_stop": false,
742
+ "should_evaluate": false,
743
+ "should_log": false,
744
+ "should_save": true,
745
+ "should_training_stop": false
746
+ },
747
+ "attributes": {}
748
+ }
749
+ },
750
+ "total_flos": 0.0,
751
+ "train_batch_size": 64,
752
+ "trial_name": null,
753
+ "trial_params": null
754
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535b0a8dcc9716f5c69e2df5b899266cd731a0793f53f2cd7fc963e9fce2d8f1
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff