SCM-LAB commited on
Commit
e546c64
·
verified ·
1 Parent(s): 439dba9

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +30 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +721 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 258,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "tokenizer_class": "PhobertTokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.39.3",
27
+ "type_vocab_size": 1,
28
+ "use_cache": true,
29
+ "vocab_size": 64001
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51414ff6067b5170e7ff65d19a7c0c655afa97405644b6d96b694c9ddd06ad06
3
+ size 540023384
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da444623471617b33ac7ec01b36268080217ee0dcc7fcdc7e7d8ae64ac19579
3
+ size 1080166650
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899aa32999f045fb3db64fcd4451e3c03ba51ce3ad9ad28d6c0f20c726155c21
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472400b40c533f1b2050f57107f24524ef4cf4ede0c9f9e20a25912d3bc1583e
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 2.37485408782959,
14
+ "learning_rate": 0.0002,
15
+ "loss": 0.7725,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "grad_norm": 2.3556101322174072,
21
+ "learning_rate": 0.0004,
22
+ "loss": 0.73,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.15,
27
+ "grad_norm": 4.192414283752441,
28
+ "learning_rate": 0.0006,
29
+ "loss": 0.7414,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.2,
34
+ "grad_norm": 3.5939464569091797,
35
+ "learning_rate": 0.0008,
36
+ "loss": 0.7544,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.25,
41
+ "grad_norm": 15.336837768554688,
42
+ "learning_rate": 0.001,
43
+ "loss": 0.7723,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.3,
48
+ "grad_norm": 3.893497943878174,
49
+ "learning_rate": 0.0009894736842105264,
50
+ "loss": 0.7893,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.35,
55
+ "grad_norm": 11.713598251342773,
56
+ "learning_rate": 0.0009789473684210528,
57
+ "loss": 0.7843,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.4,
62
+ "grad_norm": 13.350496292114258,
63
+ "learning_rate": 0.000968421052631579,
64
+ "loss": 0.7894,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.45,
69
+ "grad_norm": 2.8563292026519775,
70
+ "learning_rate": 0.0009578947368421053,
71
+ "loss": 0.7843,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.5,
76
+ "grad_norm": 9.680468559265137,
77
+ "learning_rate": 0.0009473684210526315,
78
+ "loss": 0.8511,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.55,
83
+ "grad_norm": 4.680222034454346,
84
+ "learning_rate": 0.0009368421052631579,
85
+ "loss": 0.8686,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.6,
90
+ "grad_norm": 12.037607192993164,
91
+ "learning_rate": 0.0009263157894736843,
92
+ "loss": 0.8393,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.65,
97
+ "grad_norm": 8.154277801513672,
98
+ "learning_rate": 0.0009157894736842105,
99
+ "loss": 0.8252,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.7,
104
+ "grad_norm": 3.256535530090332,
105
+ "learning_rate": 0.0009052631578947369,
106
+ "loss": 0.7854,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.75,
111
+ "grad_norm": 4.168020725250244,
112
+ "learning_rate": 0.0008947368421052632,
113
+ "loss": 0.8059,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.8,
118
+ "grad_norm": 2.775940418243408,
119
+ "learning_rate": 0.0008842105263157894,
120
+ "loss": 0.8272,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.85,
125
+ "grad_norm": 14.476820945739746,
126
+ "learning_rate": 0.0008736842105263159,
127
+ "loss": 0.8006,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.9,
132
+ "grad_norm": 14.232259750366211,
133
+ "learning_rate": 0.0008631578947368422,
134
+ "loss": 0.7537,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.95,
139
+ "grad_norm": 5.338253021240234,
140
+ "learning_rate": 0.0008526315789473684,
141
+ "loss": 0.7831,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 1.0,
146
+ "grad_norm": 5.454962730407715,
147
+ "learning_rate": 0.0008421052631578947,
148
+ "loss": 0.7633,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 1.05,
153
+ "grad_norm": 8.250731468200684,
154
+ "learning_rate": 0.0008315789473684212,
155
+ "loss": 0.7565,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 1.1,
160
+ "grad_norm": 8.233278274536133,
161
+ "learning_rate": 0.0008210526315789474,
162
+ "loss": 0.7724,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 1.15,
167
+ "grad_norm": 10.603631019592285,
168
+ "learning_rate": 0.0008105263157894737,
169
+ "loss": 0.782,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 1.2,
174
+ "grad_norm": 3.75233793258667,
175
+ "learning_rate": 0.0008,
176
+ "loss": 0.7519,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 1.25,
181
+ "grad_norm": 4.677459239959717,
182
+ "learning_rate": 0.0007894736842105263,
183
+ "loss": 0.7556,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 1.3,
188
+ "grad_norm": 4.583637714385986,
189
+ "learning_rate": 0.0007789473684210527,
190
+ "loss": 0.7459,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 1.35,
195
+ "grad_norm": 9.343656539916992,
196
+ "learning_rate": 0.0007684210526315789,
197
+ "loss": 0.7802,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 1.4,
202
+ "grad_norm": 1.4162571430206299,
203
+ "learning_rate": 0.0007578947368421053,
204
+ "loss": 0.7384,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 1.45,
209
+ "grad_norm": 6.586658477783203,
210
+ "learning_rate": 0.0007473684210526316,
211
+ "loss": 0.7795,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 1.5,
216
+ "grad_norm": 5.946737289428711,
217
+ "learning_rate": 0.0007368421052631579,
218
+ "loss": 0.7381,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 1.55,
223
+ "grad_norm": 5.825309753417969,
224
+ "learning_rate": 0.0007263157894736843,
225
+ "loss": 0.7482,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 1.6,
230
+ "grad_norm": 2.1794614791870117,
231
+ "learning_rate": 0.0007157894736842105,
232
+ "loss": 0.7381,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 1.65,
237
+ "grad_norm": 7.837281227111816,
238
+ "learning_rate": 0.0007052631578947368,
239
+ "loss": 0.7314,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 1.7,
244
+ "grad_norm": 4.612753868103027,
245
+ "learning_rate": 0.0006947368421052632,
246
+ "loss": 0.7384,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 1.75,
251
+ "grad_norm": 6.038923263549805,
252
+ "learning_rate": 0.0006842105263157895,
253
+ "loss": 0.752,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 1.8,
258
+ "grad_norm": 5.17457389831543,
259
+ "learning_rate": 0.0006736842105263158,
260
+ "loss": 0.7421,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 1.85,
265
+ "grad_norm": 4.990045547485352,
266
+ "learning_rate": 0.0006631578947368421,
267
+ "loss": 0.7253,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 1.9,
272
+ "grad_norm": 3.1730449199676514,
273
+ "learning_rate": 0.0006526315789473684,
274
+ "loss": 0.7202,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 1.95,
279
+ "grad_norm": 1.5063399076461792,
280
+ "learning_rate": 0.0006421052631578948,
281
+ "loss": 0.7488,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 2.0,
286
+ "grad_norm": 3.6247060298919678,
287
+ "learning_rate": 0.0006315789473684211,
288
+ "loss": 0.7263,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 2.05,
293
+ "grad_norm": 1.4821553230285645,
294
+ "learning_rate": 0.0006210526315789474,
295
+ "loss": 0.7176,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 2.1,
300
+ "grad_norm": 2.641312837600708,
301
+ "learning_rate": 0.0006105263157894737,
302
+ "loss": 0.7182,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 2.15,
307
+ "grad_norm": 3.3185555934906006,
308
+ "learning_rate": 0.0006,
309
+ "loss": 0.7257,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 2.2,
314
+ "grad_norm": 2.4133715629577637,
315
+ "learning_rate": 0.0005894736842105263,
316
+ "loss": 0.7202,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 2.25,
321
+ "grad_norm": 1.8694628477096558,
322
+ "learning_rate": 0.0005789473684210527,
323
+ "loss": 0.7172,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 2.3,
328
+ "grad_norm": 5.248977184295654,
329
+ "learning_rate": 0.0005684210526315789,
330
+ "loss": 0.7148,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 2.35,
335
+ "grad_norm": 6.179994106292725,
336
+ "learning_rate": 0.0005578947368421052,
337
+ "loss": 0.7308,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 2.4,
342
+ "grad_norm": 1.9322715997695923,
343
+ "learning_rate": 0.0005473684210526317,
344
+ "loss": 0.7163,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 2.45,
349
+ "grad_norm": 1.6366279125213623,
350
+ "learning_rate": 0.0005368421052631579,
351
+ "loss": 0.7262,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 2.5,
356
+ "grad_norm": 5.179625034332275,
357
+ "learning_rate": 0.0005263157894736842,
358
+ "loss": 0.7054,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 2.55,
363
+ "grad_norm": 1.7737842798233032,
364
+ "learning_rate": 0.0005157894736842106,
365
+ "loss": 0.7104,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 2.6,
370
+ "grad_norm": 1.6575433015823364,
371
+ "learning_rate": 0.0005052631578947368,
372
+ "loss": 0.7114,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 2.65,
377
+ "grad_norm": 3.6518235206604004,
378
+ "learning_rate": 0.0004947368421052632,
379
+ "loss": 0.7087,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 2.7,
384
+ "grad_norm": 1.3658417463302612,
385
+ "learning_rate": 0.0004842105263157895,
386
+ "loss": 0.7106,
387
+ "step": 27000
388
+ },
389
+ {
390
+ "epoch": 2.75,
391
+ "grad_norm": 1.312829852104187,
392
+ "learning_rate": 0.00047368421052631577,
393
+ "loss": 0.7118,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 2.8,
398
+ "grad_norm": 2.94315767288208,
399
+ "learning_rate": 0.00046315789473684214,
400
+ "loss": 0.7102,
401
+ "step": 28000
402
+ },
403
+ {
404
+ "epoch": 2.85,
405
+ "grad_norm": 1.349211573600769,
406
+ "learning_rate": 0.00045263157894736845,
407
+ "loss": 0.7058,
408
+ "step": 28500
409
+ },
410
+ {
411
+ "epoch": 2.9,
412
+ "grad_norm": 1.3551281690597534,
413
+ "learning_rate": 0.0004421052631578947,
414
+ "loss": 0.708,
415
+ "step": 29000
416
+ },
417
+ {
418
+ "epoch": 2.95,
419
+ "grad_norm": 1.3995367288589478,
420
+ "learning_rate": 0.0004315789473684211,
421
+ "loss": 0.7106,
422
+ "step": 29500
423
+ },
424
+ {
425
+ "epoch": 3.0,
426
+ "grad_norm": 0.9616995453834534,
427
+ "learning_rate": 0.00042105263157894734,
428
+ "loss": 0.7021,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 3.05,
433
+ "grad_norm": 2.390662908554077,
434
+ "learning_rate": 0.0004105263157894737,
435
+ "loss": 0.7061,
436
+ "step": 30500
437
+ },
438
+ {
439
+ "epoch": 3.1,
440
+ "grad_norm": 1.2397950887680054,
441
+ "learning_rate": 0.0004,
442
+ "loss": 0.705,
443
+ "step": 31000
444
+ },
445
+ {
446
+ "epoch": 3.15,
447
+ "grad_norm": 3.110950231552124,
448
+ "learning_rate": 0.00038947368421052633,
449
+ "loss": 0.7031,
450
+ "step": 31500
451
+ },
452
+ {
453
+ "epoch": 3.2,
454
+ "grad_norm": 1.1811543703079224,
455
+ "learning_rate": 0.00037894736842105265,
456
+ "loss": 0.7013,
457
+ "step": 32000
458
+ },
459
+ {
460
+ "epoch": 3.25,
461
+ "grad_norm": 1.1221048831939697,
462
+ "learning_rate": 0.00036842105263157896,
463
+ "loss": 0.7026,
464
+ "step": 32500
465
+ },
466
+ {
467
+ "epoch": 3.3,
468
+ "grad_norm": 0.9882568717002869,
469
+ "learning_rate": 0.0003578947368421053,
470
+ "loss": 0.7012,
471
+ "step": 33000
472
+ },
473
+ {
474
+ "epoch": 3.35,
475
+ "grad_norm": 0.8155710697174072,
476
+ "learning_rate": 0.0003473684210526316,
477
+ "loss": 0.7033,
478
+ "step": 33500
479
+ },
480
+ {
481
+ "epoch": 3.4,
482
+ "grad_norm": 1.1295320987701416,
483
+ "learning_rate": 0.0003368421052631579,
484
+ "loss": 0.701,
485
+ "step": 34000
486
+ },
487
+ {
488
+ "epoch": 3.45,
489
+ "grad_norm": 2.0776407718658447,
490
+ "learning_rate": 0.0003263157894736842,
491
+ "loss": 0.6986,
492
+ "step": 34500
493
+ },
494
+ {
495
+ "epoch": 3.5,
496
+ "grad_norm": 1.7907339334487915,
497
+ "learning_rate": 0.00031578947368421053,
498
+ "loss": 0.698,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 3.55,
503
+ "grad_norm": 1.978267788887024,
504
+ "learning_rate": 0.00030526315789473684,
505
+ "loss": 0.7031,
506
+ "step": 35500
507
+ },
508
+ {
509
+ "epoch": 3.6,
510
+ "grad_norm": 3.065232515335083,
511
+ "learning_rate": 0.00029473684210526316,
512
+ "loss": 0.697,
513
+ "step": 36000
514
+ },
515
+ {
516
+ "epoch": 3.65,
517
+ "grad_norm": 0.9516103267669678,
518
+ "learning_rate": 0.00028421052631578947,
519
+ "loss": 0.7006,
520
+ "step": 36500
521
+ },
522
+ {
523
+ "epoch": 3.7,
524
+ "grad_norm": 1.0045952796936035,
525
+ "learning_rate": 0.00027368421052631584,
526
+ "loss": 0.6986,
527
+ "step": 37000
528
+ },
529
+ {
530
+ "epoch": 3.75,
531
+ "grad_norm": 1.6901030540466309,
532
+ "learning_rate": 0.0002631578947368421,
533
+ "loss": 0.6995,
534
+ "step": 37500
535
+ },
536
+ {
537
+ "epoch": 3.8,
538
+ "grad_norm": 1.8813843727111816,
539
+ "learning_rate": 0.0002526315789473684,
540
+ "loss": 0.6987,
541
+ "step": 38000
542
+ },
543
+ {
544
+ "epoch": 3.85,
545
+ "grad_norm": 1.8174165487289429,
546
+ "learning_rate": 0.00024210526315789475,
547
+ "loss": 0.6999,
548
+ "step": 38500
549
+ },
550
+ {
551
+ "epoch": 3.9,
552
+ "grad_norm": 1.7451245784759521,
553
+ "learning_rate": 0.00023157894736842107,
554
+ "loss": 0.6981,
555
+ "step": 39000
556
+ },
557
+ {
558
+ "epoch": 3.95,
559
+ "grad_norm": 0.9422154426574707,
560
+ "learning_rate": 0.00022105263157894735,
561
+ "loss": 0.6962,
562
+ "step": 39500
563
+ },
564
+ {
565
+ "epoch": 4.0,
566
+ "grad_norm": 2.196399688720703,
567
+ "learning_rate": 0.00021052631578947367,
568
+ "loss": 0.6984,
569
+ "step": 40000
570
+ },
571
+ {
572
+ "epoch": 4.05,
573
+ "grad_norm": 1.940382719039917,
574
+ "learning_rate": 0.0002,
575
+ "loss": 0.6945,
576
+ "step": 40500
577
+ },
578
+ {
579
+ "epoch": 4.1,
580
+ "grad_norm": 1.2243621349334717,
581
+ "learning_rate": 0.00018947368421052632,
582
+ "loss": 0.6965,
583
+ "step": 41000
584
+ },
585
+ {
586
+ "epoch": 4.15,
587
+ "grad_norm": 2.004392623901367,
588
+ "learning_rate": 0.00017894736842105264,
589
+ "loss": 0.6992,
590
+ "step": 41500
591
+ },
592
+ {
593
+ "epoch": 4.2,
594
+ "grad_norm": 1.8801628351211548,
595
+ "learning_rate": 0.00016842105263157895,
596
+ "loss": 0.6944,
597
+ "step": 42000
598
+ },
599
+ {
600
+ "epoch": 4.25,
601
+ "grad_norm": 0.9306873679161072,
602
+ "learning_rate": 0.00015789473684210527,
603
+ "loss": 0.693,
604
+ "step": 42500
605
+ },
606
+ {
607
+ "epoch": 4.3,
608
+ "grad_norm": 1.9730675220489502,
609
+ "learning_rate": 0.00014736842105263158,
610
+ "loss": 0.6957,
611
+ "step": 43000
612
+ },
613
+ {
614
+ "epoch": 4.35,
615
+ "grad_norm": 1.0207428932189941,
616
+ "learning_rate": 0.00013684210526315792,
617
+ "loss": 0.7004,
618
+ "step": 43500
619
+ },
620
+ {
621
+ "epoch": 4.4,
622
+ "grad_norm": 0.9524587988853455,
623
+ "learning_rate": 0.0001263157894736842,
624
+ "loss": 0.6927,
625
+ "step": 44000
626
+ },
627
+ {
628
+ "epoch": 4.45,
629
+ "grad_norm": 0.9829258322715759,
630
+ "learning_rate": 0.00011578947368421053,
631
+ "loss": 0.6962,
632
+ "step": 44500
633
+ },
634
+ {
635
+ "epoch": 4.5,
636
+ "grad_norm": 1.317120909690857,
637
+ "learning_rate": 0.00010526315789473683,
638
+ "loss": 0.6943,
639
+ "step": 45000
640
+ },
641
+ {
642
+ "epoch": 4.55,
643
+ "grad_norm": 1.8932749032974243,
644
+ "learning_rate": 9.473684210526316e-05,
645
+ "loss": 0.6933,
646
+ "step": 45500
647
+ },
648
+ {
649
+ "epoch": 4.6,
650
+ "grad_norm": 0.8536391854286194,
651
+ "learning_rate": 8.421052631578948e-05,
652
+ "loss": 0.693,
653
+ "step": 46000
654
+ },
655
+ {
656
+ "epoch": 4.65,
657
+ "grad_norm": 1.9397382736206055,
658
+ "learning_rate": 7.368421052631579e-05,
659
+ "loss": 0.6942,
660
+ "step": 46500
661
+ },
662
+ {
663
+ "epoch": 4.7,
664
+ "grad_norm": 1.846257209777832,
665
+ "learning_rate": 6.31578947368421e-05,
666
+ "loss": 0.6941,
667
+ "step": 47000
668
+ },
669
+ {
670
+ "epoch": 4.75,
671
+ "grad_norm": 0.937384307384491,
672
+ "learning_rate": 5.263157894736842e-05,
673
+ "loss": 0.6956,
674
+ "step": 47500
675
+ },
676
+ {
677
+ "epoch": 4.8,
678
+ "grad_norm": 0.9019428491592407,
679
+ "learning_rate": 4.210526315789474e-05,
680
+ "loss": 0.6935,
681
+ "step": 48000
682
+ },
683
+ {
684
+ "epoch": 4.85,
685
+ "grad_norm": 1.892066478729248,
686
+ "learning_rate": 3.157894736842105e-05,
687
+ "loss": 0.6945,
688
+ "step": 48500
689
+ },
690
+ {
691
+ "epoch": 4.9,
692
+ "grad_norm": 1.764987826347351,
693
+ "learning_rate": 2.105263157894737e-05,
694
+ "loss": 0.695,
695
+ "step": 49000
696
+ },
697
+ {
698
+ "epoch": 4.95,
699
+ "grad_norm": 1.626028060913086,
700
+ "learning_rate": 1.0526315789473684e-05,
701
+ "loss": 0.6941,
702
+ "step": 49500
703
+ },
704
+ {
705
+ "epoch": 5.0,
706
+ "grad_norm": 1.6325174570083618,
707
+ "learning_rate": 0.0,
708
+ "loss": 0.6935,
709
+ "step": 50000
710
+ }
711
+ ],
712
+ "logging_steps": 500,
713
+ "max_steps": 50000,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 5,
716
+ "save_steps": 500,
717
+ "total_flos": 2877777168000000.0,
718
+ "train_batch_size": 2,
719
+ "trial_name": null,
720
+ "trial_params": null
721
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd66173391bcefe6df69d0eeefa6bfd9eca811bb11efc03aa1f6decd1ce0afd3
3
+ size 4920