bimabk commited on
Commit
d057f26
·
verified ·
1 Parent(s): 1aa5f3a

Upload task output 0fe99f84-0038-4cec-8e61-1eb9fea8dc55

Browse files
config.json CHANGED
@@ -32,6 +32,6 @@
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.51.3",
34
  "unsloth_fixed": true,
35
- "use_cache": true,
36
  "vocab_size": 128256
37
  }
 
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.51.3",
34
  "unsloth_fixed": true,
35
+ "use_cache": false,
36
  "vocab_size": 128256
37
  }
generation_config.json CHANGED
@@ -1,5 +1,14 @@
1
  {
2
- "temperature": null,
3
- "top_p": null,
 
 
 
 
 
 
 
 
 
4
  "transformers_version": "4.51.3"
5
  }
 
1
  {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
  "transformers_version": "4.51.3"
14
  }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 280,1.8396857976913452
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a967a42dc3590cb8b1d6c07c23c72b410d8a73b7df1ef43685d20eb2e403f137
3
  size 4965799096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67d7f869083c032884204f981e4089c56ef752c24c19e0deac51aed739a77479
3
  size 4965799096
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b770216613ac5c34d7c54bdff1fa616bc4e338a9d0b20af6303e48c295ee23c
3
  size 1459729952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dc393c55b185da78ce37f983111fcc53789d5c68a2e36d3fc5e4defcd949dc
3
  size 1459729952
trainer_state.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 280,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03571428571428571,
14
+ "grad_norm": 19.5,
15
+ "learning_rate": 1.5838110992819075e-05,
16
+ "loss": 4.4082,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.07142857142857142,
21
+ "grad_norm": 11.6875,
22
+ "learning_rate": 3.5635749733842914e-05,
23
+ "loss": 3.2859,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.10714285714285714,
28
+ "grad_norm": 8.1875,
29
+ "learning_rate": 5.5433388474866766e-05,
30
+ "loss": 2.8128,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.14285714285714285,
35
+ "grad_norm": 6.3125,
36
+ "learning_rate": 7.52310272158906e-05,
37
+ "loss": 2.6378,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.17857142857142858,
42
+ "grad_norm": 5.3125,
43
+ "learning_rate": 9.502866595691445e-05,
44
+ "loss": 2.4924,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.21428571428571427,
49
+ "grad_norm": 5.84375,
50
+ "learning_rate": 0.0001148263046979383,
51
+ "loss": 2.4994,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.25,
56
+ "grad_norm": 5.125,
57
+ "learning_rate": 0.00013462394343896213,
58
+ "loss": 2.4877,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.2857142857142857,
63
+ "grad_norm": 5.3125,
64
+ "learning_rate": 0.00013855579078350677,
65
+ "loss": 2.5123,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.32142857142857145,
70
+ "grad_norm": 4.03125,
71
+ "learning_rate": 0.0001384433896787117,
72
+ "loss": 2.453,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.35714285714285715,
77
+ "grad_norm": 4.5625,
78
+ "learning_rate": 0.00013824472478409896,
79
+ "loss": 2.4429,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.39285714285714285,
84
+ "grad_norm": 3.75,
85
+ "learning_rate": 0.00013796012675777958,
86
+ "loss": 2.4012,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.42857142857142855,
91
+ "grad_norm": 3.234375,
92
+ "learning_rate": 0.00013759006928508162,
93
+ "loss": 2.351,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.4642857142857143,
98
+ "grad_norm": 3.71875,
99
+ "learning_rate": 0.00013713516829014772,
100
+ "loss": 2.3272,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.5,
105
+ "grad_norm": 3.875,
106
+ "learning_rate": 0.00013659618091079015,
107
+ "loss": 2.3015,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.5357142857142857,
112
+ "grad_norm": 3.171875,
113
+ "learning_rate": 0.00013597400423830962,
114
+ "loss": 2.2773,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.5714285714285714,
119
+ "grad_norm": 3.359375,
120
+ "learning_rate": 0.00013526967382437543,
121
+ "loss": 2.2415,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.6071428571428571,
126
+ "grad_norm": 2.9375,
127
+ "learning_rate": 0.00013448436195745173,
128
+ "loss": 2.1806,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.6428571428571429,
133
+ "grad_norm": 2.8125,
134
+ "learning_rate": 0.00013361937571163926,
135
+ "loss": 2.1731,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.6785714285714286,
140
+ "grad_norm": 3.015625,
141
+ "learning_rate": 0.00013267615477117944,
142
+ "loss": 2.2264,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.7142857142857143,
147
+ "grad_norm": 2.75,
148
+ "learning_rate": 0.0001316562690342419,
149
+ "loss": 2.1964,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.75,
154
+ "grad_norm": 2.71875,
155
+ "learning_rate": 0.00013056141599998415,
156
+ "loss": 2.2052,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.7857142857142857,
161
+ "grad_norm": 3.21875,
162
+ "learning_rate": 0.00012939341794323162,
163
+ "loss": 2.1698,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.8214285714285714,
168
+ "grad_norm": 2.734375,
169
+ "learning_rate": 0.00012815421888148093,
170
+ "loss": 2.1723,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.8571428571428571,
175
+ "grad_norm": 2.515625,
176
+ "learning_rate": 0.0001268458813392749,
177
+ "loss": 2.1478,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.8928571428571429,
182
+ "grad_norm": 2.546875,
183
+ "learning_rate": 0.00012547058291533382,
184
+ "loss": 2.0849,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.9285714285714286,
189
+ "grad_norm": 2.640625,
190
+ "learning_rate": 0.00012403061265815721,
191
+ "loss": 2.1297,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.9642857142857143,
196
+ "grad_norm": 2.5,
197
+ "learning_rate": 0.00012252836725612872,
198
+ "loss": 2.0767,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 1.0,
203
+ "grad_norm": 2.34375,
204
+ "learning_rate": 0.00012096634704846468,
205
+ "loss": 2.1226,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 1.0,
210
+ "eval_loss": 2.0443668365478516,
211
+ "eval_runtime": 0.4691,
212
+ "eval_samples_per_second": 10.658,
213
+ "eval_steps_per_second": 10.658,
214
+ "step": 140
215
+ },
216
+ {
217
+ "epoch": 1.0357142857142858,
218
+ "grad_norm": 2.5625,
219
+ "learning_rate": 0.00011934715186364626,
220
+ "loss": 1.7431,
221
+ "step": 145
222
+ },
223
+ {
224
+ "epoch": 1.0714285714285714,
225
+ "grad_norm": 2.390625,
226
+ "learning_rate": 0.00011767347669226159,
227
+ "loss": 1.6931,
228
+ "step": 150
229
+ },
230
+ {
231
+ "epoch": 1.1071428571428572,
232
+ "grad_norm": 2.40625,
233
+ "learning_rate": 0.00011594810720145982,
234
+ "loss": 1.6984,
235
+ "step": 155
236
+ },
237
+ {
238
+ "epoch": 1.1428571428571428,
239
+ "grad_norm": 2.46875,
240
+ "learning_rate": 0.00011417391509848311,
241
+ "loss": 1.7018,
242
+ "step": 160
243
+ },
244
+ {
245
+ "epoch": 1.1785714285714286,
246
+ "grad_norm": 2.140625,
247
+ "learning_rate": 0.00011235385335099333,
248
+ "loss": 1.7014,
249
+ "step": 165
250
+ },
251
+ {
252
+ "epoch": 1.2142857142857142,
253
+ "grad_norm": 2.65625,
254
+ "learning_rate": 0.00011049095127214879,
255
+ "loss": 1.7539,
256
+ "step": 170
257
+ },
258
+ {
259
+ "epoch": 1.25,
260
+ "grad_norm": 2.65625,
261
+ "learning_rate": 0.00010858830947861153,
262
+ "loss": 1.7273,
263
+ "step": 175
264
+ },
265
+ {
266
+ "epoch": 1.2857142857142856,
267
+ "grad_norm": 2.375,
268
+ "learning_rate": 0.00010664909472987668,
269
+ "loss": 1.7267,
270
+ "step": 180
271
+ },
272
+ {
273
+ "epoch": 1.3214285714285714,
274
+ "grad_norm": 2.484375,
275
+ "learning_rate": 0.00010467653465751409,
276
+ "loss": 1.7098,
277
+ "step": 185
278
+ },
279
+ {
280
+ "epoch": 1.3571428571428572,
281
+ "grad_norm": 2.359375,
282
+ "learning_rate": 0.00010267391239309385,
283
+ "loss": 1.7123,
284
+ "step": 190
285
+ },
286
+ {
287
+ "epoch": 1.3928571428571428,
288
+ "grad_norm": 2.25,
289
+ "learning_rate": 0.00010064456110373801,
290
+ "loss": 1.7539,
291
+ "step": 195
292
+ },
293
+ {
294
+ "epoch": 1.4285714285714286,
295
+ "grad_norm": 2.34375,
296
+ "learning_rate": 9.859185844439268e-05,
297
+ "loss": 1.7102,
298
+ "step": 200
299
+ },
300
+ {
301
+ "epoch": 1.4642857142857144,
302
+ "grad_norm": 2.203125,
303
+ "learning_rate": 9.651922093605485e-05,
304
+ "loss": 1.6981,
305
+ "step": 205
306
+ },
307
+ {
308
+ "epoch": 1.5,
309
+ "grad_norm": 2.171875,
310
+ "learning_rate": 9.443009827931028e-05,
311
+ "loss": 1.7112,
312
+ "step": 210
313
+ },
314
+ {
315
+ "epoch": 1.5357142857142856,
316
+ "grad_norm": 2.234375,
317
+ "learning_rate": 9.232796761264735e-05,
318
+ "loss": 1.7439,
319
+ "step": 215
320
+ },
321
+ {
322
+ "epoch": 1.5714285714285714,
323
+ "grad_norm": 2.21875,
324
+ "learning_rate": 9.021632772510318e-05,
325
+ "loss": 1.7149,
326
+ "step": 220
327
+ },
328
+ {
329
+ "epoch": 1.6071428571428572,
330
+ "grad_norm": 2.109375,
331
+ "learning_rate": 8.809869323287461e-05,
332
+ "loss": 1.6947,
333
+ "step": 225
334
+ },
335
+ {
336
+ "epoch": 1.6428571428571428,
337
+ "grad_norm": 2.296875,
338
+ "learning_rate": 8.597858872958643e-05,
339
+ "loss": 1.6722,
340
+ "step": 230
341
+ },
342
+ {
343
+ "epoch": 1.6785714285714286,
344
+ "grad_norm": 2.140625,
345
+ "learning_rate": 8.385954291995294e-05,
346
+ "loss": 1.6419,
347
+ "step": 235
348
+ },
349
+ {
350
+ "epoch": 1.7142857142857144,
351
+ "grad_norm": 2.0,
352
+ "learning_rate": 8.174508274659743e-05,
353
+ "loss": 1.6508,
354
+ "step": 240
355
+ },
356
+ {
357
+ "epoch": 1.75,
358
+ "grad_norm": 2.03125,
359
+ "learning_rate": 7.963872751980418e-05,
360
+ "loss": 1.6213,
361
+ "step": 245
362
+ },
363
+ {
364
+ "epoch": 1.7857142857142856,
365
+ "grad_norm": 2.109375,
366
+ "learning_rate": 7.754398305997372e-05,
367
+ "loss": 1.6257,
368
+ "step": 250
369
+ },
370
+ {
371
+ "epoch": 1.8214285714285714,
372
+ "grad_norm": 2.109375,
373
+ "learning_rate": 7.546433586253086e-05,
374
+ "loss": 1.5915,
375
+ "step": 255
376
+ },
377
+ {
378
+ "epoch": 1.8571428571428572,
379
+ "grad_norm": 1.890625,
380
+ "learning_rate": 7.340324729499708e-05,
381
+ "loss": 1.6334,
382
+ "step": 260
383
+ },
384
+ {
385
+ "epoch": 1.8928571428571428,
386
+ "grad_norm": 1.96875,
387
+ "learning_rate": 7.136414783588594e-05,
388
+ "loss": 1.6345,
389
+ "step": 265
390
+ },
391
+ {
392
+ "epoch": 1.9285714285714286,
393
+ "grad_norm": 2.015625,
394
+ "learning_rate": 6.935043136501011e-05,
395
+ "loss": 1.6109,
396
+ "step": 270
397
+ },
398
+ {
399
+ "epoch": 1.9642857142857144,
400
+ "grad_norm": 2.09375,
401
+ "learning_rate": 6.736544951470336e-05,
402
+ "loss": 1.6274,
403
+ "step": 275
404
+ },
405
+ {
406
+ "epoch": 2.0,
407
+ "grad_norm": 2.109375,
408
+ "learning_rate": 6.541250609135935e-05,
409
+ "loss": 1.6177,
410
+ "step": 280
411
+ },
412
+ {
413
+ "epoch": 2.0,
414
+ "eval_loss": 1.8396857976913452,
415
+ "eval_runtime": 0.3556,
416
+ "eval_samples_per_second": 14.061,
417
+ "eval_steps_per_second": 14.061,
418
+ "step": 280
419
+ }
420
+ ],
421
+ "logging_steps": 5,
422
+ "max_steps": 420,
423
+ "num_input_tokens_seen": 0,
424
+ "num_train_epochs": 3,
425
+ "save_steps": 500,
426
+ "stateful_callbacks": {
427
+ "TrainerControl": {
428
+ "args": {
429
+ "should_epoch_stop": false,
430
+ "should_evaluate": false,
431
+ "should_log": false,
432
+ "should_save": true,
433
+ "should_training_stop": false
434
+ },
435
+ "attributes": {}
436
+ }
437
+ },
438
+ "total_flos": 4.6551816128692224e+17,
439
+ "train_batch_size": 48,
440
+ "trial_name": null,
441
+ "trial_params": null
442
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a137a800cea8d5ea995617ca46b1be4cd8a979faf342f9cfe6c266e9784a603e
3
+ size 5688