sedrickkeh commited on
Commit
0dc2c96
·
verified ·
1 Parent(s): 60cf9ba

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: oh_v1.3_camel_math_x2
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_camel_math_x2
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.7127
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: oh_v1.3_camel_math_x2
 
16
 
17
  # oh_v1.3_camel_math_x2
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh_v1.3_camel_math_x2 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7127
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9948364888123926,
3
+ "eval_loss": 0.7126539349555969,
4
+ "eval_runtime": 310.8733,
5
+ "eval_samples_per_second": 25.181,
6
+ "eval_steps_per_second": 0.396,
7
+ "total_flos": 1457073023877120.0,
8
+ "train_loss": 0.6931865083760229,
9
+ "train_runtime": 51465.7493,
10
+ "train_samples_per_second": 8.669,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9948364888123926,
3
+ "eval_loss": 0.7126539349555969,
4
+ "eval_runtime": 310.8733,
5
+ "eval_samples_per_second": 25.181,
6
+ "eval_steps_per_second": 0.396
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9948364888123926,
3
+ "total_flos": 1457073023877120.0,
4
+ "train_loss": 0.6931865083760229,
5
+ "train_runtime": 51465.7493,
6
+ "train_samples_per_second": 8.669,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,675 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9948364888123926,
5
+ "eval_steps": 500,
6
+ "global_step": 870,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03442340791738382,
13
+ "grad_norm": 3.6819635678440528,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0121,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06884681583476764,
20
+ "grad_norm": 5.925274879357907,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.8959,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10327022375215146,
27
+ "grad_norm": 1.9452350190286591,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.877,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13769363166953527,
34
+ "grad_norm": 1.180696985048175,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8454,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1721170395869191,
41
+ "grad_norm": 0.9223333997999451,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8155,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20654044750430292,
48
+ "grad_norm": 0.9307430421223478,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7988,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.24096385542168675,
55
+ "grad_norm": 0.791390062841487,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7889,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.27538726333907054,
62
+ "grad_norm": 0.6218724507386446,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7806,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3098106712564544,
69
+ "grad_norm": 0.7264494941987614,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7705,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3442340791738382,
76
+ "grad_norm": 0.6924488359878446,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7613,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.37865748709122204,
83
+ "grad_norm": 0.8803235860035055,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.761,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.41308089500860584,
90
+ "grad_norm": 0.6841880149421407,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7555,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4475043029259897,
97
+ "grad_norm": 0.667216275591224,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7507,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.4819277108433735,
104
+ "grad_norm": 0.6640712451607944,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7474,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5163511187607573,
111
+ "grad_norm": 0.5645446586749623,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7452,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5507745266781411,
118
+ "grad_norm": 0.7052276498344197,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7461,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5851979345955249,
125
+ "grad_norm": 0.7026553647920556,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7467,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6196213425129088,
132
+ "grad_norm": 0.5956245872933223,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7483,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6540447504302926,
139
+ "grad_norm": 0.5945615019725103,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7424,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6884681583476764,
146
+ "grad_norm": 0.5926282356688969,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7393,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7228915662650602,
153
+ "grad_norm": 0.529261150364574,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.734,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7573149741824441,
160
+ "grad_norm": 0.70244337869977,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7344,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.7917383820998278,
167
+ "grad_norm": 0.5208460618800276,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7332,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8261617900172117,
174
+ "grad_norm": 0.6781034767797038,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7323,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8605851979345955,
181
+ "grad_norm": 0.6364816529741125,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7311,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8950086058519794,
188
+ "grad_norm": 0.6857634900258707,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.73,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9294320137693631,
195
+ "grad_norm": 0.7533537266440626,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7274,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.963855421686747,
202
+ "grad_norm": 0.668483865607749,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.7281,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9982788296041308,
209
+ "grad_norm": 0.640731101658078,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.73,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.9982788296041308,
216
+ "eval_loss": 0.7240723967552185,
217
+ "eval_runtime": 311.5856,
218
+ "eval_samples_per_second": 25.123,
219
+ "eval_steps_per_second": 0.395,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.0327022375215147,
224
+ "grad_norm": 0.8232801616508892,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.7164,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.0671256454388984,
231
+ "grad_norm": 0.6877231272007057,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6796,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.1015490533562822,
238
+ "grad_norm": 0.7867017260974334,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6731,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.1359724612736661,
245
+ "grad_norm": 0.6102991857765998,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6804,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.1703958691910499,
252
+ "grad_norm": 0.7250816197036796,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.676,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.2048192771084336,
259
+ "grad_norm": 0.6971293258638788,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6758,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.2392426850258176,
266
+ "grad_norm": 0.6980055976515607,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6812,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.2736660929432013,
273
+ "grad_norm": 0.6257924181521026,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6829,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.3080895008605853,
280
+ "grad_norm": 0.6620444223829324,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6787,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.342512908777969,
287
+ "grad_norm": 0.6019054885784155,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6793,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.3769363166953528,
294
+ "grad_norm": 0.6430051610733118,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6774,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.4113597246127367,
301
+ "grad_norm": 0.5807368932507306,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6812,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.4457831325301205,
308
+ "grad_norm": 0.6470925978408152,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6747,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.4802065404475044,
315
+ "grad_norm": 0.6423216146537339,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6764,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.5146299483648882,
322
+ "grad_norm": 0.5134608684735672,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6744,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.549053356282272,
329
+ "grad_norm": 0.5563124728753217,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6728,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.5834767641996557,
336
+ "grad_norm": 0.6269436233978866,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6761,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.6179001721170396,
343
+ "grad_norm": 0.589734978264397,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6792,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.6523235800344234,
350
+ "grad_norm": 0.6327759222361318,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6768,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.6867469879518073,
357
+ "grad_norm": 0.6962103362892431,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.677,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.721170395869191,
364
+ "grad_norm": 0.5760289071453567,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6799,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.7555938037865748,
371
+ "grad_norm": 0.6442600102377914,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6773,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.7900172117039586,
378
+ "grad_norm": 0.7715377748849698,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6761,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.8244406196213425,
385
+ "grad_norm": 0.5533000553027299,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6736,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.8588640275387265,
392
+ "grad_norm": 0.6543045883003663,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6724,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.8932874354561102,
399
+ "grad_norm": 0.7812179906299692,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6745,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.927710843373494,
406
+ "grad_norm": 0.7706494630311692,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6744,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.9621342512908777,
413
+ "grad_norm": 0.6182434646754749,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6755,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.9965576592082617,
420
+ "grad_norm": 0.6295557645635617,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6787,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 2.0,
427
+ "eval_loss": 0.7113586664199829,
428
+ "eval_runtime": 311.8588,
429
+ "eval_samples_per_second": 25.101,
430
+ "eval_steps_per_second": 0.394,
431
+ "step": 581
432
+ },
433
+ {
434
+ "epoch": 2.0309810671256456,
435
+ "grad_norm": 1.2061368930293643,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6659,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.0654044750430294,
442
+ "grad_norm": 1.3280429163631766,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6232,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.099827882960413,
449
+ "grad_norm": 0.8615634723401497,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6239,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.134251290877797,
456
+ "grad_norm": 0.7137137740055365,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6196,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.1686746987951806,
463
+ "grad_norm": 0.7012119673623688,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6257,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.2030981067125643,
470
+ "grad_norm": 0.7539553553577881,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6232,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.2375215146299485,
477
+ "grad_norm": 0.7635231238603634,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6203,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.2719449225473323,
484
+ "grad_norm": 0.6908410296367468,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6254,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.306368330464716,
491
+ "grad_norm": 0.6587745940287006,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6301,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.3407917383820998,
498
+ "grad_norm": 0.5798868468674587,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6279,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.3752151462994835,
505
+ "grad_norm": 0.8440728118550425,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6287,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.4096385542168672,
512
+ "grad_norm": 0.6066489275997706,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6295,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.4440619621342514,
519
+ "grad_norm": 0.7165812340817078,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6277,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.478485370051635,
526
+ "grad_norm": 0.6122168594678861,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6293,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.512908777969019,
533
+ "grad_norm": 0.81573767147419,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6287,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.5473321858864026,
540
+ "grad_norm": 0.5606648215554753,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6294,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.581755593803787,
547
+ "grad_norm": 0.6406975384981994,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6232,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.6161790017211706,
554
+ "grad_norm": 0.6856546267607884,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6291,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.6506024096385543,
561
+ "grad_norm": 0.6347450877099359,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6283,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.685025817555938,
568
+ "grad_norm": 0.6621950677045059,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6305,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.719449225473322,
575
+ "grad_norm": 0.6174426541448764,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6255,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.7538726333907055,
582
+ "grad_norm": 0.6772601640104119,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6314,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.7882960413080893,
589
+ "grad_norm": 0.5940690265376317,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.6261,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.8227194492254735,
596
+ "grad_norm": 0.5557807625472435,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.6266,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.857142857142857,
603
+ "grad_norm": 0.7023723168127282,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.6278,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.891566265060241,
610
+ "grad_norm": 0.5869122563169644,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.6272,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.9259896729776247,
617
+ "grad_norm": 0.6112033798118853,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.6304,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.960413080895009,
624
+ "grad_norm": 0.6445615202118182,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.631,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.9948364888123926,
631
+ "grad_norm": 0.6223406143063472,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.6305,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.9948364888123926,
638
+ "eval_loss": 0.7126539349555969,
639
+ "eval_runtime": 315.6621,
640
+ "eval_samples_per_second": 24.799,
641
+ "eval_steps_per_second": 0.39,
642
+ "step": 870
643
+ },
644
+ {
645
+ "epoch": 2.9948364888123926,
646
+ "step": 870,
647
+ "total_flos": 1457073023877120.0,
648
+ "train_loss": 0.6931865083760229,
649
+ "train_runtime": 51465.7493,
650
+ "train_samples_per_second": 8.669,
651
+ "train_steps_per_second": 0.017
652
+ }
653
+ ],
654
+ "logging_steps": 10,
655
+ "max_steps": 870,
656
+ "num_input_tokens_seen": 0,
657
+ "num_train_epochs": 3,
658
+ "save_steps": 500,
659
+ "stateful_callbacks": {
660
+ "TrainerControl": {
661
+ "args": {
662
+ "should_epoch_stop": false,
663
+ "should_evaluate": false,
664
+ "should_log": false,
665
+ "should_save": true,
666
+ "should_training_stop": true
667
+ },
668
+ "attributes": {}
669
+ }
670
+ },
671
+ "total_flos": 1457073023877120.0,
672
+ "train_batch_size": 8,
673
+ "trial_name": null,
674
+ "trial_params": null
675
+ }
training_eval_loss.png ADDED
training_loss.png ADDED