sedrickkeh commited on
Commit
feb5ea0
·
verified ·
1 Parent(s): 9553d24

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_x.125
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_camel_math_x.125
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: 0.7486
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_x.125
 
16
 
17
  # oh_v1.3_camel_math_x.125
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_x.125 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7486
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9971181556195967,
3
+ "eval_loss": 0.7485793232917786,
4
+ "eval_runtime": 277.9316,
5
+ "eval_samples_per_second": 25.233,
6
+ "eval_steps_per_second": 0.396,
7
+ "total_flos": 1306319671787520.0,
8
+ "train_loss": 0.7206086501097068,
9
+ "train_runtime": 45973.7379,
10
+ "train_samples_per_second": 8.694,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9971181556195967,
3
+ "eval_loss": 0.7485793232917786,
4
+ "eval_runtime": 277.9316,
5
+ "eval_samples_per_second": 25.233,
6
+ "eval_steps_per_second": 0.396
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9971181556195967,
3
+ "total_flos": 1306319671787520.0,
4
+ "train_loss": 0.7206086501097068,
5
+ "train_runtime": 45973.7379,
6
+ "train_samples_per_second": 8.694,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,612 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9971181556195967,
5
+ "eval_steps": 500,
6
+ "global_step": 780,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03842459173871278,
13
+ "grad_norm": 2.22598139805258,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0605,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07684918347742556,
20
+ "grad_norm": 1.8651908058801285,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9358,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11527377521613832,
27
+ "grad_norm": 2.6599993200524916,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.893,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.15369836695485112,
34
+ "grad_norm": 1.7240152968762026,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8656,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.19212295869356388,
41
+ "grad_norm": 1.3749810808043914,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.845,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.23054755043227665,
48
+ "grad_norm": 1.1007270333926593,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8299,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2689721421709894,
55
+ "grad_norm": 1.2050224496780755,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.818,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.30739673390970224,
62
+ "grad_norm": 0.9788138383899402,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8033,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.345821325648415,
69
+ "grad_norm": 0.884055914711954,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8036,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.38424591738712777,
76
+ "grad_norm": 0.8235015272280632,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7934,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.42267050912584053,
83
+ "grad_norm": 1.245984363361222,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7926,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4610951008645533,
90
+ "grad_norm": 0.8556601852472671,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7844,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.49951969260326606,
97
+ "grad_norm": 1.1413084645120115,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7801,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5379442843419788,
104
+ "grad_norm": 0.8043285660887262,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7784,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5763688760806917,
111
+ "grad_norm": 0.7459273515185546,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7741,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.6147934678194045,
118
+ "grad_norm": 0.8660117432164065,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7736,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6532180595581172,
125
+ "grad_norm": 1.0007814674866071,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7706,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.69164265129683,
132
+ "grad_norm": 0.7055795079240674,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7664,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.7300672430355427,
139
+ "grad_norm": 0.7838600424732732,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7698,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7684918347742555,
146
+ "grad_norm": 0.7583120615774692,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7641,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.8069164265129684,
153
+ "grad_norm": 0.5733684412033053,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7623,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8453410182516811,
160
+ "grad_norm": 0.859078978836711,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7594,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8837656099903939,
167
+ "grad_norm": 0.6923227057286715,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7619,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.9221902017291066,
174
+ "grad_norm": 0.8251505086096959,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7555,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9606147934678194,
181
+ "grad_norm": 0.7435533797370215,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7585,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9990393852065321,
188
+ "grad_norm": 0.7678197391666464,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7576,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9990393852065321,
195
+ "eval_loss": 0.7591712474822998,
196
+ "eval_runtime": 277.1989,
197
+ "eval_samples_per_second": 25.3,
198
+ "eval_steps_per_second": 0.397,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.037463976945245,
203
+ "grad_norm": 1.5561145218285635,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.768,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.0758885686839577,
210
+ "grad_norm": 1.1330094006549452,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.7048,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.1143131604226706,
217
+ "grad_norm": 1.1036306351344938,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.7049,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.1527377521613833,
224
+ "grad_norm": 0.8088529561657445,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.7065,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.191162343900096,
231
+ "grad_norm": 0.6453683425935199,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.7053,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.229586935638809,
238
+ "grad_norm": 0.7446769681200912,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.705,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2680115273775217,
245
+ "grad_norm": 0.6286087733342373,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.7034,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.3064361191162344,
252
+ "grad_norm": 0.7100549600622268,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.7042,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.344860710854947,
259
+ "grad_norm": 0.9359540512097944,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.7074,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.38328530259366,
266
+ "grad_norm": 0.8699027772413719,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.7029,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.4217098943323727,
273
+ "grad_norm": 0.7184467018616941,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.7049,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.4601344860710854,
280
+ "grad_norm": 0.707621532856516,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.7011,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4985590778097984,
287
+ "grad_norm": 0.6450672044350859,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.7033,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.536983669548511,
294
+ "grad_norm": 0.6206488333062592,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.7007,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.5754082612872238,
301
+ "grad_norm": 0.6551961537173275,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.7073,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.6138328530259365,
308
+ "grad_norm": 0.759327282861503,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.7014,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.6522574447646494,
315
+ "grad_norm": 0.6747434203983423,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.7026,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.6906820365033621,
322
+ "grad_norm": 0.7077879716432668,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.697,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.729106628242075,
329
+ "grad_norm": 0.6097521106522427,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.7006,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.7675312199807878,
336
+ "grad_norm": 0.6284752403489111,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6945,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.8059558117195005,
343
+ "grad_norm": 0.6322821309286489,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.7004,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.8443804034582132,
350
+ "grad_norm": 0.6503834070635269,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6978,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.882804995196926,
357
+ "grad_norm": 0.5928523527781089,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6965,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.9212295869356388,
364
+ "grad_norm": 0.7766248894494607,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6983,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.9596541786743515,
371
+ "grad_norm": 0.6619286278573577,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7017,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.9980787704130645,
378
+ "grad_norm": 0.6972596313365015,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.7051,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9980787704130645,
385
+ "eval_loss": 0.7455958724021912,
386
+ "eval_runtime": 276.3849,
387
+ "eval_samples_per_second": 25.374,
388
+ "eval_steps_per_second": 0.398,
389
+ "step": 520
390
+ },
391
+ {
392
+ "epoch": 2.036503362151777,
393
+ "grad_norm": 0.90057408209001,
394
+ "learning_rate": 5e-06,
395
+ "loss": 0.703,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 2.07492795389049,
400
+ "grad_norm": 0.5876798686485762,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.6459,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.1133525456292026,
407
+ "grad_norm": 0.6750213227294546,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.6429,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.1517771373679153,
414
+ "grad_norm": 0.6562193769008317,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.647,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.1902017291066285,
421
+ "grad_norm": 1.0106178235163223,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.647,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.228626320845341,
428
+ "grad_norm": 1.203791734016265,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6464,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.267050912584054,
435
+ "grad_norm": 1.072833126484535,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6436,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.3054755043227666,
442
+ "grad_norm": 0.7265275190167136,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6496,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.3439000960614793,
449
+ "grad_norm": 0.7159981148293034,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6488,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.382324687800192,
456
+ "grad_norm": 0.7499566009343647,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6471,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.4207492795389047,
463
+ "grad_norm": 0.7298967563003717,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6484,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.459173871277618,
470
+ "grad_norm": 0.7953731123916896,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6457,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.4975984630163306,
477
+ "grad_norm": 0.7193497283697384,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6456,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.5360230547550433,
484
+ "grad_norm": 0.6304268096938748,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6538,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.574447646493756,
491
+ "grad_norm": 0.6119037125847125,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6511,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.6128722382324687,
498
+ "grad_norm": 0.668738855127415,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6497,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.6512968299711814,
505
+ "grad_norm": 0.6759770116611106,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6532,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.689721421709894,
512
+ "grad_norm": 0.7216343244870027,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6504,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.7281460134486073,
519
+ "grad_norm": 0.6238981674987125,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6509,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.76657060518732,
526
+ "grad_norm": 0.8189531719324571,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6512,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.8049951969260327,
533
+ "grad_norm": 0.641751150175285,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6535,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.8434197886647454,
540
+ "grad_norm": 0.8091455165748344,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6513,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.881844380403458,
547
+ "grad_norm": 0.6798414752987015,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6496,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.920268972142171,
554
+ "grad_norm": 0.8078397653599894,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6505,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.9586935638808836,
561
+ "grad_norm": 0.7023876525964049,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6511,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.9971181556195967,
568
+ "grad_norm": 0.6381184685536545,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6472,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.9971181556195967,
575
+ "eval_loss": 0.7485793232917786,
576
+ "eval_runtime": 276.3503,
577
+ "eval_samples_per_second": 25.377,
578
+ "eval_steps_per_second": 0.398,
579
+ "step": 780
580
+ },
581
+ {
582
+ "epoch": 2.9971181556195967,
583
+ "step": 780,
584
+ "total_flos": 1306319671787520.0,
585
+ "train_loss": 0.7206086501097068,
586
+ "train_runtime": 45973.7379,
587
+ "train_samples_per_second": 8.694,
588
+ "train_steps_per_second": 0.017
589
+ }
590
+ ],
591
+ "logging_steps": 10,
592
+ "max_steps": 780,
593
+ "num_input_tokens_seen": 0,
594
+ "num_train_epochs": 3,
595
+ "save_steps": 500,
596
+ "stateful_callbacks": {
597
+ "TrainerControl": {
598
+ "args": {
599
+ "should_epoch_stop": false,
600
+ "should_evaluate": false,
601
+ "should_log": false,
602
+ "should_save": true,
603
+ "should_training_stop": true
604
+ },
605
+ "attributes": {}
606
+ }
607
+ },
608
+ "total_flos": 1306319671787520.0,
609
+ "train_batch_size": 8,
610
+ "trial_name": null,
611
+ "trial_params": null
612
+ }
training_eval_loss.png ADDED
training_loss.png ADDED