sedrickkeh commited on
Commit
914fd17
·
verified ·
1 Parent(s): 6990cb2

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.25
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_camel_math_x.25
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: 0.7211
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.25
 
16
 
17
  # oh_v1.3_camel_math_x.25
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.25 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7211
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.995899772209567,
3
+ "eval_loss": 0.7211272120475769,
4
+ "eval_runtime": 291.637,
5
+ "eval_samples_per_second": 25.347,
6
+ "eval_steps_per_second": 0.398,
7
+ "total_flos": 1376671236096000.0,
8
+ "train_loss": 0.6964337152866261,
9
+ "train_runtime": 48380.1477,
10
+ "train_samples_per_second": 8.709,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.995899772209567,
3
+ "eval_loss": 0.7211272120475769,
4
+ "eval_runtime": 291.637,
5
+ "eval_samples_per_second": 25.347,
6
+ "eval_steps_per_second": 0.398
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.995899772209567,
3
+ "total_flos": 1376671236096000.0,
4
+ "train_loss": 0.6964337152866261,
5
+ "train_runtime": 48380.1477,
6
+ "train_samples_per_second": 8.709,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,640 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.995899772209567,
5
+ "eval_steps": 500,
6
+ "global_step": 822,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03644646924829157,
13
+ "grad_norm": 13.273536409408566,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0215,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07289293849658314,
20
+ "grad_norm": 2.0256934340222124,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.901,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10933940774487472,
27
+ "grad_norm": 1.1110745496419128,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8577,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.14578587699316628,
34
+ "grad_norm": 1.2500399664289437,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8319,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.18223234624145787,
41
+ "grad_norm": 0.993614371192878,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8081,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.21867881548974943,
48
+ "grad_norm": 0.97363008151794,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7963,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.255125284738041,
55
+ "grad_norm": 0.9129099469883597,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7888,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.29157175398633256,
62
+ "grad_norm": 0.9344193654869811,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7758,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.32801822323462415,
69
+ "grad_norm": 1.0188210165751896,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.775,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.36446469248291574,
76
+ "grad_norm": 0.9232347440747942,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7692,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.4009111617312073,
83
+ "grad_norm": 0.6783140292643164,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7621,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.43735763097949887,
90
+ "grad_norm": 0.6184031681315292,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7556,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.47380410022779046,
97
+ "grad_norm": 0.5469349607429109,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7551,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.510250569476082,
104
+ "grad_norm": 0.8877445271536203,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7554,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5466970387243736,
111
+ "grad_norm": 1.0291306012367956,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7495,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5831435079726651,
118
+ "grad_norm": 0.6607692936776239,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7459,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6195899772209568,
125
+ "grad_norm": 0.6336927673267501,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.748,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6560364464692483,
132
+ "grad_norm": 0.8944901762240539,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7452,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6924829157175398,
139
+ "grad_norm": 0.8843897330408937,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7445,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7289293849658315,
146
+ "grad_norm": 0.6972008986400734,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7385,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.765375854214123,
153
+ "grad_norm": 0.5894622066220608,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7375,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8018223234624146,
160
+ "grad_norm": 0.5755055010916849,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7366,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8382687927107062,
167
+ "grad_norm": 0.6956357933104967,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7418,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8747152619589977,
174
+ "grad_norm": 0.7222014717098794,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7289,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9111617312072893,
181
+ "grad_norm": 0.6509301599056833,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7353,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9476082004555809,
188
+ "grad_norm": 0.5946415096003963,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.739,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9840546697038725,
195
+ "grad_norm": 0.6399983053851734,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7315,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9986332574031891,
202
+ "eval_loss": 0.7315455079078674,
203
+ "eval_runtime": 290.5947,
204
+ "eval_samples_per_second": 25.437,
205
+ "eval_steps_per_second": 0.399,
206
+ "step": 274
207
+ },
208
+ {
209
+ "epoch": 1.020501138952164,
210
+ "grad_norm": 0.8395093526707935,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.747,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.0569476082004556,
217
+ "grad_norm": 0.9199729633560787,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.6787,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.0933940774487472,
224
+ "grad_norm": 0.6628677057491944,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6791,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1298405466970387,
231
+ "grad_norm": 0.6614989831751948,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6854,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.1662870159453302,
238
+ "grad_norm": 0.6964522514874895,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6763,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2027334851936218,
245
+ "grad_norm": 0.7090306269606215,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6753,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2391799544419135,
252
+ "grad_norm": 0.648532712130652,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.68,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.275626423690205,
259
+ "grad_norm": 0.7822954196339824,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6817,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.3120728929384966,
266
+ "grad_norm": 0.6766423459315555,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6803,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.3485193621867881,
273
+ "grad_norm": 0.7731309625470634,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6788,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.3849658314350797,
280
+ "grad_norm": 0.6229285700860081,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6856,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4214123006833712,
287
+ "grad_norm": 0.6927410350677501,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6808,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.4578587699316627,
294
+ "grad_norm": 0.834486739783265,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6772,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.4943052391799545,
301
+ "grad_norm": 0.7099676513539387,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6803,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.530751708428246,
308
+ "grad_norm": 0.6104516289365347,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.683,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.5671981776765376,
315
+ "grad_norm": 0.5971848121166693,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6787,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.603644646924829,
322
+ "grad_norm": 0.6649414637192727,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6849,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.6400911161731209,
329
+ "grad_norm": 0.7320907085872882,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6817,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.6765375854214124,
336
+ "grad_norm": 0.5705453457499549,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6836,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.712984054669704,
343
+ "grad_norm": 0.6288020854363963,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6788,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.7494305239179955,
350
+ "grad_norm": 0.5726327402033801,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6808,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.785876993166287,
357
+ "grad_norm": 0.5173548522448698,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6799,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.8223234624145785,
364
+ "grad_norm": 0.5790339638087626,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6747,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.85876993166287,
371
+ "grad_norm": 0.6584239869836397,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.677,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.8952164009111616,
378
+ "grad_norm": 0.5311060458966043,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6854,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9316628701594531,
385
+ "grad_norm": 0.6512560331845895,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6784,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.968109339407745,
392
+ "grad_norm": 0.584794911589519,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6805,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.9972665148063782,
399
+ "eval_loss": 0.7187947630882263,
400
+ "eval_runtime": 291.938,
401
+ "eval_samples_per_second": 25.32,
402
+ "eval_steps_per_second": 0.397,
403
+ "step": 548
404
+ },
405
+ {
406
+ "epoch": 2.0045558086560367,
407
+ "grad_norm": 0.885264185792607,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.7193,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.041002277904328,
414
+ "grad_norm": 0.7654881044126012,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6233,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.0774487471526197,
421
+ "grad_norm": 0.6151945001911823,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6283,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.1138952164009113,
428
+ "grad_norm": 0.8374365216828517,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6207,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.150341685649203,
435
+ "grad_norm": 0.7031485699411321,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6244,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.1867881548974943,
442
+ "grad_norm": 0.8633299586157721,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6258,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.223234624145786,
449
+ "grad_norm": 0.7458455143129973,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.628,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.2596810933940774,
456
+ "grad_norm": 1.0109682737601884,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6264,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.296127562642369,
463
+ "grad_norm": 0.6211087319945944,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6242,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.3325740318906605,
470
+ "grad_norm": 0.7036393621519607,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6305,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.369020501138952,
477
+ "grad_norm": 0.6058323256112293,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6297,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.4054669703872436,
484
+ "grad_norm": 0.6608686938446593,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.631,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.4419134396355355,
491
+ "grad_norm": 0.6199043838308076,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6264,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.478359908883827,
498
+ "grad_norm": 0.607673754805363,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6266,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.5148063781321186,
505
+ "grad_norm": 0.9277091135129097,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6263,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.55125284738041,
512
+ "grad_norm": 0.9381891238069503,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6317,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.5876993166287017,
519
+ "grad_norm": 0.6592786383334494,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6264,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.624145785876993,
526
+ "grad_norm": 0.7421181566721138,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6295,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.6605922551252847,
533
+ "grad_norm": 0.6781081672896357,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6273,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.6970387243735763,
540
+ "grad_norm": 0.609137054982541,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6328,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.733485193621868,
547
+ "grad_norm": 0.6919361244155826,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6333,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.7699316628701594,
554
+ "grad_norm": 0.6379259386020866,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6306,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.806378132118451,
561
+ "grad_norm": 0.6035608731746878,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6338,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.8428246013667424,
568
+ "grad_norm": 0.7325417971133363,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6352,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.879271070615034,
575
+ "grad_norm": 0.8532590605538493,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6284,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.9157175398633255,
582
+ "grad_norm": 0.6185281977585761,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6306,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.9521640091116175,
589
+ "grad_norm": 0.6806046770942457,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.6402,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.988610478359909,
596
+ "grad_norm": 0.6802410015239903,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.6348,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.995899772209567,
603
+ "eval_loss": 0.7211272120475769,
604
+ "eval_runtime": 291.822,
605
+ "eval_samples_per_second": 25.331,
606
+ "eval_steps_per_second": 0.398,
607
+ "step": 822
608
+ },
609
+ {
610
+ "epoch": 2.995899772209567,
611
+ "step": 822,
612
+ "total_flos": 1376671236096000.0,
613
+ "train_loss": 0.6964337152866261,
614
+ "train_runtime": 48380.1477,
615
+ "train_samples_per_second": 8.709,
616
+ "train_steps_per_second": 0.017
617
+ }
618
+ ],
619
+ "logging_steps": 10,
620
+ "max_steps": 822,
621
+ "num_input_tokens_seen": 0,
622
+ "num_train_epochs": 3,
623
+ "save_steps": 500,
624
+ "stateful_callbacks": {
625
+ "TrainerControl": {
626
+ "args": {
627
+ "should_epoch_stop": false,
628
+ "should_evaluate": false,
629
+ "should_log": false,
630
+ "should_save": true,
631
+ "should_training_stop": true
632
+ },
633
+ "attributes": {}
634
+ }
635
+ },
636
+ "total_flos": 1376671236096000.0,
637
+ "train_batch_size": 8,
638
+ "trial_name": null,
639
+ "trial_params": null
640
+ }
training_eval_loss.png ADDED
training_loss.png ADDED