sedrickkeh commited on
Commit
4a056c3
·
verified ·
1 Parent(s): ba86bc4

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_x4
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_camel_math_x4
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: 0.6915
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_x4
 
16
 
17
  # oh_v1.3_camel_math_x4
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_x4 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6915
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9976507439310884,
3
+ "eval_loss": 0.6914501786231995,
4
+ "eval_runtime": 343.183,
5
+ "eval_samples_per_second": 25.065,
6
+ "eval_steps_per_second": 0.393,
7
+ "total_flos": 1602801264230400.0,
8
+ "train_loss": 0.6732874076069958,
9
+ "train_runtime": 56787.3035,
10
+ "train_samples_per_second": 8.633,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9976507439310884,
3
+ "eval_loss": 0.6914501786231995,
4
+ "eval_runtime": 343.183,
5
+ "eval_samples_per_second": 25.065,
6
+ "eval_steps_per_second": 0.393
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9976507439310884,
3
+ "total_flos": 1602801264230400.0,
4
+ "train_loss": 0.6732874076069958,
5
+ "train_runtime": 56787.3035,
6
+ "train_samples_per_second": 8.633,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,731 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9976507439310884,
5
+ "eval_steps": 500,
6
+ "global_step": 957,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.031323414252153486,
13
+ "grad_norm": 2.8610078308107854,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.9785,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06264682850430697,
20
+ "grad_norm": 1.7702609085485501,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.8565,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.09397024275646046,
27
+ "grad_norm": 1.0245069679485275,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8274,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.12529365700861395,
34
+ "grad_norm": 1.3708437833993996,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.799,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.15661707126076743,
41
+ "grad_norm": 0.8356008055369265,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7847,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.18794048551292092,
48
+ "grad_norm": 1.0931171880514496,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7733,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2192638997650744,
55
+ "grad_norm": 0.8028201655311987,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7543,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2505873140172279,
62
+ "grad_norm": 0.7488845273909638,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7505,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.28191072826938135,
69
+ "grad_norm": 0.6273923877919437,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7414,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.31323414252153486,
76
+ "grad_norm": 0.5605687620675001,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.741,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.3445575567736883,
83
+ "grad_norm": 0.6510334014280172,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7386,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.37588097102584184,
90
+ "grad_norm": 0.6570705408467123,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7283,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4072043852779953,
97
+ "grad_norm": 0.6492497055594569,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7326,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.4385277995301488,
104
+ "grad_norm": 0.8036703292766153,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7239,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.46985121378230227,
111
+ "grad_norm": 0.5816796226058352,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7294,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5011746280344558,
118
+ "grad_norm": 0.6877992121274088,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7287,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5324980422866092,
125
+ "grad_norm": 0.7272574314246748,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7208,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.5638214565387627,
132
+ "grad_norm": 0.5709516023324598,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7194,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.5951448707909162,
139
+ "grad_norm": 0.5707557600894976,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7209,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6264682850430697,
146
+ "grad_norm": 0.6274568023357758,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.719,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.6577916992952232,
153
+ "grad_norm": 0.5482714368683154,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7155,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.6891151135473766,
160
+ "grad_norm": 0.5435355545098447,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7137,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.7204385277995301,
167
+ "grad_norm": 0.5549463909209981,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7145,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.7517619420516837,
174
+ "grad_norm": 0.5872929591126732,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7151,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.7830853563038371,
181
+ "grad_norm": 0.6595124362809732,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7145,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8144087705559906,
188
+ "grad_norm": 0.5459174781598405,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7174,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.845732184808144,
195
+ "grad_norm": 0.659643905818339,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7089,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.8770555990602976,
202
+ "grad_norm": 0.686424151578199,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.7113,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9083790133124511,
209
+ "grad_norm": 0.7152116087909246,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.7087,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.9397024275646045,
216
+ "grad_norm": 0.5755513442821608,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.7035,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.971025841816758,
223
+ "grad_norm": 0.49802238359887663,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.7101,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.9992169146436961,
230
+ "eval_loss": 0.7040486931800842,
231
+ "eval_runtime": 340.4664,
232
+ "eval_samples_per_second": 25.265,
233
+ "eval_steps_per_second": 0.397,
234
+ "step": 319
235
+ },
236
+ {
237
+ "epoch": 1.0023492560689116,
238
+ "grad_norm": 1.39557569608369,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.7543,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.033672670321065,
245
+ "grad_norm": 0.7048516666631669,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6574,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.0649960845732185,
252
+ "grad_norm": 0.7154001922458556,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6596,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.096319498825372,
259
+ "grad_norm": 0.8075870470182475,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6634,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.1276429130775254,
266
+ "grad_norm": 0.6958604595694347,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6588,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.1589663273296789,
273
+ "grad_norm": 0.6457902283198051,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6627,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.1902897415818323,
280
+ "grad_norm": 0.7060779787846581,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6623,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.221613155833986,
287
+ "grad_norm": 0.7178631366122828,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6595,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.2529365700861395,
294
+ "grad_norm": 0.7303589998987047,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6602,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.284259984338293,
301
+ "grad_norm": 0.614614426793837,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6623,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.3155833985904464,
308
+ "grad_norm": 0.5603517373438384,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6623,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.3469068128425998,
315
+ "grad_norm": 0.5439036905330217,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6624,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.3782302270947533,
322
+ "grad_norm": 0.5345730868641901,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6597,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.4095536413469067,
329
+ "grad_norm": 0.6120306566548636,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6601,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.4408770555990604,
336
+ "grad_norm": 0.7662777275751876,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6579,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.4722004698512139,
343
+ "grad_norm": 0.5861171635982056,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6617,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.5035238841033673,
350
+ "grad_norm": 0.550703096699278,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6575,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.5348472983555208,
357
+ "grad_norm": 0.8724124589877997,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6619,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.5661707126076743,
364
+ "grad_norm": 0.5466331808335562,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6582,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.5974941268598277,
371
+ "grad_norm": 0.5658899060560815,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6606,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.6288175411119812,
378
+ "grad_norm": 0.5924530569896768,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6591,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.6601409553641346,
385
+ "grad_norm": 0.6898298377267612,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6567,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.691464369616288,
392
+ "grad_norm": 0.5747921428491914,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6558,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.7227877838684416,
399
+ "grad_norm": 0.5318671363061512,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6552,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.754111198120595,
406
+ "grad_norm": 0.6440423203167484,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6569,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.7854346123727485,
413
+ "grad_norm": 0.6871334064396125,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6579,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.8167580266249022,
420
+ "grad_norm": 0.6410119301707079,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6586,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.8480814408770556,
427
+ "grad_norm": 0.5225004293954756,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6602,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.879404855129209,
434
+ "grad_norm": 0.5478451699362562,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6562,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.9107282693813625,
441
+ "grad_norm": 0.6535107349232507,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6598,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.9420516836335162,
448
+ "grad_norm": 0.5332260801259929,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6577,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.9733750978856697,
455
+ "grad_norm": 0.6351126336858737,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6588,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.9984338292873924,
462
+ "eval_loss": 0.6915597319602966,
463
+ "eval_runtime": 342.8543,
464
+ "eval_samples_per_second": 25.089,
465
+ "eval_steps_per_second": 0.394,
466
+ "step": 638
467
+ },
468
+ {
469
+ "epoch": 2.004698512137823,
470
+ "grad_norm": 0.9348794210283986,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.7005,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.0360219263899766,
477
+ "grad_norm": 0.6116207803075494,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.61,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.06734534064213,
484
+ "grad_norm": 0.7136818100838924,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6129,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.0986687548942835,
491
+ "grad_norm": 0.6893268088593335,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6073,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.129992169146437,
498
+ "grad_norm": 0.5885891280735964,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6069,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.1613155833985904,
505
+ "grad_norm": 0.5966990660667627,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6115,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.192638997650744,
512
+ "grad_norm": 0.5903227979936005,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6083,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.2239624119028973,
519
+ "grad_norm": 0.5378339870907247,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6055,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.255285826155051,
526
+ "grad_norm": 0.7262899779231057,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.612,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.2866092404072043,
533
+ "grad_norm": 0.5969529088102685,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6119,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.3179326546593577,
540
+ "grad_norm": 0.6265310864883772,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6113,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.349256068911511,
547
+ "grad_norm": 0.6715123614069597,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6111,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.3805794831636646,
554
+ "grad_norm": 0.5903854838476866,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6121,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.4119028974158185,
561
+ "grad_norm": 0.7108455834296159,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6159,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.443226311667972,
568
+ "grad_norm": 0.5396295194681806,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6142,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.4745497259201255,
575
+ "grad_norm": 0.6709263277652183,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6181,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.505873140172279,
582
+ "grad_norm": 0.6922212368293488,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6127,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.5371965544244324,
589
+ "grad_norm": 0.802266836685208,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.6192,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.568519968676586,
596
+ "grad_norm": 0.7055921712823672,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.6098,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.5998433829287393,
603
+ "grad_norm": 0.6549155076226189,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.6126,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.6311667971808927,
610
+ "grad_norm": 0.6145335107184124,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.618,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.662490211433046,
617
+ "grad_norm": 0.6520405733421761,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.6132,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.6938136256851997,
624
+ "grad_norm": 0.5955304451757282,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.6211,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.725137039937353,
631
+ "grad_norm": 0.6957752696961866,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.6072,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.7564604541895066,
638
+ "grad_norm": 0.7212196624619537,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.6181,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.78778386844166,
645
+ "grad_norm": 0.6362474481595267,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.6183,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.8191072826938135,
652
+ "grad_norm": 0.6043748136471383,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.6185,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.850430696945967,
659
+ "grad_norm": 0.6293339433347603,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.6113,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.881754111198121,
666
+ "grad_norm": 0.5487837401420806,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.613,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.913077525450274,
673
+ "grad_norm": 0.6366669947057394,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.6178,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.9444009397024278,
680
+ "grad_norm": 0.6539470297076938,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.6157,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.975724353954581,
687
+ "grad_norm": 0.7862259105525281,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.6176,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.9976507439310884,
694
+ "eval_loss": 0.6914501786231995,
695
+ "eval_runtime": 343.0486,
696
+ "eval_samples_per_second": 25.075,
697
+ "eval_steps_per_second": 0.394,
698
+ "step": 957
699
+ },
700
+ {
701
+ "epoch": 2.9976507439310884,
702
+ "step": 957,
703
+ "total_flos": 1602801264230400.0,
704
+ "train_loss": 0.6732874076069958,
705
+ "train_runtime": 56787.3035,
706
+ "train_samples_per_second": 8.633,
707
+ "train_steps_per_second": 0.017
708
+ }
709
+ ],
710
+ "logging_steps": 10,
711
+ "max_steps": 957,
712
+ "num_input_tokens_seen": 0,
713
+ "num_train_epochs": 3,
714
+ "save_steps": 500,
715
+ "stateful_callbacks": {
716
+ "TrainerControl": {
717
+ "args": {
718
+ "should_epoch_stop": false,
719
+ "should_evaluate": false,
720
+ "should_log": false,
721
+ "should_save": true,
722
+ "should_training_stop": true
723
+ },
724
+ "attributes": {}
725
+ }
726
+ },
727
+ "total_flos": 1602801264230400.0,
728
+ "train_batch_size": 8,
729
+ "trial_name": null,
730
+ "trial_params": null
731
+ }
training_eval_loss.png ADDED
training_loss.png ADDED