sedrickkeh commited on
Commit
1415838
·
verified ·
1 Parent(s): 6f357d6

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_airoboros_x2
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_airoboros_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: 0.7277
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_airoboros_x2
 
16
 
17
  # oh_v1.3_airoboros_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_airoboros_x2 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7277
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9918991899189917,
3
+ "eval_loss": 0.7277409434318542,
4
+ "eval_runtime": 295.6731,
5
+ "eval_samples_per_second": 25.315,
6
+ "eval_steps_per_second": 0.396,
7
+ "total_flos": 1391746571304960.0,
8
+ "train_loss": 0.7029923594385278,
9
+ "train_runtime": 48819.4117,
10
+ "train_samples_per_second": 8.738,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9918991899189917,
3
+ "eval_loss": 0.7277409434318542,
4
+ "eval_runtime": 295.6731,
5
+ "eval_samples_per_second": 25.315,
6
+ "eval_steps_per_second": 0.396
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9918991899189917,
3
+ "total_flos": 1391746571304960.0,
4
+ "train_loss": 0.7029923594385278,
5
+ "train_runtime": 48819.4117,
6
+ "train_samples_per_second": 8.738,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,647 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9918991899189917,
5
+ "eval_steps": 500,
6
+ "global_step": 831,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.036003600360036005,
13
+ "grad_norm": 8.28188267008514,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0366,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07200720072007201,
20
+ "grad_norm": 2.372440318983394,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.911,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10801080108010801,
27
+ "grad_norm": 1.5430691151708913,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8737,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.14401440144014402,
34
+ "grad_norm": 1.6852866024979738,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8448,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.18001800180018002,
41
+ "grad_norm": 1.0422319477358,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.825,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.21602160216021601,
48
+ "grad_norm": 0.9965056562001428,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8107,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.252025202520252,
55
+ "grad_norm": 0.7739884302751978,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7958,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.28802880288028804,
62
+ "grad_norm": 1.1803788120317176,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7931,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.324032403240324,
69
+ "grad_norm": 1.0324340981283762,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7803,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.36003600360036003,
76
+ "grad_norm": 0.9575288046763553,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7766,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.39603960396039606,
83
+ "grad_norm": 0.8374754661300629,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7723,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.43204320432043203,
90
+ "grad_norm": 0.7907545033736981,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7647,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.46804680468046805,
97
+ "grad_norm": 0.7676769317854443,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7671,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.504050405040504,
104
+ "grad_norm": 0.6051545961732036,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7621,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.54005400540054,
111
+ "grad_norm": 0.6744258472614542,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7577,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5760576057605761,
118
+ "grad_norm": 0.7199869824208848,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7576,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6120612061206121,
125
+ "grad_norm": 0.8152068316855611,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7546,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.648064806480648,
132
+ "grad_norm": 0.6341559903827244,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.756,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.684068406840684,
139
+ "grad_norm": 0.6367964073514584,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.753,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7200720072007201,
146
+ "grad_norm": 0.647151007125146,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7568,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7560756075607561,
153
+ "grad_norm": 0.7248014312732076,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7512,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7920792079207921,
160
+ "grad_norm": 0.7677811996827786,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7455,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.828082808280828,
167
+ "grad_norm": 0.6716581315266134,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7442,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8640864086408641,
174
+ "grad_norm": 0.6700748281170444,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7463,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9000900090009001,
181
+ "grad_norm": 0.7119873555561343,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7433,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9360936093609361,
188
+ "grad_norm": 0.7505227904025245,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7417,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9720972097209721,
195
+ "grad_norm": 0.6278240730412481,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7392,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9972997299729973,
202
+ "eval_loss": 0.7396969199180603,
203
+ "eval_runtime": 292.6851,
204
+ "eval_samples_per_second": 25.574,
205
+ "eval_steps_per_second": 0.4,
206
+ "step": 277
207
+ },
208
+ {
209
+ "epoch": 1.008100810081008,
210
+ "grad_norm": 1.160799237623972,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.7435,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.0441044104410442,
217
+ "grad_norm": 0.8183376727189909,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.6915,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.08010801080108,
224
+ "grad_norm": 0.8424246758574473,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6946,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.116111611161116,
231
+ "grad_norm": 0.7487195203197069,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6902,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.1521152115211521,
238
+ "grad_norm": 0.7322920833129869,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6898,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.188118811881188,
245
+ "grad_norm": 0.9645673518101977,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6853,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2241224122412242,
252
+ "grad_norm": 1.4283577735373754,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6863,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.2601260126012601,
259
+ "grad_norm": 1.0313433086608226,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.689,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.296129612961296,
266
+ "grad_norm": 0.6108529584385496,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6872,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.3321332133213322,
273
+ "grad_norm": 0.5789421153850809,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6815,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.368136813681368,
280
+ "grad_norm": 0.62526363928803,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6871,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4041404140414042,
287
+ "grad_norm": 0.6010956062715849,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6809,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.4401440144014401,
294
+ "grad_norm": 0.7964635599244039,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6885,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.476147614761476,
301
+ "grad_norm": 0.5804300574827144,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6851,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.5121512151215122,
308
+ "grad_norm": 0.5856848362882421,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6872,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.5481548154815483,
315
+ "grad_norm": 0.6958357748276202,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6872,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.5841584158415842,
322
+ "grad_norm": 0.6768954740097681,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6816,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.6201620162016201,
329
+ "grad_norm": 0.6656001302473941,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6852,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.656165616561656,
336
+ "grad_norm": 0.5847297445098926,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6837,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.6921692169216922,
343
+ "grad_norm": 0.6677237827833459,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6828,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.7281728172817283,
350
+ "grad_norm": 0.6717288073606101,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6892,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.7641764176417642,
357
+ "grad_norm": 0.6026508515544339,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6895,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.8001800180018002,
364
+ "grad_norm": 0.7348397512725225,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6888,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.836183618361836,
371
+ "grad_norm": 0.6767034208815822,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6822,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.8721872187218722,
378
+ "grad_norm": 0.5868328971723439,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6856,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9081908190819084,
385
+ "grad_norm": 0.6657122165386851,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6858,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.9441944194419443,
392
+ "grad_norm": 0.6843562239717784,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6854,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.9801980198019802,
399
+ "grad_norm": 0.6325820368205368,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6894,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.9981998199819984,
406
+ "eval_loss": 0.7263253331184387,
407
+ "eval_runtime": 294.6365,
408
+ "eval_samples_per_second": 25.404,
409
+ "eval_steps_per_second": 0.397,
410
+ "step": 555
411
+ },
412
+ {
413
+ "epoch": 2.016201620162016,
414
+ "grad_norm": 0.8901113520582664,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6805,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.052205220522052,
421
+ "grad_norm": 0.8312586311675406,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6302,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.0882088208820884,
428
+ "grad_norm": 0.645523505968572,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6315,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.1242124212421243,
435
+ "grad_norm": 0.6812801702191339,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6301,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.16021602160216,
442
+ "grad_norm": 0.6483786618034394,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6298,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.196219621962196,
449
+ "grad_norm": 0.6784530791335628,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6354,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.232223222322232,
456
+ "grad_norm": 0.60627028648818,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6319,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.2682268226822684,
463
+ "grad_norm": 0.6121470761934804,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6336,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.3042304230423043,
470
+ "grad_norm": 0.7236081633441965,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6345,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.34023402340234,
477
+ "grad_norm": 0.8548869591277164,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6363,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.376237623762376,
484
+ "grad_norm": 0.647183532105941,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6313,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.412241224122412,
491
+ "grad_norm": 0.6087053644736625,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6357,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.4482448244824484,
498
+ "grad_norm": 0.7533233767115554,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6383,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.4842484248424843,
505
+ "grad_norm": 0.8219213281281937,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6376,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.5202520252025202,
512
+ "grad_norm": 0.5918279562239513,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6358,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.556255625562556,
519
+ "grad_norm": 0.6812649937783365,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6346,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.592259225922592,
526
+ "grad_norm": 0.7062046537729157,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6341,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.6282628262826284,
533
+ "grad_norm": 0.6513878255971934,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6345,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.6642664266426643,
540
+ "grad_norm": 0.6543385256924704,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6346,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.7002700270027002,
547
+ "grad_norm": 0.737112200862458,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6319,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.736273627362736,
554
+ "grad_norm": 0.7994135143651142,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.636,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.772277227722772,
561
+ "grad_norm": 0.6219351198221807,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6426,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.8082808280828084,
568
+ "grad_norm": 0.7158062619534662,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.632,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.8442844284428443,
575
+ "grad_norm": 0.5601405956877966,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6349,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.8802880288028803,
582
+ "grad_norm": 0.5993882826107069,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6382,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.916291629162916,
589
+ "grad_norm": 0.5557179063729003,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.6362,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.952295229522952,
596
+ "grad_norm": 0.5645061472428777,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.6357,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.9882988298829884,
603
+ "grad_norm": 0.6301929405752535,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.6329,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.9918991899189917,
610
+ "eval_loss": 0.7277409434318542,
611
+ "eval_runtime": 293.9341,
612
+ "eval_samples_per_second": 25.465,
613
+ "eval_steps_per_second": 0.398,
614
+ "step": 831
615
+ },
616
+ {
617
+ "epoch": 2.9918991899189917,
618
+ "step": 831,
619
+ "total_flos": 1391746571304960.0,
620
+ "train_loss": 0.7029923594385278,
621
+ "train_runtime": 48819.4117,
622
+ "train_samples_per_second": 8.738,
623
+ "train_steps_per_second": 0.017
624
+ }
625
+ ],
626
+ "logging_steps": 10,
627
+ "max_steps": 831,
628
+ "num_input_tokens_seen": 0,
629
+ "num_train_epochs": 3,
630
+ "save_steps": 500,
631
+ "stateful_callbacks": {
632
+ "TrainerControl": {
633
+ "args": {
634
+ "should_epoch_stop": false,
635
+ "should_evaluate": false,
636
+ "should_log": false,
637
+ "should_save": true,
638
+ "should_training_stop": true
639
+ },
640
+ "attributes": {}
641
+ }
642
+ },
643
+ "total_flos": 1391746571304960.0,
644
+ "train_batch_size": 8,
645
+ "trial_name": null,
646
+ "trial_params": null
647
+ }
training_eval_loss.png ADDED
training_loss.png ADDED