sedrickkeh commited on
Commit
bc0de42
·
verified ·
1 Parent(s): 05c312e

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_metamath_x.25
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_metamath_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: 0.7495
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_metamath_x.25
 
16
 
17
  # oh_v1.3_metamath_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_metamath_x.25 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7495
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961795606494745,
3
+ "eval_loss": 0.7494649887084961,
4
+ "eval_runtime": 279.2244,
5
+ "eval_samples_per_second": 25.259,
6
+ "eval_steps_per_second": 0.398,
7
+ "total_flos": 1311344783523840.0,
8
+ "train_loss": 0.7237713550090181,
9
+ "train_runtime": 46210.0208,
10
+ "train_samples_per_second": 8.699,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961795606494745,
3
+ "eval_loss": 0.7494649887084961,
4
+ "eval_runtime": 279.2244,
5
+ "eval_samples_per_second": 25.259,
6
+ "eval_steps_per_second": 0.398
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9961795606494745,
3
+ "total_flos": 1311344783523840.0,
4
+ "train_loss": 0.7237713550090181,
5
+ "train_runtime": 46210.0208,
6
+ "train_samples_per_second": 8.699,
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": 2.9961795606494745,
5
+ "eval_steps": 500,
6
+ "global_step": 783,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.038204393505253106,
13
+ "grad_norm": 17.106196027203886,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0699,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07640878701050621,
20
+ "grad_norm": 3.7575313843264073,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9412,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11461318051575932,
27
+ "grad_norm": 2.0783280143086302,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8972,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.15281757402101243,
34
+ "grad_norm": 1.419216051491444,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8682,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.19102196752626552,
41
+ "grad_norm": 1.5492013803153966,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8507,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.22922636103151864,
48
+ "grad_norm": 0.9979261775157234,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8317,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.26743075453677173,
55
+ "grad_norm": 1.1453499414283712,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8257,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.30563514804202485,
62
+ "grad_norm": 1.0657509981340374,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8136,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3438395415472779,
69
+ "grad_norm": 0.8154629296380118,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8012,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.38204393505253104,
76
+ "grad_norm": 0.7783174666894658,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7944,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.42024832855778416,
83
+ "grad_norm": 0.7557295182511866,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7976,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4584527220630373,
90
+ "grad_norm": 0.7419048503084669,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7838,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.49665711556829034,
97
+ "grad_norm": 0.6023078446753443,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7861,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5348615090735435,
104
+ "grad_norm": 0.8029384495653265,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7794,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5730659025787965,
111
+ "grad_norm": 0.8049936585803824,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7824,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.6112702960840497,
118
+ "grad_norm": 0.8903153692892993,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7716,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6494746895893028,
125
+ "grad_norm": 0.7481918362618383,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7781,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6876790830945558,
132
+ "grad_norm": 0.8571380886679489,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7728,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.725883476599809,
139
+ "grad_norm": 0.603577733589318,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7693,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7640878701050621,
146
+ "grad_norm": 0.6986000212250895,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7708,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.8022922636103151,
153
+ "grad_norm": 0.6654581267839026,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7686,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8404966571155683,
160
+ "grad_norm": 0.7161329148587753,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7639,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8787010506208214,
167
+ "grad_norm": 0.7291450225202621,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7653,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.9169054441260746,
174
+ "grad_norm": 0.7588585120562266,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7633,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9551098376313276,
181
+ "grad_norm": 0.8527681409489486,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.758,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9933142311365807,
188
+ "grad_norm": 0.5733961547084557,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7556,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.997134670487106,
195
+ "eval_loss": 0.7598350644111633,
196
+ "eval_runtime": 277.7141,
197
+ "eval_samples_per_second": 25.397,
198
+ "eval_steps_per_second": 0.4,
199
+ "step": 261
200
+ },
201
+ {
202
+ "epoch": 1.033906399235912,
203
+ "grad_norm": 0.8279780719142003,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.7812,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.0721107927411653,
210
+ "grad_norm": 0.8247306859370325,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.7055,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.1103151862464182,
217
+ "grad_norm": 0.6966889761138212,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.7083,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.1485195797516714,
224
+ "grad_norm": 0.7158212384271236,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.7028,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1867239732569246,
231
+ "grad_norm": 0.6513073930120158,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.7105,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.2249283667621778,
238
+ "grad_norm": 0.6782643522162839,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.7092,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2631327602674307,
245
+ "grad_norm": 0.7229522703779768,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.7027,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.3013371537726839,
252
+ "grad_norm": 0.686689277377695,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.7092,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.3395415472779368,
259
+ "grad_norm": 0.6686838666832164,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.7076,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.37774594078319,
266
+ "grad_norm": 0.8906041633095456,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.703,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.4159503342884432,
273
+ "grad_norm": 0.6554966723136705,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.7078,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.4541547277936964,
280
+ "grad_norm": 0.6044694699607192,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.7064,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4923591212989493,
287
+ "grad_norm": 0.6795649168516978,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.7042,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.5305635148042025,
294
+ "grad_norm": 0.6518471106071317,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.7055,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.5687679083094554,
301
+ "grad_norm": 0.656923516770704,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.707,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.6069723018147086,
308
+ "grad_norm": 0.6225351538335282,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.7045,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.6451766953199618,
315
+ "grad_norm": 0.777993155808027,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.7056,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.683381088825215,
322
+ "grad_norm": 0.6859522609411438,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.7047,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.7215854823304682,
329
+ "grad_norm": 0.6651740116728566,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.7004,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.759789875835721,
336
+ "grad_norm": 0.5969267067929888,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.7012,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.797994269340974,
343
+ "grad_norm": 0.613011364797191,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.7073,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.8361986628462272,
350
+ "grad_norm": 0.6207675725240294,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.7002,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.8744030563514804,
357
+ "grad_norm": 0.5957548029122114,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.7063,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.9126074498567336,
364
+ "grad_norm": 0.6972405923078006,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.7046,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.9508118433619868,
371
+ "grad_norm": 0.6246007349854923,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7074,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.9890162368672397,
378
+ "grad_norm": 0.6291588284508969,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6989,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9966571155682904,
385
+ "eval_loss": 0.7465963363647461,
386
+ "eval_runtime": 278.0536,
387
+ "eval_samples_per_second": 25.366,
388
+ "eval_steps_per_second": 0.399,
389
+ "step": 522
390
+ },
391
+ {
392
+ "epoch": 2.029608404966571,
393
+ "grad_norm": 0.9162417337081611,
394
+ "learning_rate": 5e-06,
395
+ "loss": 0.7192,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 2.067812798471824,
400
+ "grad_norm": 0.6666792440916017,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.6447,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.1060171919770774,
407
+ "grad_norm": 0.6320270044953581,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.6504,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.1442215854823305,
414
+ "grad_norm": 0.8407791173957067,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6486,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.1824259789875837,
421
+ "grad_norm": 0.9821964292842589,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6528,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.2206303724928365,
428
+ "grad_norm": 0.9530943320810575,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6536,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.2588347659980896,
435
+ "grad_norm": 0.7065407366963496,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6515,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.297039159503343,
442
+ "grad_norm": 0.9143814042284045,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6516,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.335243553008596,
449
+ "grad_norm": 1.0356120889247198,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6522,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.373447946513849,
456
+ "grad_norm": 0.5955479754526213,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6484,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.4116523400191023,
463
+ "grad_norm": 0.668667957683453,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6517,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.4498567335243555,
470
+ "grad_norm": 0.5916712868955213,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6492,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.4880611270296082,
477
+ "grad_norm": 0.7078011059499841,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6499,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.5262655205348614,
484
+ "grad_norm": 0.7113167536030103,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6491,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.5644699140401146,
491
+ "grad_norm": 0.7286729281959395,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6559,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.6026743075453678,
498
+ "grad_norm": 0.8393175922718014,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6537,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.640878701050621,
505
+ "grad_norm": 0.9635082597402534,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.645,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.6790830945558737,
512
+ "grad_norm": 0.6376260449080609,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6516,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.7172874880611273,
519
+ "grad_norm": 0.9042073773765085,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6538,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.75549188156638,
526
+ "grad_norm": 0.8795780646670239,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6537,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.793696275071633,
533
+ "grad_norm": 0.7101546769683508,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6507,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.8319006685768864,
540
+ "grad_norm": 0.6112049740364579,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6536,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.8701050620821396,
547
+ "grad_norm": 0.6240740305145582,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6525,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.9083094555873927,
554
+ "grad_norm": 0.6687610050145816,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6569,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.9465138490926455,
561
+ "grad_norm": 0.7981405552978358,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.655,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.9847182425978986,
568
+ "grad_norm": 0.6901040178181519,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6567,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.9961795606494745,
575
+ "eval_loss": 0.7494649887084961,
576
+ "eval_runtime": 280.3949,
577
+ "eval_samples_per_second": 25.154,
578
+ "eval_steps_per_second": 0.396,
579
+ "step": 783
580
+ },
581
+ {
582
+ "epoch": 2.9961795606494745,
583
+ "step": 783,
584
+ "total_flos": 1311344783523840.0,
585
+ "train_loss": 0.7237713550090181,
586
+ "train_runtime": 46210.0208,
587
+ "train_samples_per_second": 8.699,
588
+ "train_steps_per_second": 0.017
589
+ }
590
+ ],
591
+ "logging_steps": 10,
592
+ "max_steps": 783,
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": 1311344783523840.0,
609
+ "train_batch_size": 8,
610
+ "trial_name": null,
611
+ "trial_params": null
612
+ }
training_eval_loss.png ADDED
training_loss.png ADDED