sedrickkeh commited on
Commit
e851674
·
verified ·
1 Parent(s): ed5743d

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_alpaca_x.25
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_alpaca_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: 0.7274
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_alpaca_x.25
 
16
 
17
  # oh_v1.3_alpaca_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_alpaca_x.25 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7274
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99209669920967,
3
+ "eval_loss": 0.7273504734039307,
4
+ "eval_runtime": 288.6407,
5
+ "eval_samples_per_second": 25.1,
6
+ "eval_steps_per_second": 0.395,
7
+ "total_flos": 1346520565678080.0,
8
+ "train_loss": 0.7017793898558735,
9
+ "train_runtime": 47601.6388,
10
+ "train_samples_per_second": 8.675,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99209669920967,
3
+ "eval_loss": 0.7273504734039307,
4
+ "eval_runtime": 288.6407,
5
+ "eval_samples_per_second": 25.1,
6
+ "eval_steps_per_second": 0.395
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99209669920967,
3
+ "total_flos": 1346520565678080.0,
4
+ "train_loss": 0.7017793898558735,
5
+ "train_runtime": 47601.6388,
6
+ "train_samples_per_second": 8.675,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,626 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.99209669920967,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.037192003719200374,
13
+ "grad_norm": 10.70026537944554,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0236,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07438400743840075,
20
+ "grad_norm": 2.4683708369251702,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9061,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11157601115760112,
27
+ "grad_norm": 1.557001339119401,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8674,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.1487680148768015,
34
+ "grad_norm": 0.9397524898555749,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8384,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.18596001859600186,
41
+ "grad_norm": 1.1936988926222905,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8231,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.22315202231520223,
48
+ "grad_norm": 1.435799706744866,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8033,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2603440260344026,
55
+ "grad_norm": 1.1073029578095623,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.792,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.297536029753603,
62
+ "grad_norm": 0.7590034814601881,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7831,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.33472803347280333,
69
+ "grad_norm": 0.7187163632098286,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7785,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3719200371920037,
76
+ "grad_norm": 0.8381967164711774,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7677,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.40911204091120407,
83
+ "grad_norm": 0.9379366153843277,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.769,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.44630404463040446,
90
+ "grad_norm": 1.022992740054695,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.767,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.48349604834960486,
97
+ "grad_norm": 0.6758807465967622,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7648,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5206880520688052,
104
+ "grad_norm": 0.6206586625414877,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7624,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5578800557880056,
111
+ "grad_norm": 0.7908504795288729,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7585,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.595072059507206,
118
+ "grad_norm": 0.6997124813442255,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7561,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6322640632264063,
125
+ "grad_norm": 0.9021517727581455,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7524,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6694560669456067,
132
+ "grad_norm": 1.0929713413971875,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7569,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.7066480706648071,
139
+ "grad_norm": 0.5949383799920382,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.748,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7438400743840075,
146
+ "grad_norm": 0.7114176678865975,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7457,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7810320781032078,
153
+ "grad_norm": 0.6511538389514762,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7485,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8182240818224081,
160
+ "grad_norm": 0.6169446521242461,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7452,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8554160855416085,
167
+ "grad_norm": 0.6679649201553077,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7413,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8926080892608089,
174
+ "grad_norm": 0.6367051553135998,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7421,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9298000929800093,
181
+ "grad_norm": 0.6538238961476153,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7432,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9669920966992097,
188
+ "grad_norm": 0.8807180489777804,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7459,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9967456996745699,
195
+ "eval_loss": 0.7386682629585266,
196
+ "eval_runtime": 288.2212,
197
+ "eval_samples_per_second": 25.137,
198
+ "eval_steps_per_second": 0.396,
199
+ "step": 268
200
+ },
201
+ {
202
+ "epoch": 1.00511390051139,
203
+ "grad_norm": 0.7939367182993704,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.7611,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.0423059042305904,
210
+ "grad_norm": 0.8873443926000695,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.6879,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.0794979079497908,
217
+ "grad_norm": 0.8271973959498057,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.6857,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.1166899116689912,
224
+ "grad_norm": 0.650424701317403,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6851,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1538819153881916,
231
+ "grad_norm": 0.6802876097167041,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6887,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.1910739191073918,
238
+ "grad_norm": 0.6411203090099377,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6861,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2282659228265922,
245
+ "grad_norm": 0.6005865715164875,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6841,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2654579265457926,
252
+ "grad_norm": 0.5935758121572628,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6888,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.302649930264993,
259
+ "grad_norm": 0.692663892802115,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6867,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.3398419339841934,
266
+ "grad_norm": 0.6681511034577128,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6867,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.3770339377033938,
273
+ "grad_norm": 0.7802593590884934,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6848,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.4142259414225942,
280
+ "grad_norm": 0.9804677340757696,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6893,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4514179451417946,
287
+ "grad_norm": 0.6847329774555626,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6886,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.488609948860995,
294
+ "grad_norm": 0.8352892154706931,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6859,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.5258019525801951,
301
+ "grad_norm": 0.5967270820719447,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6868,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.5629939562993957,
308
+ "grad_norm": 0.5880142959801617,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6842,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.600185960018596,
315
+ "grad_norm": 0.5635288435173463,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6801,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.6373779637377965,
322
+ "grad_norm": 0.6514598287968293,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6861,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.6745699674569967,
329
+ "grad_norm": 0.8211565671387909,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6826,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.711761971176197,
336
+ "grad_norm": 0.656234536726472,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6828,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.7489539748953975,
343
+ "grad_norm": 0.6424316411884232,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.686,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.786145978614598,
350
+ "grad_norm": 1.055200713989444,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6865,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.8233379823337983,
357
+ "grad_norm": 0.62784173351756,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6828,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.8605299860529985,
364
+ "grad_norm": 0.6942985618719518,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6822,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.897721989772199,
371
+ "grad_norm": 0.6606054547047716,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6903,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.9349139934913993,
378
+ "grad_norm": 0.6017670933672693,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6827,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9721059972105999,
385
+ "grad_norm": 0.6807163168349626,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6846,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.99814039981404,
392
+ "eval_loss": 0.7252578735351562,
393
+ "eval_runtime": 289.9595,
394
+ "eval_samples_per_second": 24.986,
395
+ "eval_steps_per_second": 0.393,
396
+ "step": 537
397
+ },
398
+ {
399
+ "epoch": 2.01022780102278,
400
+ "grad_norm": 1.162466060623287,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.6895,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.0474198047419803,
407
+ "grad_norm": 0.8408033292352894,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.633,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.084611808461181,
414
+ "grad_norm": 0.9210969340667359,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6306,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.121803812180381,
421
+ "grad_norm": 1.0327996873074714,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6268,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.1589958158995817,
428
+ "grad_norm": 0.7309858611795417,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6236,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.196187819618782,
435
+ "grad_norm": 0.797584262196217,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6347,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.2333798233379825,
442
+ "grad_norm": 0.5968988938337217,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6303,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.2705718270571826,
449
+ "grad_norm": 0.6433554089375944,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6397,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.3077638307763833,
456
+ "grad_norm": 0.6218944010086928,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6314,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.3449558344955834,
463
+ "grad_norm": 0.5763593732539121,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6333,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.3821478382147836,
470
+ "grad_norm": 0.7290595985655166,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.635,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.419339841933984,
477
+ "grad_norm": 0.6299706173541643,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6327,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.4565318456531844,
484
+ "grad_norm": 0.5979725097626455,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6325,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.493723849372385,
491
+ "grad_norm": 0.7200143941899763,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6304,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.530915853091585,
498
+ "grad_norm": 0.7049012156152652,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6291,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.568107856810786,
505
+ "grad_norm": 0.6965936516378921,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6326,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.605299860529986,
512
+ "grad_norm": 0.6586486248284427,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6359,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.6424918642491866,
519
+ "grad_norm": 0.6619077887920902,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6323,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.6796838679683868,
526
+ "grad_norm": 0.6839746749523397,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6361,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.716875871687587,
533
+ "grad_norm": 0.6080087714334472,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6354,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.7540678754067875,
540
+ "grad_norm": 0.6159664816628709,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6385,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.791259879125988,
547
+ "grad_norm": 0.6838698604764274,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6377,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.8284518828451883,
554
+ "grad_norm": 0.6428004205887895,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6379,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.8656438865643885,
561
+ "grad_norm": 0.5859321354937221,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.635,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.902835890283589,
568
+ "grad_norm": 0.5843229275997851,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6373,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.9400278940027893,
575
+ "grad_norm": 0.7374252361646211,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6363,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.97721989772199,
582
+ "grad_norm": 0.6415227611860442,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6343,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.99209669920967,
589
+ "eval_loss": 0.7273504734039307,
590
+ "eval_runtime": 288.8843,
591
+ "eval_samples_per_second": 25.079,
592
+ "eval_steps_per_second": 0.395,
593
+ "step": 804
594
+ },
595
+ {
596
+ "epoch": 2.99209669920967,
597
+ "step": 804,
598
+ "total_flos": 1346520565678080.0,
599
+ "train_loss": 0.7017793898558735,
600
+ "train_runtime": 47601.6388,
601
+ "train_samples_per_second": 8.675,
602
+ "train_steps_per_second": 0.017
603
+ }
604
+ ],
605
+ "logging_steps": 10,
606
+ "max_steps": 804,
607
+ "num_input_tokens_seen": 0,
608
+ "num_train_epochs": 3,
609
+ "save_steps": 500,
610
+ "stateful_callbacks": {
611
+ "TrainerControl": {
612
+ "args": {
613
+ "should_epoch_stop": false,
614
+ "should_evaluate": false,
615
+ "should_log": false,
616
+ "should_save": true,
617
+ "should_training_stop": true
618
+ },
619
+ "attributes": {}
620
+ }
621
+ },
622
+ "total_flos": 1346520565678080.0,
623
+ "train_batch_size": 8,
624
+ "trial_name": null,
625
+ "trial_params": null
626
+ }
training_eval_loss.png ADDED
training_loss.png ADDED