sedrickkeh commited on
Commit
fb54816
·
verified ·
1 Parent(s): 1e3de15

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_teknium_scaling_down_random_0.8
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_teknium_scaling_down_random_0.8
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: 0.6006
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_teknium_scaling_down_random_0.8
 
16
 
17
  # oh_teknium_scaling_down_random_0.8
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_teknium_scaling_down_random_0.8 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6006
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.6005940437316895,
4
+ "eval_runtime": 275.223,
5
+ "eval_samples_per_second": 25.158,
6
+ "eval_steps_per_second": 0.396,
7
+ "total_flos": 1291244336578560.0,
8
+ "train_loss": 0.5620605509955287,
9
+ "train_runtime": 45702.4745,
10
+ "train_samples_per_second": 8.636,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.6005940437316895,
4
+ "eval_runtime": 275.223,
5
+ "eval_samples_per_second": 25.158,
6
+ "eval_steps_per_second": 0.396
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1291244336578560.0,
4
+ "train_loss": 0.5620605509955287,
5
+ "train_runtime": 45702.4745,
6
+ "train_samples_per_second": 8.636,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,605 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 771,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.038910505836575876,
13
+ "grad_norm": 1.1950826608910594,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7894,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07782101167315175,
20
+ "grad_norm": 0.8641628238228234,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7077,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11673151750972763,
27
+ "grad_norm": 1.0850249051640393,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6773,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.1556420233463035,
34
+ "grad_norm": 2.1113594635780544,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6672,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.19455252918287938,
41
+ "grad_norm": 2.7266567559510855,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.655,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.23346303501945526,
48
+ "grad_norm": 0.8866071545434335,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.646,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2723735408560311,
55
+ "grad_norm": 1.0279911167206606,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.6403,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.311284046692607,
62
+ "grad_norm": 1.2351298423408894,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6418,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.35019455252918286,
69
+ "grad_norm": 1.4010637045179566,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6327,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.38910505836575876,
76
+ "grad_norm": 0.8292028754750206,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6193,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.4280155642023346,
83
+ "grad_norm": 1.0764429621104903,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6207,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4669260700389105,
90
+ "grad_norm": 0.9459675747674458,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6163,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.5058365758754864,
97
+ "grad_norm": 0.5625210449909341,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6274,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5447470817120622,
104
+ "grad_norm": 0.5592680038544479,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6072,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5836575875486382,
111
+ "grad_norm": 0.9284204912138712,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6133,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.622568093385214,
118
+ "grad_norm": 0.5401038269116542,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6082,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6614785992217899,
125
+ "grad_norm": 0.6501354489369745,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.623,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.7003891050583657,
132
+ "grad_norm": 0.4374034361305582,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6028,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.7392996108949417,
139
+ "grad_norm": 0.48237196565070833,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6084,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7782101167315175,
146
+ "grad_norm": 0.6671847308065324,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6084,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.8171206225680934,
153
+ "grad_norm": 0.492851346406084,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6115,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8560311284046692,
160
+ "grad_norm": 0.5561699128946762,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6084,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8949416342412452,
167
+ "grad_norm": 0.523790379318423,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6074,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.933852140077821,
174
+ "grad_norm": 0.4858980422996836,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.5988,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9727626459143969,
181
+ "grad_norm": 0.614521306119893,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.5983,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "eval_loss": 0.6058223843574524,
189
+ "eval_runtime": 275.8969,
190
+ "eval_samples_per_second": 25.096,
191
+ "eval_steps_per_second": 0.395,
192
+ "step": 257
193
+ },
194
+ {
195
+ "epoch": 1.0116731517509727,
196
+ "grad_norm": 0.7818180596091272,
197
+ "learning_rate": 5e-06,
198
+ "loss": 0.5823,
199
+ "step": 260
200
+ },
201
+ {
202
+ "epoch": 1.0505836575875487,
203
+ "grad_norm": 0.694447527091343,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.5545,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.0894941634241244,
210
+ "grad_norm": 0.9129706616389401,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.5519,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.1284046692607004,
217
+ "grad_norm": 0.5744956834175966,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.5524,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.1673151750972763,
224
+ "grad_norm": 0.5365095452402927,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.5522,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.206225680933852,
231
+ "grad_norm": 0.5366207968612337,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.5501,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.245136186770428,
238
+ "grad_norm": 0.566878607561335,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.5593,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2840466926070038,
245
+ "grad_norm": 0.5025021953975053,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.5529,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.3229571984435797,
252
+ "grad_norm": 0.6517974108354097,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.5516,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.3618677042801557,
259
+ "grad_norm": 0.5877223133514731,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.5478,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.4007782101167314,
266
+ "grad_norm": 0.523088164773279,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.5648,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.4396887159533074,
273
+ "grad_norm": 0.618255839408507,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.5513,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.4785992217898833,
280
+ "grad_norm": 0.6260088198489807,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.5544,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.517509727626459,
287
+ "grad_norm": 0.7806658992319804,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.5528,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.556420233463035,
294
+ "grad_norm": 0.6140146431690726,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.5481,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.595330739299611,
301
+ "grad_norm": 0.5582487614699068,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.5545,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.6342412451361867,
308
+ "grad_norm": 0.542657780109806,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.553,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.6731517509727627,
315
+ "grad_norm": 0.6708086079418305,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.5391,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.7120622568093387,
322
+ "grad_norm": 0.5278094833402398,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.5576,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.7509727626459144,
329
+ "grad_norm": 0.47924313254672846,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5439,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.7898832684824901,
336
+ "grad_norm": 0.6689950674332287,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5509,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.8287937743190663,
343
+ "grad_norm": 0.4975766449875395,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5547,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.867704280155642,
350
+ "grad_norm": 0.5110905522427862,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5466,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.9066147859922178,
357
+ "grad_norm": 0.5472555938572321,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5505,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.9455252918287937,
364
+ "grad_norm": 0.47391342497543426,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.548,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.9844357976653697,
371
+ "grad_norm": 0.5241425070111457,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5559,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 2.0,
378
+ "eval_loss": 0.5962130427360535,
379
+ "eval_runtime": 274.4938,
380
+ "eval_samples_per_second": 25.225,
381
+ "eval_steps_per_second": 0.397,
382
+ "step": 514
383
+ },
384
+ {
385
+ "epoch": 2.0233463035019454,
386
+ "grad_norm": 0.7607891193722286,
387
+ "learning_rate": 5e-06,
388
+ "loss": 0.5269,
389
+ "step": 520
390
+ },
391
+ {
392
+ "epoch": 2.062256809338521,
393
+ "grad_norm": 0.80811781065185,
394
+ "learning_rate": 5e-06,
395
+ "loss": 0.4971,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 2.1011673151750974,
400
+ "grad_norm": 0.6433576240535729,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.4955,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.140077821011673,
407
+ "grad_norm": 0.5189612131550143,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.5002,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.178988326848249,
414
+ "grad_norm": 0.5760279746695216,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.5012,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.217898832684825,
421
+ "grad_norm": 0.6914197290750576,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.4955,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.2568093385214008,
428
+ "grad_norm": 0.7728451901596064,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.5055,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.2957198443579765,
435
+ "grad_norm": 0.5835397819143044,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.503,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.3346303501945527,
442
+ "grad_norm": 0.5879273137062859,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.5027,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.3735408560311284,
449
+ "grad_norm": 0.5684409532220068,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.497,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.412451361867704,
456
+ "grad_norm": 0.6525031507435581,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.4932,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.4513618677042803,
463
+ "grad_norm": 0.49071643579732227,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.5024,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.490272373540856,
470
+ "grad_norm": 0.5247335428962803,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.4985,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.529182879377432,
477
+ "grad_norm": 0.48059327924155726,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.5107,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.5680933852140075,
484
+ "grad_norm": 0.5430102339057058,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.4941,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.6070038910505837,
491
+ "grad_norm": 0.534453464123415,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.5018,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.6459143968871595,
498
+ "grad_norm": 0.571745060913961,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.5104,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.6848249027237356,
505
+ "grad_norm": 0.540202566567447,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.4999,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.7237354085603114,
512
+ "grad_norm": 0.4691152648293088,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5009,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.762645914396887,
519
+ "grad_norm": 0.6372006699442468,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5055,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.801556420233463,
526
+ "grad_norm": 0.484555768964224,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5075,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.840466926070039,
533
+ "grad_norm": 0.5065631150373296,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.4927,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.8793774319066148,
540
+ "grad_norm": 0.5294227842308346,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.51,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.9182879377431905,
547
+ "grad_norm": 0.541508376210009,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.4998,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.9571984435797667,
554
+ "grad_norm": 0.5130299093056558,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5119,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.9961089494163424,
561
+ "grad_norm": 0.4915867802493192,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5053,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 3.0,
568
+ "eval_loss": 0.6005940437316895,
569
+ "eval_runtime": 276.4988,
570
+ "eval_samples_per_second": 25.042,
571
+ "eval_steps_per_second": 0.394,
572
+ "step": 771
573
+ },
574
+ {
575
+ "epoch": 3.0,
576
+ "step": 771,
577
+ "total_flos": 1291244336578560.0,
578
+ "train_loss": 0.5620605509955287,
579
+ "train_runtime": 45702.4745,
580
+ "train_samples_per_second": 8.636,
581
+ "train_steps_per_second": 0.017
582
+ }
583
+ ],
584
+ "logging_steps": 10,
585
+ "max_steps": 771,
586
+ "num_input_tokens_seen": 0,
587
+ "num_train_epochs": 3,
588
+ "save_steps": 500,
589
+ "stateful_callbacks": {
590
+ "TrainerControl": {
591
+ "args": {
592
+ "should_epoch_stop": false,
593
+ "should_evaluate": false,
594
+ "should_log": false,
595
+ "should_save": true,
596
+ "should_training_stop": true
597
+ },
598
+ "attributes": {}
599
+ }
600
+ },
601
+ "total_flos": 1291244336578560.0,
602
+ "train_batch_size": 8,
603
+ "trial_name": null,
604
+ "trial_params": null
605
+ }
training_eval_loss.png ADDED
training_loss.png ADDED