sedrickkeh commited on
Commit
0ac908e
·
verified ·
1 Parent(s): e493b8b

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3
4
  base_model: meta-llama/Meta-Llama-3-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: OH_DCFT_V3_wo_glaive_code_assistant
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_DCFT_V3_wo_glaive_code_assistant
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6776
21
 
 
4
  base_model: meta-llama/Meta-Llama-3-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: OH_DCFT_V3_wo_glaive_code_assistant
 
16
 
17
  # OH_DCFT_V3_wo_glaive_code_assistant
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the mlfoundations-dev/OH_DCFT_V3_wo_glaive_code_assistant dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6776
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9952,
3
+ "eval_loss": 0.6776005029678345,
4
+ "eval_runtime": 168.3612,
5
+ "eval_samples_per_second": 50.0,
6
+ "eval_steps_per_second": 0.392,
7
+ "total_flos": 1567416102420480.0,
8
+ "train_loss": 0.6459089978637859,
9
+ "train_runtime": 28277.8546,
10
+ "train_samples_per_second": 16.967,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9952,
3
+ "eval_loss": 0.6776005029678345,
4
+ "eval_runtime": 168.3612,
5
+ "eval_samples_per_second": 50.0,
6
+ "eval_steps_per_second": 0.392
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9952,
3
+ "total_flos": 1567416102420480.0,
4
+ "train_loss": 0.6459089978637859,
5
+ "train_runtime": 28277.8546,
6
+ "train_samples_per_second": 16.967,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9952,
5
+ "eval_steps": 500,
6
+ "global_step": 936,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.032,
13
+ "grad_norm": 4.681128681680185,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.944,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.064,
20
+ "grad_norm": 1.4664616243938466,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.8428,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.096,
27
+ "grad_norm": 1.8998988032315547,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.7982,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.128,
34
+ "grad_norm": 1.92324741635604,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7714,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.16,
41
+ "grad_norm": 2.4002264952882335,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7676,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.192,
48
+ "grad_norm": 1.2695794968340761,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7461,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.224,
55
+ "grad_norm": 0.9170291045990026,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7377,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.256,
62
+ "grad_norm": 1.2359528897417442,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7232,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.288,
69
+ "grad_norm": 0.8951767220444212,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7189,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.32,
76
+ "grad_norm": 0.7069383759659909,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7113,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.352,
83
+ "grad_norm": 1.0819828977879882,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7162,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.384,
90
+ "grad_norm": 1.304901636304286,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.713,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.416,
97
+ "grad_norm": 0.6373106432007576,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.711,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.448,
104
+ "grad_norm": 0.6304264579464928,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7103,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.48,
111
+ "grad_norm": 0.7649551484704428,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7074,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.512,
118
+ "grad_norm": 0.6150803591520316,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6995,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.544,
125
+ "grad_norm": 0.60459672442792,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.576,
132
+ "grad_norm": 0.5617178085268674,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7039,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.608,
139
+ "grad_norm": 0.6434460581488514,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.704,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.64,
146
+ "grad_norm": 0.7168502004019935,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.693,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.672,
153
+ "grad_norm": 0.7600011834386737,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6971,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.704,
160
+ "grad_norm": 0.6044774583977053,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6973,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.736,
167
+ "grad_norm": 0.65068804006829,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.691,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.768,
174
+ "grad_norm": 0.5634185501342828,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6956,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8,
181
+ "grad_norm": 0.6768741126198279,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.693,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.832,
188
+ "grad_norm": 0.6013038960725747,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.695,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.864,
195
+ "grad_norm": 0.5521163219149124,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6956,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.896,
202
+ "grad_norm": 0.6101943227594748,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6863,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.928,
209
+ "grad_norm": 0.7006837763958106,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.686,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.96,
216
+ "grad_norm": 0.7462008507832877,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.679,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.992,
223
+ "grad_norm": 0.5329536650880176,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6722,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.9984,
230
+ "eval_loss": 0.684551477432251,
231
+ "eval_runtime": 168.4477,
232
+ "eval_samples_per_second": 49.974,
233
+ "eval_steps_per_second": 0.392,
234
+ "step": 312
235
+ },
236
+ {
237
+ "epoch": 1.024,
238
+ "grad_norm": 0.877682536384727,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6394,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.056,
245
+ "grad_norm": 0.6299661618385989,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6282,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.088,
252
+ "grad_norm": 0.9299954358565179,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6327,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.12,
259
+ "grad_norm": 0.6355052821952561,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6326,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.152,
266
+ "grad_norm": 0.6315825615381476,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6289,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.184,
273
+ "grad_norm": 0.5622112607620553,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6448,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.216,
280
+ "grad_norm": 0.6577442757912503,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6314,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.248,
287
+ "grad_norm": 0.6462394250281904,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6307,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.28,
294
+ "grad_norm": 0.6305710848857419,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6335,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.312,
301
+ "grad_norm": 0.6739586427264055,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6305,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.3439999999999999,
308
+ "grad_norm": 0.5926724148807778,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6244,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.376,
315
+ "grad_norm": 0.5553139599738963,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6385,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.408,
322
+ "grad_norm": 0.6469857046293095,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6266,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.44,
329
+ "grad_norm": 0.5756297365306258,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6274,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.472,
336
+ "grad_norm": 0.5935989657812096,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.643,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.504,
343
+ "grad_norm": 0.646580130562456,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6347,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.536,
350
+ "grad_norm": 0.6662432182668429,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.637,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.568,
357
+ "grad_norm": 0.6098294179034147,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6339,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.6,
364
+ "grad_norm": 0.5297071787734379,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6385,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.6320000000000001,
371
+ "grad_norm": 0.719632379699023,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.626,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.6640000000000001,
378
+ "grad_norm": 0.5076459047888962,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6359,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.696,
385
+ "grad_norm": 0.5629232051091821,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.635,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.728,
392
+ "grad_norm": 0.5166400346895539,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6255,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.76,
399
+ "grad_norm": 0.6147003690488106,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6328,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.792,
406
+ "grad_norm": 0.6210621909628569,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6375,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.8239999999999998,
413
+ "grad_norm": 0.6198915290710809,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6421,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.8559999999999999,
420
+ "grad_norm": 0.5425204952547927,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.636,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.888,
427
+ "grad_norm": 0.4753843958385197,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6214,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.92,
434
+ "grad_norm": 0.5703253197864113,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6245,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.952,
441
+ "grad_norm": 0.6133997537829436,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6315,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.984,
448
+ "grad_norm": 0.5628290861601559,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6363,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 2.0,
455
+ "eval_loss": 0.6738976836204529,
456
+ "eval_runtime": 168.9768,
457
+ "eval_samples_per_second": 49.817,
458
+ "eval_steps_per_second": 0.391,
459
+ "step": 625
460
+ },
461
+ {
462
+ "epoch": 2.016,
463
+ "grad_norm": 0.8168281752833556,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6036,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.048,
470
+ "grad_norm": 0.7580260940938055,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.5682,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.08,
477
+ "grad_norm": 0.7062292404432674,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.5747,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.112,
484
+ "grad_norm": 0.5992453206728847,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.5836,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.144,
491
+ "grad_norm": 0.5619811705811777,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.581,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.176,
498
+ "grad_norm": 0.5958747225446613,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.578,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.208,
505
+ "grad_norm": 0.6497415815637109,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.5732,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.24,
512
+ "grad_norm": 0.5780693478259846,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5816,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.2720000000000002,
519
+ "grad_norm": 0.596184390481402,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5741,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.304,
526
+ "grad_norm": 0.6306865439208578,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5833,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.336,
533
+ "grad_norm": 0.583701490553111,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.5867,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.368,
540
+ "grad_norm": 0.6055766388646271,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.5894,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.4,
547
+ "grad_norm": 0.67228235956439,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.5802,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.432,
554
+ "grad_norm": 0.6434293537696463,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5797,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.464,
561
+ "grad_norm": 0.8446283351461378,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5847,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.496,
568
+ "grad_norm": 0.6805593232272164,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.5791,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.528,
575
+ "grad_norm": 0.6396132909626955,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.576,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.56,
582
+ "grad_norm": 0.5939211838981279,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.5762,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.592,
589
+ "grad_norm": 0.617055354774866,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.5828,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.624,
596
+ "grad_norm": 0.8572554082731082,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.5879,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.656,
603
+ "grad_norm": 0.6390611228450237,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.5849,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.6879999999999997,
610
+ "grad_norm": 0.616019451907882,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.5836,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.7199999999999998,
617
+ "grad_norm": 0.6021038686149264,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.582,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.752,
624
+ "grad_norm": 0.6506064567719853,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5895,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.784,
631
+ "grad_norm": 0.5976578928465824,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5888,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.816,
638
+ "grad_norm": 0.7052250144169027,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5835,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.848,
645
+ "grad_norm": 0.5708818723724719,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5873,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.88,
652
+ "grad_norm": 0.5395580422880416,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5813,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.912,
659
+ "grad_norm": 0.6226733841326677,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5845,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.944,
666
+ "grad_norm": 0.9233745991272709,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.5937,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.976,
673
+ "grad_norm": 0.6314988399397768,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5882,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.9952,
680
+ "eval_loss": 0.6776005029678345,
681
+ "eval_runtime": 169.1842,
682
+ "eval_samples_per_second": 49.756,
683
+ "eval_steps_per_second": 0.39,
684
+ "step": 936
685
+ },
686
+ {
687
+ "epoch": 2.9952,
688
+ "step": 936,
689
+ "total_flos": 1567416102420480.0,
690
+ "train_loss": 0.6459089978637859,
691
+ "train_runtime": 28277.8546,
692
+ "train_samples_per_second": 16.967,
693
+ "train_steps_per_second": 0.033
694
+ }
695
+ ],
696
+ "logging_steps": 10,
697
+ "max_steps": 936,
698
+ "num_input_tokens_seen": 0,
699
+ "num_train_epochs": 3,
700
+ "save_steps": 500,
701
+ "stateful_callbacks": {
702
+ "TrainerControl": {
703
+ "args": {
704
+ "should_epoch_stop": false,
705
+ "should_evaluate": false,
706
+ "should_log": false,
707
+ "should_save": true,
708
+ "should_training_stop": true
709
+ },
710
+ "attributes": {}
711
+ }
712
+ },
713
+ "total_flos": 1567416102420480.0,
714
+ "train_batch_size": 8,
715
+ "trial_name": null,
716
+ "trial_params": null
717
+ }
training_eval_loss.png ADDED
training_loss.png ADDED