sedrickkeh commited on
Commit
ea1b90c
·
verified ·
1 Parent(s): a6ee72a

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama2
4
  base_model: meta-llama/Llama-2-7b-hf
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: llama2_oh_teknium_scaling_down_random_0.7
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama2_oh_teknium_scaling_down_random_0.7
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.5556
21
 
 
4
  base_model: meta-llama/Llama-2-7b-hf
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: llama2_oh_teknium_scaling_down_random_0.7
 
16
 
17
  # llama2_oh_teknium_scaling_down_random_0.7
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the mlfoundations-dev/oh_teknium_scaling_down_random_0.7 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.5556
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9914040114613183,
3
+ "eval_loss": 0.5556380152702332,
4
+ "eval_runtime": 266.6242,
5
+ "eval_samples_per_second": 26.445,
6
+ "eval_steps_per_second": 0.416,
7
+ "total_flos": 1311344783523840.0,
8
+ "train_loss": 0.56458546481979,
9
+ "train_runtime": 43241.279,
10
+ "train_samples_per_second": 9.294,
11
+ "train_steps_per_second": 0.018
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9914040114613183,
3
+ "eval_loss": 0.5556380152702332,
4
+ "eval_runtime": 266.6242,
5
+ "eval_samples_per_second": 26.445,
6
+ "eval_steps_per_second": 0.416
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9914040114613183,
3
+ "total_flos": 1311344783523840.0,
4
+ "train_loss": 0.56458546481979,
5
+ "train_runtime": 43241.279,
6
+ "train_samples_per_second": 9.294,
7
+ "train_steps_per_second": 0.018
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,612 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9914040114613183,
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": 0.4276723796700453,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7667,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07640878701050621,
20
+ "grad_norm": 0.32348084518039205,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.6918,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11461318051575932,
27
+ "grad_norm": 0.249229325173226,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6746,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.15281757402101243,
34
+ "grad_norm": 0.2330974473839111,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6616,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.19102196752626552,
41
+ "grad_norm": 0.21939385628582367,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6476,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.22922636103151864,
48
+ "grad_norm": 0.22653282596248933,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.6393,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.26743075453677173,
55
+ "grad_norm": 0.21566654146702766,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.6332,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.30563514804202485,
62
+ "grad_norm": 0.23074248808260428,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6213,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3438395415472779,
69
+ "grad_norm": 0.2243717024132665,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6308,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.38204393505253104,
76
+ "grad_norm": 0.22036293175240984,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6164,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.42024832855778416,
83
+ "grad_norm": 0.21643485347884658,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.614,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4584527220630373,
90
+ "grad_norm": 0.23679718136436143,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6122,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.49665711556829034,
97
+ "grad_norm": 0.21300114530932357,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6116,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5348615090735435,
104
+ "grad_norm": 0.22152143302856503,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.605,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5730659025787965,
111
+ "grad_norm": 0.22150673339975496,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6043,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.6112702960840497,
118
+ "grad_norm": 0.24912302728756616,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.602,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6494746895893028,
125
+ "grad_norm": 0.2432846766077662,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.5968,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6876790830945558,
132
+ "grad_norm": 0.26332738403854294,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.5951,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.725883476599809,
139
+ "grad_norm": 0.21754173355334794,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.5931,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7640878701050621,
146
+ "grad_norm": 0.22624132864342666,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6013,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.8022922636103151,
153
+ "grad_norm": 0.23298472948158777,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.5911,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8404966571155683,
160
+ "grad_norm": 0.23281516321048557,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.5843,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8787010506208214,
167
+ "grad_norm": 0.24902984573388898,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.5833,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.9169054441260746,
174
+ "grad_norm": 0.23447860858377242,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.5904,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9551098376313276,
181
+ "grad_norm": 0.2505627332870155,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.5883,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9933142311365807,
188
+ "grad_norm": 0.22477676543315434,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.5903,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.997134670487106,
195
+ "eval_loss": 0.584246039390564,
196
+ "eval_runtime": 265.5626,
197
+ "eval_samples_per_second": 26.551,
198
+ "eval_steps_per_second": 0.418,
199
+ "step": 261
200
+ },
201
+ {
202
+ "epoch": 1.0315186246418337,
203
+ "grad_norm": 0.2352884844118039,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.5757,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.069723018147087,
210
+ "grad_norm": 0.2265143278786619,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.5599,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.10792741165234,
217
+ "grad_norm": 0.23703051084829976,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.5609,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.146131805157593,
224
+ "grad_norm": 0.23682463293260125,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.5617,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1843361986628462,
231
+ "grad_norm": 0.22196069951621014,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.5659,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.2225405921680994,
238
+ "grad_norm": 0.22990143320629003,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.5623,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2607449856733524,
245
+ "grad_norm": 0.23117727752852635,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.5536,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2989493791786055,
252
+ "grad_norm": 0.24177690757057696,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.5524,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.3371537726838587,
259
+ "grad_norm": 0.277046963962815,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.557,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.3753581661891117,
266
+ "grad_norm": 0.24447457739587525,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.5562,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.4135625596943648,
273
+ "grad_norm": 0.22521828675343608,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.5557,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.451766953199618,
280
+ "grad_norm": 0.24923924743373047,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.5535,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4899713467048712,
287
+ "grad_norm": 0.23051752759244015,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.5512,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.5281757402101241,
294
+ "grad_norm": 0.2305514578191316,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.5574,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.5663801337153773,
301
+ "grad_norm": 0.2315782231048154,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.5544,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.6045845272206303,
308
+ "grad_norm": 0.22664996821288788,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.5425,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.6427889207258835,
315
+ "grad_norm": 0.2418068965690577,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.5577,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.6809933142311366,
322
+ "grad_norm": 0.22893902566494653,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.5538,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.7191977077363898,
329
+ "grad_norm": 0.2465301749712713,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5485,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.7574021012416428,
336
+ "grad_norm": 0.24143985417715072,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5474,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.795606494746896,
343
+ "grad_norm": 0.24566695881021275,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5503,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.8338108882521489,
350
+ "grad_norm": 0.24718715138028305,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5526,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.872015281757402,
357
+ "grad_norm": 0.22975894080844286,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5453,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.9102196752626552,
364
+ "grad_norm": 0.23859388198650291,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5464,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.9484240687679084,
371
+ "grad_norm": 0.23136216226812198,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5449,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.9866284622731614,
378
+ "grad_norm": 0.2349357255149748,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.5494,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9980897803247375,
385
+ "eval_loss": 0.5642140507698059,
386
+ "eval_runtime": 264.3703,
387
+ "eval_samples_per_second": 26.671,
388
+ "eval_steps_per_second": 0.42,
389
+ "step": 523
390
+ },
391
+ {
392
+ "epoch": 2.0248328557784143,
393
+ "grad_norm": 0.25826245327612535,
394
+ "learning_rate": 5e-06,
395
+ "loss": 0.5442,
396
+ "step": 530
397
+ },
398
+ {
399
+ "epoch": 2.0630372492836675,
400
+ "grad_norm": 0.2626169515572602,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.512,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.1012416427889207,
407
+ "grad_norm": 0.2603762571041837,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.5191,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.139446036294174,
414
+ "grad_norm": 0.23015404536582382,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.5197,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.177650429799427,
421
+ "grad_norm": 0.25412548793554895,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.5239,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.21585482330468,
428
+ "grad_norm": 0.2441125264745981,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.5222,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.2540592168099334,
435
+ "grad_norm": 0.24058030309164696,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.5279,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.292263610315186,
442
+ "grad_norm": 0.24101649460454033,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.5189,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.3304680038204393,
449
+ "grad_norm": 0.239682006849809,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.5245,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.3686723973256925,
456
+ "grad_norm": 0.2534122143594625,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.5204,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.4068767908309456,
463
+ "grad_norm": 0.258948321654359,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.5136,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.445081184336199,
470
+ "grad_norm": 0.25723419087922345,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.5158,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.4832855778414515,
477
+ "grad_norm": 0.23908804434217376,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.526,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.5214899713467047,
484
+ "grad_norm": 0.25488020166141667,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.5168,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.559694364851958,
491
+ "grad_norm": 0.24336089633028843,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.5161,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.597898758357211,
498
+ "grad_norm": 0.2345400964975648,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.5249,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.6361031518624642,
505
+ "grad_norm": 0.23758922544588199,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.5151,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.6743075453677174,
512
+ "grad_norm": 0.24683864837473207,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5183,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.7125119388729706,
519
+ "grad_norm": 0.2380248988277514,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5063,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.7507163323782233,
526
+ "grad_norm": 0.2475222519828434,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5112,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.7889207258834765,
533
+ "grad_norm": 0.2519246553878985,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.5163,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.8271251193887297,
540
+ "grad_norm": 0.2677256569155169,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.5207,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.865329512893983,
547
+ "grad_norm": 0.24396924044719615,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.5102,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.903533906399236,
554
+ "grad_norm": 0.2451469714206881,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5149,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.9417382999044888,
561
+ "grad_norm": 0.23740064104751296,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5115,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.9799426934097424,
568
+ "grad_norm": 0.24379186400055985,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.5177,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.9914040114613183,
575
+ "eval_loss": 0.5556380152702332,
576
+ "eval_runtime": 265.4623,
577
+ "eval_samples_per_second": 26.561,
578
+ "eval_steps_per_second": 0.418,
579
+ "step": 783
580
+ },
581
+ {
582
+ "epoch": 2.9914040114613183,
583
+ "step": 783,
584
+ "total_flos": 1311344783523840.0,
585
+ "train_loss": 0.56458546481979,
586
+ "train_runtime": 43241.279,
587
+ "train_samples_per_second": 9.294,
588
+ "train_steps_per_second": 0.018
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