sedrickkeh commited on
Commit
e81fd14
·
verified ·
1 Parent(s): e1a6c18

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_camel_math_x.5
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_camel_math_x.5
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: 0.7408
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_camel_math_x.5
 
16
 
17
  # oh_v1.3_camel_math_x.5
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_camel_math_x.5 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7408
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9958081043316254,
3
+ "eval_loss": 0.7408209443092346,
4
+ "eval_runtime": 283.3849,
5
+ "eval_samples_per_second": 25.509,
6
+ "eval_steps_per_second": 0.399,
7
+ "total_flos": 1346520565678080.0,
8
+ "train_loss": 0.7105088189466676,
9
+ "train_runtime": 47269.4774,
10
+ "train_samples_per_second": 8.717,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9958081043316254,
3
+ "eval_loss": 0.7408209443092346,
4
+ "eval_runtime": 283.3849,
5
+ "eval_samples_per_second": 25.509,
6
+ "eval_steps_per_second": 0.399
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9958081043316254,
3
+ "total_flos": 1346520565678080.0,
4
+ "train_loss": 0.7105088189466676,
5
+ "train_runtime": 47269.4774,
6
+ "train_samples_per_second": 8.717,
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": 2.9958081043316254,
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": 0.037261294829995344,
13
+ "grad_norm": 3.177923185690651,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0446,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07452258965999069,
20
+ "grad_norm": 1.5655148840692104,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9101,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11178388448998602,
27
+ "grad_norm": 1.2741458134596388,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8739,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.14904517931998137,
34
+ "grad_norm": 1.1521931357563782,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8458,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.18630647414997673,
41
+ "grad_norm": 1.1371625192876917,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8221,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.22356776897997205,
48
+ "grad_norm": 0.9080984413465669,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8159,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2608290638099674,
55
+ "grad_norm": 0.9330400679788563,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8017,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.29809035863996275,
62
+ "grad_norm": 0.7711080271829996,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7893,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3353516534699581,
69
+ "grad_norm": 0.7516775112714674,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.792,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.37261294829995345,
76
+ "grad_norm": 0.6720880112699107,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7807,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.40987424312994875,
83
+ "grad_norm": 1.0015408115889342,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7739,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4471355379599441,
90
+ "grad_norm": 0.7967270535006579,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7753,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.48439683278993945,
97
+ "grad_norm": 0.7992952214381639,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7685,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5216581276199348,
104
+ "grad_norm": 0.822692265972509,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7664,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5589194224499301,
111
+ "grad_norm": 0.6248743169023847,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7619,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5961807172799255,
118
+ "grad_norm": 0.7681721127721153,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7601,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6334420121099208,
125
+ "grad_norm": 0.6670980060596134,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7594,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6707033069399162,
132
+ "grad_norm": 1.6054759679741344,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7627,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.7079646017699115,
139
+ "grad_norm": 1.0157126085127113,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7612,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7452258965999069,
146
+ "grad_norm": 1.0987509598845462,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7566,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7824871914299022,
153
+ "grad_norm": 0.8874349124844947,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.7578,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8197484862598975,
160
+ "grad_norm": 0.8625833938546213,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7472,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8570097810898929,
167
+ "grad_norm": 0.6536315928798102,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7499,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8942710759198882,
174
+ "grad_norm": 0.5976487344814351,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7493,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9315323707498836,
181
+ "grad_norm": 0.6377854255157969,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7449,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.9687936655798789,
188
+ "grad_norm": 0.6255963141536746,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7463,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9986027014438752,
195
+ "eval_loss": 0.753118097782135,
196
+ "eval_runtime": 282.6878,
197
+ "eval_samples_per_second": 25.572,
198
+ "eval_steps_per_second": 0.4,
199
+ "step": 268
200
+ },
201
+ {
202
+ "epoch": 1.0060549604098743,
203
+ "grad_norm": 0.7967440184692027,
204
+ "learning_rate": 5e-06,
205
+ "loss": 0.7858,
206
+ "step": 270
207
+ },
208
+ {
209
+ "epoch": 1.0433162552398696,
210
+ "grad_norm": 0.6961321881435635,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.6975,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.080577550069865,
217
+ "grad_norm": 0.762772210563081,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.6948,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.1178388448998602,
224
+ "grad_norm": 0.7180309443204612,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6976,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1551001397298557,
231
+ "grad_norm": 0.7681051261580779,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6927,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.192361434559851,
238
+ "grad_norm": 0.5509672175600794,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6914,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2296227293898463,
245
+ "grad_norm": 0.6540568092405752,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.7042,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2668840242198416,
252
+ "grad_norm": 0.6081452030296887,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6964,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.3041453190498369,
259
+ "grad_norm": 0.6548111894829255,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6982,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.3414066138798324,
266
+ "grad_norm": 0.6390670197121491,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6958,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.3786679087098277,
273
+ "grad_norm": 0.6212133244114497,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6966,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.415929203539823,
280
+ "grad_norm": 0.5799521943921166,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6891,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4531904983698183,
287
+ "grad_norm": 0.6895979564472926,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6961,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.4904517931998136,
294
+ "grad_norm": 0.7051355249345896,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6937,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.527713088029809,
301
+ "grad_norm": 0.5848394801525845,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6934,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.5649743828598044,
308
+ "grad_norm": 0.7559716416869524,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6895,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.6022356776897997,
315
+ "grad_norm": 0.6232619179980586,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6982,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.6394969725197952,
322
+ "grad_norm": 0.5824898687040235,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6952,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.6767582673497903,
329
+ "grad_norm": 0.6210814650937644,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6973,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.7140195621797858,
336
+ "grad_norm": 0.6197587117855798,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6941,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.751280857009781,
343
+ "grad_norm": 0.5610090469048251,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6918,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.7885421518397764,
350
+ "grad_norm": 0.6397472245527632,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6896,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.825803446669772,
357
+ "grad_norm": 0.8540795729270456,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6949,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.863064741499767,
364
+ "grad_norm": 0.5933184699793366,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6941,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.9003260363297625,
371
+ "grad_norm": 0.5702682781752477,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6947,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.9375873311597578,
378
+ "grad_norm": 0.6485728293989254,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6934,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.974848625989753,
385
+ "grad_norm": 0.658819869120822,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6935,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.9972054028877504,
392
+ "eval_loss": 0.7391706705093384,
393
+ "eval_runtime": 284.9966,
394
+ "eval_samples_per_second": 25.365,
395
+ "eval_steps_per_second": 0.396,
396
+ "step": 536
397
+ },
398
+ {
399
+ "epoch": 2.0121099208197486,
400
+ "grad_norm": 0.8176370133975521,
401
+ "learning_rate": 5e-06,
402
+ "loss": 0.7119,
403
+ "step": 540
404
+ },
405
+ {
406
+ "epoch": 2.0493712156497437,
407
+ "grad_norm": 1.0394836748871732,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.6404,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.086632510479739,
414
+ "grad_norm": 0.7102912397553353,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6384,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.1238938053097347,
421
+ "grad_norm": 0.6303371150790377,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6368,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.16115510013973,
428
+ "grad_norm": 0.7194505328759309,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6331,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.1984163949697253,
435
+ "grad_norm": 0.8581082758870584,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6414,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.2356776897997204,
442
+ "grad_norm": 0.7882079908607245,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.642,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.272938984629716,
449
+ "grad_norm": 0.7493026584846839,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.644,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.3102002794597114,
456
+ "grad_norm": 0.6779697760274137,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6446,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.3474615742897065,
463
+ "grad_norm": 0.7469773522523896,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6413,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.384722869119702,
470
+ "grad_norm": 0.8234476990672971,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6383,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.421984163949697,
477
+ "grad_norm": 0.6740528425843195,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6403,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.4592454587796926,
484
+ "grad_norm": 0.8699308162958452,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6424,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.496506753609688,
491
+ "grad_norm": 0.7201278110102733,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.645,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.533768048439683,
498
+ "grad_norm": 0.6724034506353075,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6432,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.5710293432696787,
505
+ "grad_norm": 0.69360608529311,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6396,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.6082906380996738,
512
+ "grad_norm": 0.8274824206163831,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6392,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.6455519329296693,
519
+ "grad_norm": 0.6599355927406194,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6376,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.682813227759665,
526
+ "grad_norm": 0.6028719649182044,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6426,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.72007452258966,
533
+ "grad_norm": 0.8529220528875564,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6442,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.7573358174196554,
540
+ "grad_norm": 0.5833740770838279,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6435,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.794597112249651,
547
+ "grad_norm": 0.75585676373348,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.643,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.831858407079646,
554
+ "grad_norm": 0.7316206001732912,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.645,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.8691197019096415,
561
+ "grad_norm": 0.6022571096523994,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.643,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.9063809967396366,
568
+ "grad_norm": 0.6980539018883889,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6444,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.943642291569632,
575
+ "grad_norm": 0.6379664123364885,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6418,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.980903586399627,
582
+ "grad_norm": 0.617861393266688,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6473,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.9958081043316254,
589
+ "eval_loss": 0.7408209443092346,
590
+ "eval_runtime": 283.5662,
591
+ "eval_samples_per_second": 25.493,
592
+ "eval_steps_per_second": 0.398,
593
+ "step": 804
594
+ },
595
+ {
596
+ "epoch": 2.9958081043316254,
597
+ "step": 804,
598
+ "total_flos": 1346520565678080.0,
599
+ "train_loss": 0.7105088189466676,
600
+ "train_runtime": 47269.4774,
601
+ "train_samples_per_second": 8.717,
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