gsmyrnis commited on
Commit
4a9bf2c
·
verified ·
1 Parent(s): 555b74e

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_opengpt_x4
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_opengpt_x4
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: 0.7273
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_opengpt_x4
 
16
 
17
  # oh_v1.3_opengpt_x4
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_opengpt_x4 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7273
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7273038625717163,
4
+ "eval_runtime": 26.0262,
5
+ "eval_samples_per_second": 283.598,
6
+ "eval_steps_per_second": 1.114,
7
+ "total_flos": 1376880615751680.0,
8
+ "train_loss": 0.7032751636783572,
9
+ "train_runtime": 5303.7541,
10
+ "train_samples_per_second": 79.315,
11
+ "train_steps_per_second": 0.155
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7273038625717163,
4
+ "eval_runtime": 26.0262,
5
+ "eval_samples_per_second": 283.598,
6
+ "eval_steps_per_second": 1.114
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1376880615751680.0,
4
+ "train_loss": 0.7032751636783572,
5
+ "train_runtime": 5303.7541,
6
+ "train_samples_per_second": 79.315,
7
+ "train_steps_per_second": 0.155
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,640 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 822,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0364963503649635,
13
+ "grad_norm": 6.242694070966219,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0388,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.072992700729927,
20
+ "grad_norm": 6.140265839791405,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9087,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10948905109489052,
27
+ "grad_norm": 2.0729558067197855,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8718,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.145985401459854,
34
+ "grad_norm": 2.0048530569345027,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8466,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.18248175182481752,
41
+ "grad_norm": 1.2903801782452229,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8272,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.21897810218978103,
48
+ "grad_norm": 1.9320500006452086,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8176,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.25547445255474455,
55
+ "grad_norm": 1.3130529470395709,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8039,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.291970802919708,
62
+ "grad_norm": 1.1106618130287023,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.7935,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3284671532846715,
69
+ "grad_norm": 0.9675468601929832,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.78,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.36496350364963503,
76
+ "grad_norm": 0.6972886370921517,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7753,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.40145985401459855,
83
+ "grad_norm": 0.6872017378102949,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7722,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.43795620437956206,
90
+ "grad_norm": 0.6670734728993309,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7673,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4744525547445255,
97
+ "grad_norm": 0.6673276704616633,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7643,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5109489051094891,
104
+ "grad_norm": 0.7068821433326216,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7637,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5474452554744526,
111
+ "grad_norm": 0.8071055608747135,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.7604,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.583941605839416,
118
+ "grad_norm": 0.6868966364491296,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7522,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6204379562043796,
125
+ "grad_norm": 0.9124104678824304,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7547,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.656934306569343,
132
+ "grad_norm": 0.6792590544713151,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7562,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6934306569343066,
139
+ "grad_norm": 0.617023036902581,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.756,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7299270072992701,
146
+ "grad_norm": 0.6319144841610138,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.751,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7664233576642335,
153
+ "grad_norm": 0.6320543677861779,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.748,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.8029197080291971,
160
+ "grad_norm": 0.6210695741046822,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7489,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.8394160583941606,
167
+ "grad_norm": 0.7516050498994822,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7453,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8759124087591241,
174
+ "grad_norm": 0.5948362298346876,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7444,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.9124087591240876,
181
+ "grad_norm": 0.7329567143609019,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7444,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.948905109489051,
188
+ "grad_norm": 0.5724746440812548,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7372,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.9854014598540146,
195
+ "grad_norm": 0.5915513551849372,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.7414,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.0,
202
+ "eval_loss": 0.737393319606781,
203
+ "eval_runtime": 26.5119,
204
+ "eval_samples_per_second": 278.403,
205
+ "eval_steps_per_second": 1.094,
206
+ "step": 274
207
+ },
208
+ {
209
+ "epoch": 1.0218978102189782,
210
+ "grad_norm": 1.1407224725998888,
211
+ "learning_rate": 5e-06,
212
+ "loss": 0.707,
213
+ "step": 280
214
+ },
215
+ {
216
+ "epoch": 1.0583941605839415,
217
+ "grad_norm": 0.8137371947663772,
218
+ "learning_rate": 5e-06,
219
+ "loss": 0.6965,
220
+ "step": 290
221
+ },
222
+ {
223
+ "epoch": 1.094890510948905,
224
+ "grad_norm": 0.7624656836561821,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6929,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.1313868613138687,
231
+ "grad_norm": 0.6731270507290879,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.6907,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.167883211678832,
238
+ "grad_norm": 0.6477624974220811,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6883,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.2043795620437956,
245
+ "grad_norm": 0.6806120359954909,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.6896,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.2408759124087592,
252
+ "grad_norm": 0.6534094167466027,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.6834,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.2773722627737225,
259
+ "grad_norm": 0.7053154028357804,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.6938,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.313868613138686,
266
+ "grad_norm": 0.5843975789107667,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.6905,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.3503649635036497,
273
+ "grad_norm": 0.6607671591107314,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.6887,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.3868613138686132,
280
+ "grad_norm": 0.6948472684652132,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.6863,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.4233576642335766,
287
+ "grad_norm": 0.6575033962434685,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.6886,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.4598540145985401,
294
+ "grad_norm": 0.5872317321934506,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.6868,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.4963503649635037,
301
+ "grad_norm": 0.5826458330462528,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.6895,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.5328467153284673,
308
+ "grad_norm": 0.6464190966828731,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6836,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.5693430656934306,
315
+ "grad_norm": 0.7159795940614451,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6834,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.6058394160583942,
322
+ "grad_norm": 0.74415061125301,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6922,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.6423357664233578,
329
+ "grad_norm": 0.5766064803057743,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6848,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.6788321167883211,
336
+ "grad_norm": 0.6927585803335585,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6839,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.7153284671532847,
343
+ "grad_norm": 0.551695429707459,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6859,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.7518248175182483,
350
+ "grad_norm": 0.6002867275771926,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6872,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.7883211678832116,
357
+ "grad_norm": 0.5786825602682476,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6882,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.8248175182481752,
364
+ "grad_norm": 0.6235940806026485,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6869,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.8613138686131387,
371
+ "grad_norm": 0.6421720075253999,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6869,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.897810218978102,
378
+ "grad_norm": 0.6399996565023783,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.683,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.9343065693430657,
385
+ "grad_norm": 0.6345252795641959,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.683,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.9708029197080292,
392
+ "grad_norm": 0.6174798987748756,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6788,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 2.0,
399
+ "eval_loss": 0.724261999130249,
400
+ "eval_runtime": 29.7165,
401
+ "eval_samples_per_second": 248.38,
402
+ "eval_steps_per_second": 0.976,
403
+ "step": 548
404
+ },
405
+ {
406
+ "epoch": 2.0072992700729926,
407
+ "grad_norm": 0.9503885013468557,
408
+ "learning_rate": 5e-06,
409
+ "loss": 0.6733,
410
+ "step": 550
411
+ },
412
+ {
413
+ "epoch": 2.0437956204379564,
414
+ "grad_norm": 0.7079333930728279,
415
+ "learning_rate": 5e-06,
416
+ "loss": 0.6294,
417
+ "step": 560
418
+ },
419
+ {
420
+ "epoch": 2.0802919708029197,
421
+ "grad_norm": 0.8055321987953024,
422
+ "learning_rate": 5e-06,
423
+ "loss": 0.6282,
424
+ "step": 570
425
+ },
426
+ {
427
+ "epoch": 2.116788321167883,
428
+ "grad_norm": 0.7013752206943129,
429
+ "learning_rate": 5e-06,
430
+ "loss": 0.6346,
431
+ "step": 580
432
+ },
433
+ {
434
+ "epoch": 2.153284671532847,
435
+ "grad_norm": 0.795586932183297,
436
+ "learning_rate": 5e-06,
437
+ "loss": 0.6309,
438
+ "step": 590
439
+ },
440
+ {
441
+ "epoch": 2.18978102189781,
442
+ "grad_norm": 0.6072532710663935,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6288,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.2262773722627736,
449
+ "grad_norm": 0.7308694689768187,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.6335,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.2627737226277373,
456
+ "grad_norm": 0.8888891048172273,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.6347,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.2992700729927007,
463
+ "grad_norm": 0.5694467380633018,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.6358,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.335766423357664,
470
+ "grad_norm": 0.6996612017894321,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.6331,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.372262773722628,
477
+ "grad_norm": 0.6798927912381371,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.6355,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.408759124087591,
484
+ "grad_norm": 0.7832060679040136,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.6306,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.445255474452555,
491
+ "grad_norm": 0.8518259483264891,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.6329,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.4817518248175183,
498
+ "grad_norm": 0.8847565076314947,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.6355,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.5182481751824817,
505
+ "grad_norm": 0.8790006051896251,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.6341,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.554744525547445,
512
+ "grad_norm": 0.7205003318722193,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.6353,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.591240875912409,
519
+ "grad_norm": 0.6695065635591323,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.6336,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.627737226277372,
526
+ "grad_norm": 0.701791622519896,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.6392,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.664233576642336,
533
+ "grad_norm": 0.6510579026114841,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.6325,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.7007299270072993,
540
+ "grad_norm": 0.6391591776977092,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.6379,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.7372262773722627,
547
+ "grad_norm": 0.6379410196843575,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.6428,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.7737226277372264,
554
+ "grad_norm": 0.5663117162856989,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.6365,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.81021897810219,
561
+ "grad_norm": 0.5976599060822565,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.6337,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.846715328467153,
568
+ "grad_norm": 0.5764241288666703,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.6378,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.883211678832117,
575
+ "grad_norm": 0.5923449235752416,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.6414,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.9197080291970803,
582
+ "grad_norm": 0.7012989231730122,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.6389,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.9562043795620436,
589
+ "grad_norm": 0.669400873506838,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.6429,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.9927007299270074,
596
+ "grad_norm": 0.6342356482957713,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.6398,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 3.0,
603
+ "eval_loss": 0.7273038625717163,
604
+ "eval_runtime": 26.4167,
605
+ "eval_samples_per_second": 279.406,
606
+ "eval_steps_per_second": 1.098,
607
+ "step": 822
608
+ },
609
+ {
610
+ "epoch": 3.0,
611
+ "step": 822,
612
+ "total_flos": 1376880615751680.0,
613
+ "train_loss": 0.7032751636783572,
614
+ "train_runtime": 5303.7541,
615
+ "train_samples_per_second": 79.315,
616
+ "train_steps_per_second": 0.155
617
+ }
618
+ ],
619
+ "logging_steps": 10,
620
+ "max_steps": 822,
621
+ "num_input_tokens_seen": 0,
622
+ "num_train_epochs": 3,
623
+ "save_steps": 500,
624
+ "stateful_callbacks": {
625
+ "TrainerControl": {
626
+ "args": {
627
+ "should_epoch_stop": false,
628
+ "should_evaluate": false,
629
+ "should_log": false,
630
+ "should_save": true,
631
+ "should_training_stop": true
632
+ },
633
+ "attributes": {}
634
+ }
635
+ },
636
+ "total_flos": 1376880615751680.0,
637
+ "train_batch_size": 16,
638
+ "trial_name": null,
639
+ "trial_params": null
640
+ }
training_eval_loss.png ADDED
training_loss.png ADDED