sedrickkeh commited on
Commit
d7883a7
·
verified ·
1 Parent(s): 7d551c3

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: OH_original_wo_caseus_custom
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_original_wo_caseus_custom
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6034
21
 
 
4
  base_model: meta-llama/Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: OH_original_wo_caseus_custom
 
16
 
17
  # OH_original_wo_caseus_custom
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/OH_original_wo_caseus_custom dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6034
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99775617053104,
3
+ "eval_loss": 0.6033644080162048,
4
+ "eval_runtime": 179.1425,
5
+ "eval_samples_per_second": 50.273,
6
+ "eval_steps_per_second": 0.396,
7
+ "total_flos": 1677968560619520.0,
8
+ "train_loss": 0.5679433697949865,
9
+ "train_runtime": 29958.3489,
10
+ "train_samples_per_second": 17.134,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99775617053104,
3
+ "eval_loss": 0.6033644080162048,
4
+ "eval_runtime": 179.1425,
5
+ "eval_samples_per_second": 50.273,
6
+ "eval_steps_per_second": 0.396
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99775617053104,
3
+ "total_flos": 1677968560619520.0,
4
+ "train_loss": 0.5679433697949865,
5
+ "train_runtime": 29958.3489,
6
+ "train_samples_per_second": 17.134,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,766 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.99775617053104,
5
+ "eval_steps": 500,
6
+ "global_step": 1002,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.029917726252804786,
13
+ "grad_norm": 3.1024108625766647,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7821,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.05983545250560957,
20
+ "grad_norm": 2.0154961377920744,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.709,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.08975317875841436,
27
+ "grad_norm": 4.098110110830773,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.716,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.11967090501121914,
34
+ "grad_norm": 1.3839237187441724,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6884,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.14958863126402394,
41
+ "grad_norm": 1.6642156675636246,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6742,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.17950635751682872,
48
+ "grad_norm": 0.8382342346916078,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.6578,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2094240837696335,
55
+ "grad_norm": 1.0785514818670323,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.6526,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.2393418100224383,
62
+ "grad_norm": 0.6806480615454938,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6534,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.26925953627524307,
69
+ "grad_norm": 0.6822998110330022,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6396,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2991772625280479,
76
+ "grad_norm": 0.6407539938463268,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6336,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.32909498878085264,
83
+ "grad_norm": 0.6023614683907215,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6345,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.35901271503365745,
90
+ "grad_norm": 1.2991344935679592,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6284,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.3889304412864622,
97
+ "grad_norm": 1.2836405178889319,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6206,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.418848167539267,
104
+ "grad_norm": 0.5455928257982399,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.626,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.4487658937920718,
111
+ "grad_norm": 0.8705277514817991,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6243,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.4786836200448766,
118
+ "grad_norm": 0.6015797080220293,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6239,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5086013462976814,
125
+ "grad_norm": 0.5799933689114735,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6242,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.5385190725504861,
132
+ "grad_norm": 0.7181956170370547,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6187,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.5684367988032909,
139
+ "grad_norm": 1.1457159660009166,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6249,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.5983545250560958,
146
+ "grad_norm": 0.8081668167489676,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6262,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.6282722513089005,
153
+ "grad_norm": 0.494100005031363,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6115,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.6581899775617053,
160
+ "grad_norm": 0.49011911418037035,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6154,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.6881077038145101,
167
+ "grad_norm": 0.5619549814669743,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6182,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.7180254300673149,
174
+ "grad_norm": 0.47978866623290667,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6136,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.7479431563201197,
181
+ "grad_norm": 0.4834220711675942,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6092,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.7778608825729244,
188
+ "grad_norm": 0.5842572852141615,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6183,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.8077786088257293,
195
+ "grad_norm": 0.5124590739903697,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6091,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.837696335078534,
202
+ "grad_norm": 0.571561034937845,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6089,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.8676140613313388,
209
+ "grad_norm": 0.50639640711907,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6075,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.8975317875841436,
216
+ "grad_norm": 0.47922109749059255,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6113,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.9274495138369484,
223
+ "grad_norm": 0.6105089487425442,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6123,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.9573672400897532,
230
+ "grad_norm": 0.5056360719681718,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6156,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.9872849663425579,
237
+ "grad_norm": 0.48485936511026195,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6008,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.9992520568436799,
244
+ "eval_loss": 0.6066673398017883,
245
+ "eval_runtime": 179.254,
246
+ "eval_samples_per_second": 50.242,
247
+ "eval_steps_per_second": 0.396,
248
+ "step": 334
249
+ },
250
+ {
251
+ "epoch": 1.0172026925953628,
252
+ "grad_norm": 0.6922596264407767,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.5765,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.0471204188481675,
259
+ "grad_norm": 0.49267857964550554,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.5603,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.0770381451009723,
266
+ "grad_norm": 0.49751934654599217,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.5686,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.106955871353777,
273
+ "grad_norm": 0.6837370299507576,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.5612,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.136873597606582,
280
+ "grad_norm": 0.47693359913296135,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.5539,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.1667913238593868,
287
+ "grad_norm": 0.648584636579785,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.5622,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.1967090501121915,
294
+ "grad_norm": 0.5670898037838431,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.554,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.2266267763649963,
301
+ "grad_norm": 0.5703136712557304,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.5609,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.256544502617801,
308
+ "grad_norm": 0.6102946772879293,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.559,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.2864622288706058,
315
+ "grad_norm": 0.5772564364701466,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.5603,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.3163799551234106,
322
+ "grad_norm": 0.450931906177121,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.5601,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.3462976813762153,
329
+ "grad_norm": 0.5054266947188414,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5572,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.37621540762902,
336
+ "grad_norm": 0.48292336210926307,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5587,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.406133133881825,
343
+ "grad_norm": 0.5249447315851029,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5575,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.4360508601346298,
350
+ "grad_norm": 0.5140359027555277,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5546,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.4659685863874345,
357
+ "grad_norm": 0.5354245491327346,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5578,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.4958863126402393,
364
+ "grad_norm": 0.5682468395490031,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5602,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.5258040388930443,
371
+ "grad_norm": 0.5900754898799866,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5616,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.555721765145849,
378
+ "grad_norm": 0.4996963352974884,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.5557,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.5856394913986538,
385
+ "grad_norm": 0.5075965675534208,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.5573,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.6155572176514585,
392
+ "grad_norm": 0.6139589992144621,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.5601,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.6454749439042633,
399
+ "grad_norm": 0.5479413460230939,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.5549,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.675392670157068,
406
+ "grad_norm": 0.5917928857307124,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.553,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.7053103964098728,
413
+ "grad_norm": 0.5837997645694308,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.557,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.7352281226626776,
420
+ "grad_norm": 0.5008632390644033,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.5497,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.7651458489154823,
427
+ "grad_norm": 0.5321160422034145,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.554,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.795063575168287,
434
+ "grad_norm": 0.5334951007964042,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.5594,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.824981301421092,
441
+ "grad_norm": 0.5210632059648287,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.56,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.8548990276738968,
448
+ "grad_norm": 0.5043445814465957,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.5575,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.8848167539267016,
455
+ "grad_norm": 0.613976408483885,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.5583,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.9147344801795063,
462
+ "grad_norm": 0.5363674682216356,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.5643,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.9446522064323113,
469
+ "grad_norm": 0.5061979916241445,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.5617,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.974569932685116,
476
+ "grad_norm": 0.5681791964553616,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.5567,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.9985041136873598,
483
+ "eval_loss": 0.5981965661048889,
484
+ "eval_runtime": 179.6452,
485
+ "eval_samples_per_second": 50.132,
486
+ "eval_steps_per_second": 0.395,
487
+ "step": 668
488
+ },
489
+ {
490
+ "epoch": 2.004487658937921,
491
+ "grad_norm": 0.7426343168495358,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.5487,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.0344053851907256,
498
+ "grad_norm": 0.8360352246281931,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.509,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.0643231114435303,
505
+ "grad_norm": 0.5586788759798959,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.5107,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.094240837696335,
512
+ "grad_norm": 0.5334495185578801,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5083,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.12415856394914,
519
+ "grad_norm": 0.5451729047772684,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5103,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.1540762902019446,
526
+ "grad_norm": 0.5384304992109907,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5083,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.1839940164547493,
533
+ "grad_norm": 0.6897130607106118,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.5087,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.213911742707554,
540
+ "grad_norm": 0.4914356466355389,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.5028,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.243829468960359,
547
+ "grad_norm": 0.4859395300154547,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.5107,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.273747195213164,
554
+ "grad_norm": 0.5080772320686796,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5085,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.303664921465969,
561
+ "grad_norm": 0.5928831782745143,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5065,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.3335826477187736,
568
+ "grad_norm": 0.5292235530530627,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.5064,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.3635003739715783,
575
+ "grad_norm": 0.5612309376826925,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.5047,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.393418100224383,
582
+ "grad_norm": 0.7840153330542589,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.5107,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.423335826477188,
589
+ "grad_norm": 0.563462388459372,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.5074,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.4532535527299926,
596
+ "grad_norm": 0.6037763909811528,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.5027,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.4831712789827973,
603
+ "grad_norm": 0.512144492512373,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.5059,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.513089005235602,
610
+ "grad_norm": 0.5423885548086916,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.5087,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.543006731488407,
617
+ "grad_norm": 0.5435953936785038,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5097,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.5729244577412116,
624
+ "grad_norm": 0.5702298253328785,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5139,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.6028421839940163,
631
+ "grad_norm": 0.5598880036547539,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5108,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.632759910246821,
638
+ "grad_norm": 0.5408931335977699,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5123,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.662677636499626,
645
+ "grad_norm": 0.5650280550038018,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5024,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.6925953627524306,
652
+ "grad_norm": 0.5162753582027944,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5086,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.7225130890052354,
659
+ "grad_norm": 0.562255619044257,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5091,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.75243081525804,
666
+ "grad_norm": 0.525530348245258,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.5101,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.7823485415108453,
673
+ "grad_norm": 0.5416570745705145,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5099,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.81226626776365,
680
+ "grad_norm": 0.5094752288812316,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5091,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.842183994016455,
687
+ "grad_norm": 0.48328984684734566,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.5115,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.8721017202692596,
694
+ "grad_norm": 0.5309507328482131,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5145,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.9020194465220643,
701
+ "grad_norm": 0.5645199920156511,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.507,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.931937172774869,
708
+ "grad_norm": 0.6341772078202893,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5164,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.961854899027674,
715
+ "grad_norm": 0.5241928497019043,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5075,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.9917726252804786,
722
+ "grad_norm": 0.5568699384966846,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.5124,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.99775617053104,
729
+ "eval_loss": 0.6033644080162048,
730
+ "eval_runtime": 179.8158,
731
+ "eval_samples_per_second": 50.085,
732
+ "eval_steps_per_second": 0.395,
733
+ "step": 1002
734
+ },
735
+ {
736
+ "epoch": 2.99775617053104,
737
+ "step": 1002,
738
+ "total_flos": 1677968560619520.0,
739
+ "train_loss": 0.5679433697949865,
740
+ "train_runtime": 29958.3489,
741
+ "train_samples_per_second": 17.134,
742
+ "train_steps_per_second": 0.033
743
+ }
744
+ ],
745
+ "logging_steps": 10,
746
+ "max_steps": 1002,
747
+ "num_input_tokens_seen": 0,
748
+ "num_train_epochs": 3,
749
+ "save_steps": 500,
750
+ "stateful_callbacks": {
751
+ "TrainerControl": {
752
+ "args": {
753
+ "should_epoch_stop": false,
754
+ "should_evaluate": false,
755
+ "should_log": false,
756
+ "should_save": true,
757
+ "should_training_stop": true
758
+ },
759
+ "attributes": {}
760
+ }
761
+ },
762
+ "total_flos": 1677968560619520.0,
763
+ "train_batch_size": 8,
764
+ "trial_name": null,
765
+ "trial_params": null
766
+ }
training_eval_loss.png ADDED
training_loss.png ADDED