sedrickkeh commited on
Commit
fabda64
·
verified ·
1 Parent(s): a903b43

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_dataforge_economics
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_DCFT_V3_wo_dataforge_economics
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: 0.6410
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_dataforge_economics
 
16
 
17
  # OH_DCFT_V3_wo_dataforge_economics
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_dataforge_economics dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6410
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "eval_loss": 0.6410338282585144,
4
+ "eval_runtime": 226.5313,
5
+ "eval_samples_per_second": 50.214,
6
+ "eval_steps_per_second": 0.393,
7
+ "total_flos": 2120178393415680.0,
8
+ "train_loss": 0.6170312019321026,
9
+ "train_runtime": 37849.9965,
10
+ "train_samples_per_second": 17.13,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "eval_loss": 0.6410338282585144,
4
+ "eval_runtime": 226.5313,
5
+ "eval_samples_per_second": 50.214,
6
+ "eval_steps_per_second": 0.393
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9982238010657194,
3
+ "total_flos": 2120178393415680.0,
4
+ "train_loss": 0.6170312019321026,
5
+ "train_runtime": 37849.9965,
6
+ "train_samples_per_second": 17.13,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,948 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9982238010657194,
5
+ "eval_steps": 500,
6
+ "global_step": 1266,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.023682652457075192,
13
+ "grad_norm": 1.816531801378568,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.9186,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.047365304914150384,
20
+ "grad_norm": 1.3574653188634527,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.8003,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07104795737122557,
27
+ "grad_norm": 1.5669400481998332,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.7709,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09473060982830077,
34
+ "grad_norm": 1.693017888571637,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7443,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11841326228537596,
41
+ "grad_norm": 1.4722298325308145,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.7337,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14209591474245115,
48
+ "grad_norm": 0.6948406074694712,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7183,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16577856719952636,
55
+ "grad_norm": 1.0658863949894195,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7146,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18946121965660154,
62
+ "grad_norm": 0.6741474876420499,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6984,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.21314387211367672,
69
+ "grad_norm": 1.0831273123966574,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.7001,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.23682652457075193,
76
+ "grad_norm": 1.6635919094429064,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6886,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2605091770278271,
83
+ "grad_norm": 0.8636474722702722,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.686,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2841918294849023,
90
+ "grad_norm": 0.7926351502503324,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6817,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.30787448194197753,
97
+ "grad_norm": 0.5901918000373718,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.692,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3315571343990527,
104
+ "grad_norm": 0.6148247600757576,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6817,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3552397868561279,
111
+ "grad_norm": 0.5101477855796542,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6853,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3789224393132031,
118
+ "grad_norm": 0.5704569063807804,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6737,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.40260509177027826,
125
+ "grad_norm": 0.6027371888875237,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6774,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.42628774422735344,
132
+ "grad_norm": 0.6683781224223748,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6688,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4499703966844287,
139
+ "grad_norm": 0.5016914580041181,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.676,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.47365304914150386,
146
+ "grad_norm": 0.5452609890724252,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.667,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.49733570159857904,
153
+ "grad_norm": 0.6510845954594989,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6691,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5210183540556542,
160
+ "grad_norm": 0.5161096609174309,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6666,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5447010065127295,
167
+ "grad_norm": 0.48148888185279093,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6705,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5683836589698046,
174
+ "grad_norm": 0.646541503129204,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6615,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5920663114268798,
181
+ "grad_norm": 0.5813160913392431,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6761,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6157489638839551,
188
+ "grad_norm": 0.6228219376370357,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6645,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6394316163410302,
195
+ "grad_norm": 0.532227126517761,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6634,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6631142687981054,
202
+ "grad_norm": 0.5335777471459527,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6707,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6867969212551805,
209
+ "grad_norm": 0.5859556398404715,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6595,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7104795737122558,
216
+ "grad_norm": 0.678661754791658,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6635,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7341622261693309,
223
+ "grad_norm": 0.5182311919791005,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6546,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7578448786264061,
230
+ "grad_norm": 0.5694216979735989,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6541,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7815275310834814,
237
+ "grad_norm": 0.5806274782090943,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6581,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8052101835405565,
244
+ "grad_norm": 0.57308874729709,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.661,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8288928359976317,
251
+ "grad_norm": 0.48566616576972127,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6514,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8525754884547069,
258
+ "grad_norm": 0.5177674580432304,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6521,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8762581409117821,
265
+ "grad_norm": 0.7662128776841642,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6521,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8999407933688574,
272
+ "grad_norm": 0.7194268558213192,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.6527,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9236234458259325,
279
+ "grad_norm": 0.5317577993198188,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.6462,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9473060982830077,
286
+ "grad_norm": 0.6130071094405808,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6536,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9709887507400828,
293
+ "grad_norm": 0.5054262813488729,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.651,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9946714031971581,
300
+ "grad_norm": 0.5216224953516784,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.6504,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9994079336885732,
307
+ "eval_loss": 0.6479789018630981,
308
+ "eval_runtime": 225.9605,
309
+ "eval_samples_per_second": 50.341,
310
+ "eval_steps_per_second": 0.394,
311
+ "step": 422
312
+ },
313
+ {
314
+ "epoch": 1.0183540556542332,
315
+ "grad_norm": 0.6448097818743337,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6143,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.0420367081113084,
322
+ "grad_norm": 0.5557066787595923,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.6112,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0657193605683837,
329
+ "grad_norm": 0.6491926304674187,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5991,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.089402013025459,
336
+ "grad_norm": 0.5604079979316403,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6058,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1130846654825342,
343
+ "grad_norm": 0.5772544741030392,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6075,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.1367673179396092,
350
+ "grad_norm": 0.4792859571457941,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.6064,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1604499703966844,
357
+ "grad_norm": 0.5655936542523597,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5994,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1841326228537596,
364
+ "grad_norm": 0.7349705127084367,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6097,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.2078152753108349,
371
+ "grad_norm": 0.5763999652681121,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.6135,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.2314979277679101,
378
+ "grad_norm": 0.6420586148204931,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6132,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2551805802249851,
385
+ "grad_norm": 0.5788998804332586,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.6004,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2788632326820604,
392
+ "grad_norm": 0.536638979204567,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.5964,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.3025458851391356,
399
+ "grad_norm": 0.555896270898685,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6059,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.3262285375962108,
406
+ "grad_norm": 0.523881024195525,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6065,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.349911190053286,
413
+ "grad_norm": 0.5750577354690338,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.6056,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.373593842510361,
420
+ "grad_norm": 0.5341219344965924,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6038,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3972764949674363,
427
+ "grad_norm": 0.53243695293744,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6045,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4209591474245116,
434
+ "grad_norm": 0.5160793462220815,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6109,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.4446417998815868,
441
+ "grad_norm": 0.519786480340386,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6047,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.468324452338662,
448
+ "grad_norm": 0.5176998387507717,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6025,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.492007104795737,
455
+ "grad_norm": 0.5326374678084742,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6058,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.5156897572528123,
462
+ "grad_norm": 0.6814294915516854,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.6018,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.5393724097098875,
469
+ "grad_norm": 0.5067893932415504,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.6093,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.5630550621669625,
476
+ "grad_norm": 0.6391993779464403,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.6045,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.586737714624038,
483
+ "grad_norm": 0.5670108575671168,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6046,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.610420367081113,
490
+ "grad_norm": 0.5200973369062145,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6083,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.6341030195381883,
497
+ "grad_norm": 0.49629609919819867,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.6102,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.6577856719952635,
504
+ "grad_norm": 0.5411312975043618,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6058,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.6814683244523385,
511
+ "grad_norm": 0.6511065530477933,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6061,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.705150976909414,
518
+ "grad_norm": 0.5356040304164067,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.608,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.728833629366489,
525
+ "grad_norm": 0.5044332661887174,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.6067,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.7525162818235642,
532
+ "grad_norm": 0.5679268459481845,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.6044,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.7761989342806395,
539
+ "grad_norm": 0.5041966525853055,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6012,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7998815867377145,
546
+ "grad_norm": 0.622815173397146,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.6064,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.82356423919479,
553
+ "grad_norm": 0.6105310434875696,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.5993,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.847246891651865,
560
+ "grad_norm": 0.6478637621549127,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6083,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.8709295441089402,
567
+ "grad_norm": 0.5288770221223392,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6064,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.8946121965660154,
574
+ "grad_norm": 0.6310494125165369,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6054,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.9182948490230904,
581
+ "grad_norm": 0.6224434949310766,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.6014,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.941977501480166,
588
+ "grad_norm": 0.5690732220009218,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.6026,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.965660153937241,
595
+ "grad_norm": 0.5819642741301115,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.6056,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.9893428063943162,
602
+ "grad_norm": 0.4867726663758881,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.6039,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9988158673771461,
609
+ "eval_loss": 0.6381043791770935,
610
+ "eval_runtime": 226.3666,
611
+ "eval_samples_per_second": 50.25,
612
+ "eval_steps_per_second": 0.393,
613
+ "step": 844
614
+ },
615
+ {
616
+ "epoch": 2.0130254588513914,
617
+ "grad_norm": 0.799137975988829,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5789,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.0367081113084664,
624
+ "grad_norm": 0.5651415058987638,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5532,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.060390763765542,
631
+ "grad_norm": 0.6785997009798781,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5528,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.084073416222617,
638
+ "grad_norm": 0.589434711398729,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5581,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.1077560686796923,
645
+ "grad_norm": 0.6120240073948606,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5578,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.1314387211367674,
652
+ "grad_norm": 0.5356757525158238,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5564,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.1551213735938424,
659
+ "grad_norm": 0.6532444755899165,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5609,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.178804026050918,
666
+ "grad_norm": 0.7762170235905984,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.5588,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.202486678507993,
673
+ "grad_norm": 0.5110672320160398,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5611,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.2261693309650683,
680
+ "grad_norm": 0.5175930179811897,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5592,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.2498519834221433,
687
+ "grad_norm": 0.5781036208277457,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.5567,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.2735346358792183,
694
+ "grad_norm": 0.638650838885228,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5566,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.297217288336294,
701
+ "grad_norm": 0.5928010322906232,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5595,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.320899940793369,
708
+ "grad_norm": 0.6471191913384154,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5618,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.3445825932504443,
715
+ "grad_norm": 0.5439480452105689,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5623,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.3682652457075193,
722
+ "grad_norm": 0.5616150107415377,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.559,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.3919478981645943,
729
+ "grad_norm": 0.6063862680614267,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5584,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.4156305506216698,
736
+ "grad_norm": 0.6514652096821626,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.564,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.4393132030787448,
743
+ "grad_norm": 0.5978550068800899,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.5648,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.4629958555358202,
750
+ "grad_norm": 0.5389659551331341,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.557,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.4866785079928952,
757
+ "grad_norm": 0.49728611593057986,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.5563,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.5103611604499703,
764
+ "grad_norm": 0.5602610558768696,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.5628,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.5340438129070457,
771
+ "grad_norm": 0.6603901062892502,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5576,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.5577264653641207,
778
+ "grad_norm": 0.6506359439942624,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.5567,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.581409117821196,
785
+ "grad_norm": 0.6081261618456771,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.5622,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.605091770278271,
792
+ "grad_norm": 0.5583840013876924,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5641,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.6287744227353462,
799
+ "grad_norm": 0.677285075920703,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.5676,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.6524570751924217,
806
+ "grad_norm": 0.5283556684105596,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.5609,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.6761397276494967,
813
+ "grad_norm": 0.5373459018769577,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5619,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.699822380106572,
820
+ "grad_norm": 0.5544732747898201,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5577,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.723505032563647,
827
+ "grad_norm": 0.5842636221616775,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.5644,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.747187685020722,
834
+ "grad_norm": 0.5195933914819354,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.5669,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.7708703374777977,
841
+ "grad_norm": 0.6191768570542974,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5647,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.7945529899348727,
848
+ "grad_norm": 0.5155223116029976,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5681,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.818235642391948,
855
+ "grad_norm": 0.6371568852312499,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5604,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.841918294849023,
862
+ "grad_norm": 0.6170324836320265,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.5634,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.865600947306098,
869
+ "grad_norm": 0.5196345014766655,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.5585,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.8892835997631736,
876
+ "grad_norm": 0.5582532842634907,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5681,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.9129662522202486,
883
+ "grad_norm": 0.5370930409847251,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5622,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.936648904677324,
890
+ "grad_norm": 0.5553114047738701,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.5698,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.960331557134399,
897
+ "grad_norm": 0.5109477407586265,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.5651,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.984014209591474,
904
+ "grad_norm": 0.535258137027712,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.5552,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.9982238010657194,
911
+ "eval_loss": 0.6410338282585144,
912
+ "eval_runtime": 226.7918,
913
+ "eval_samples_per_second": 50.156,
914
+ "eval_steps_per_second": 0.392,
915
+ "step": 1266
916
+ },
917
+ {
918
+ "epoch": 2.9982238010657194,
919
+ "step": 1266,
920
+ "total_flos": 2120178393415680.0,
921
+ "train_loss": 0.6170312019321026,
922
+ "train_runtime": 37849.9965,
923
+ "train_samples_per_second": 17.13,
924
+ "train_steps_per_second": 0.033
925
+ }
926
+ ],
927
+ "logging_steps": 10,
928
+ "max_steps": 1266,
929
+ "num_input_tokens_seen": 0,
930
+ "num_train_epochs": 3,
931
+ "save_steps": 500,
932
+ "stateful_callbacks": {
933
+ "TrainerControl": {
934
+ "args": {
935
+ "should_epoch_stop": false,
936
+ "should_evaluate": false,
937
+ "should_log": false,
938
+ "should_save": true,
939
+ "should_training_stop": true
940
+ },
941
+ "attributes": {}
942
+ }
943
+ },
944
+ "total_flos": 2120178393415680.0,
945
+ "train_batch_size": 8,
946
+ "trial_name": null,
947
+ "trial_params": null
948
+ }
training_eval_loss.png ADDED
training_loss.png ADDED