sedrickkeh commited on
Commit
ee5f8f5
·
verified ·
1 Parent(s): 8c1d199

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_evol_instruct_70k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_original_wo_evol_instruct_70k
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: 0.6157
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_evol_instruct_70k
 
16
 
17
  # OH_original_wo_evol_instruct_70k
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_evol_instruct_70k dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6157
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.992874109263658,
3
+ "eval_loss": 0.6157404184341431,
4
+ "eval_runtime": 170.8534,
5
+ "eval_samples_per_second": 49.785,
6
+ "eval_steps_per_second": 0.392,
7
+ "total_flos": 1582491437629440.0,
8
+ "train_loss": 0.5832562999119835,
9
+ "train_runtime": 28511.6322,
10
+ "train_samples_per_second": 17.004,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.992874109263658,
3
+ "eval_loss": 0.6157404184341431,
4
+ "eval_runtime": 170.8534,
5
+ "eval_samples_per_second": 49.785,
6
+ "eval_steps_per_second": 0.392
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.992874109263658,
3
+ "total_flos": 1582491437629440.0,
4
+ "train_loss": 0.5832562999119835,
5
+ "train_runtime": 28511.6322,
6
+ "train_samples_per_second": 17.004,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,724 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.992874109263658,
5
+ "eval_steps": 500,
6
+ "global_step": 945,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03167062549485352,
13
+ "grad_norm": 1.8530284877370395,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.8166,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06334125098970704,
20
+ "grad_norm": 1.5337420189302975,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7464,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.09501187648456057,
27
+ "grad_norm": 1.4029937472724519,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.7243,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.12668250197941408,
34
+ "grad_norm": 0.9360700334222073,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7146,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1583531274742676,
41
+ "grad_norm": 0.994137693760135,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6895,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.19002375296912113,
48
+ "grad_norm": 0.9347536063077458,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.6778,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.22169437846397466,
55
+ "grad_norm": 1.4913361116122625,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.6594,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.25336500395882816,
62
+ "grad_norm": 0.7126258978453617,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6637,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2850356294536817,
69
+ "grad_norm": 0.9899069063293856,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6456,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3167062549485352,
76
+ "grad_norm": 0.8045731477224973,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6537,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.34837688044338877,
83
+ "grad_norm": 0.7578866653732541,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6481,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.38004750593824227,
90
+ "grad_norm": 0.5676407147308244,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6419,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.4117181314330958,
97
+ "grad_norm": 0.8078622210774858,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6479,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.4433887569279493,
104
+ "grad_norm": 0.7647299971015771,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6439,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.4750593824228028,
111
+ "grad_norm": 0.5575084199732572,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6388,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5067300079176563,
118
+ "grad_norm": 0.5128045187828547,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6347,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5384006334125099,
125
+ "grad_norm": 0.8861637952775342,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6354,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.5700712589073634,
132
+ "grad_norm": 0.7708516251715861,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6365,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.601741884402217,
139
+ "grad_norm": 0.6980158820500171,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6339,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6334125098970704,
146
+ "grad_norm": 0.5994527923990384,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6384,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.665083135391924,
153
+ "grad_norm": 1.2967423762938355,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6369,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.6967537608867775,
160
+ "grad_norm": 0.47535091611506025,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6321,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.728424386381631,
167
+ "grad_norm": 0.6353037224955166,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6241,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.7600950118764845,
174
+ "grad_norm": 0.6601833755256151,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.623,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.7917656373713381,
181
+ "grad_norm": 0.6122026802056224,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6263,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8234362628661916,
188
+ "grad_norm": 0.5075094381024849,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6301,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.8551068883610451,
195
+ "grad_norm": 0.5422031773802576,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6292,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.8867775138558986,
202
+ "grad_norm": 0.42516469360864606,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6177,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9184481393507522,
209
+ "grad_norm": 0.7465232508313683,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6197,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.9501187648456056,
216
+ "grad_norm": 0.5164060465761252,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6286,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.9817893903404592,
223
+ "grad_norm": 0.6125601748565044,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6301,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.997624703087886,
230
+ "eval_loss": 0.6208310723304749,
231
+ "eval_runtime": 170.2387,
232
+ "eval_samples_per_second": 49.965,
233
+ "eval_steps_per_second": 0.394,
234
+ "step": 315
235
+ },
236
+ {
237
+ "epoch": 1.0134600158353126,
238
+ "grad_norm": 0.8577950377026092,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.6042,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.0451306413301662,
245
+ "grad_norm": 0.563239613051996,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.5769,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.0768012668250198,
252
+ "grad_norm": 0.5011250455738395,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.5753,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.1084718923198733,
259
+ "grad_norm": 0.507779510609032,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.5755,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.1401425178147269,
266
+ "grad_norm": 0.5864390033721468,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.5731,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.1718131433095804,
273
+ "grad_norm": 0.5651111499269338,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.5687,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.203483768804434,
280
+ "grad_norm": 0.6150558670403593,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.5729,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.2351543942992875,
287
+ "grad_norm": 0.5808136283436993,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.5718,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.2668250197941409,
294
+ "grad_norm": 0.5830305205374973,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.5761,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.2984956452889944,
301
+ "grad_norm": 0.5467014072656838,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.5799,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.330166270783848,
308
+ "grad_norm": 0.5214522227982674,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.5734,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.3618368962787015,
315
+ "grad_norm": 0.7855825418949094,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.5712,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.393507521773555,
322
+ "grad_norm": 0.5656871920545978,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.576,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.4251781472684084,
329
+ "grad_norm": 0.5944245365102998,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5708,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.4568487727632622,
336
+ "grad_norm": 0.5333261966632318,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5671,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.4885193982581155,
343
+ "grad_norm": 0.491104016024968,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5743,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.520190023752969,
350
+ "grad_norm": 0.5014163060947014,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5728,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.5518606492478226,
357
+ "grad_norm": 0.4892383437610088,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5802,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.5835312747426762,
364
+ "grad_norm": 0.4989580296588211,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5751,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.6152019002375297,
371
+ "grad_norm": 0.616735446474154,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5716,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.646872525732383,
378
+ "grad_norm": 0.5387044899734632,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.5751,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.6785431512272369,
385
+ "grad_norm": 0.5526914425760312,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.5684,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.7102137767220902,
392
+ "grad_norm": 0.6545410316398991,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.5702,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.7418844022169437,
399
+ "grad_norm": 0.5254133456615973,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.5674,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.7735550277117973,
406
+ "grad_norm": 0.521939360967283,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.5724,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.8052256532066508,
413
+ "grad_norm": 0.463070184825861,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.5818,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.8368962787015044,
420
+ "grad_norm": 0.6381561992890791,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.5688,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.8685669041963577,
427
+ "grad_norm": 0.6496360141809046,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.5646,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.9002375296912115,
434
+ "grad_norm": 0.5324989809239741,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.566,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.9319081551860648,
441
+ "grad_norm": 0.5111765382529705,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.5708,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.9635787806809184,
448
+ "grad_norm": 0.5610135178229989,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.574,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.995249406175772,
455
+ "grad_norm": 0.6915334000048331,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.58,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.9984164687252575,
462
+ "eval_loss": 0.6117470860481262,
463
+ "eval_runtime": 171.4849,
464
+ "eval_samples_per_second": 49.602,
465
+ "eval_steps_per_second": 0.391,
466
+ "step": 631
467
+ },
468
+ {
469
+ "epoch": 2.0269200316706253,
470
+ "grad_norm": 0.616676539774963,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.528,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.058590657165479,
477
+ "grad_norm": 0.6073136045120692,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.5195,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.0902612826603324,
484
+ "grad_norm": 0.5470687590939235,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.5258,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.121931908155186,
491
+ "grad_norm": 0.5476384369380188,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.5207,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.1536025336500395,
498
+ "grad_norm": 0.5807654736471419,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.5229,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.1852731591448933,
505
+ "grad_norm": 0.5658725818639244,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.5155,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.2169437846397466,
512
+ "grad_norm": 0.5270348810540799,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5257,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.2486144101346,
519
+ "grad_norm": 0.6710965861689625,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5148,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.2802850356294537,
526
+ "grad_norm": 0.5096235564504402,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5181,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.311955661124307,
533
+ "grad_norm": 0.5550769313636378,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.5171,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.343626286619161,
540
+ "grad_norm": 0.7122071616039661,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.5181,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.375296912114014,
547
+ "grad_norm": 0.5158288008674774,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.5255,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.406967537608868,
554
+ "grad_norm": 0.5744842064968558,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5232,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.4386381631037213,
561
+ "grad_norm": 0.48569927712881583,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5231,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.470308788598575,
568
+ "grad_norm": 0.6323853806061133,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.5199,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.5019794140934284,
575
+ "grad_norm": 0.5506449580962853,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.5192,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.5336500395882817,
582
+ "grad_norm": 0.4790039532718334,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.5179,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.5653206650831355,
589
+ "grad_norm": 0.5390096335172841,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.5269,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.596991290577989,
596
+ "grad_norm": 0.5217848609501268,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.5229,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.6286619160728426,
603
+ "grad_norm": 0.5196866879306132,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.5217,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.660332541567696,
610
+ "grad_norm": 0.5333118708551611,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.525,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.6920031670625493,
617
+ "grad_norm": 0.5483398687319767,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5224,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.723673792557403,
624
+ "grad_norm": 0.5117263088559509,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5283,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.7553444180522564,
631
+ "grad_norm": 0.5377436931762913,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5232,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.78701504354711,
638
+ "grad_norm": 0.5662585202942261,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5274,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.8186856690419635,
645
+ "grad_norm": 0.48954404185612554,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5273,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.850356294536817,
652
+ "grad_norm": 0.5387435059221906,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5181,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.8820269200316706,
659
+ "grad_norm": 0.5630237900783817,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5228,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.9136975455265244,
666
+ "grad_norm": 0.4995116097709295,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.5247,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.9453681710213777,
673
+ "grad_norm": 0.49890480333211984,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.521,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.977038796516231,
680
+ "grad_norm": 0.5217828385490265,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5261,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.992874109263658,
687
+ "eval_loss": 0.6157404184341431,
688
+ "eval_runtime": 171.3558,
689
+ "eval_samples_per_second": 49.639,
690
+ "eval_steps_per_second": 0.391,
691
+ "step": 945
692
+ },
693
+ {
694
+ "epoch": 2.992874109263658,
695
+ "step": 945,
696
+ "total_flos": 1582491437629440.0,
697
+ "train_loss": 0.5832562999119835,
698
+ "train_runtime": 28511.6322,
699
+ "train_samples_per_second": 17.004,
700
+ "train_steps_per_second": 0.033
701
+ }
702
+ ],
703
+ "logging_steps": 10,
704
+ "max_steps": 945,
705
+ "num_input_tokens_seen": 0,
706
+ "num_train_epochs": 3,
707
+ "save_steps": 500,
708
+ "stateful_callbacks": {
709
+ "TrainerControl": {
710
+ "args": {
711
+ "should_epoch_stop": false,
712
+ "should_evaluate": false,
713
+ "should_log": false,
714
+ "should_save": true,
715
+ "should_training_stop": true
716
+ },
717
+ "attributes": {}
718
+ }
719
+ },
720
+ "total_flos": 1582491437629440.0,
721
+ "train_batch_size": 8,
722
+ "trial_name": null,
723
+ "trial_params": null
724
+ }
training_eval_loss.png ADDED
training_loss.png ADDED