sedrickkeh commited on
Commit
2729b72
·
verified ·
1 Parent(s): 4dd3850

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama2
4
  base_model: meta-llama/Llama-2-7b-hf
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: llama2_oh_teknium_scaling_down_random_0.8
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama2_oh_teknium_scaling_down_random_0.8
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.5802
21
 
 
4
  base_model: meta-llama/Llama-2-7b-hf
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: llama2_oh_teknium_scaling_down_random_0.8
 
16
 
17
  # llama2_oh_teknium_scaling_down_random_0.8
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the mlfoundations-dev/oh_teknium_scaling_down_random_0.8 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.5802
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9987463435018804,
3
+ "eval_loss": 0.5801695585250854,
4
+ "eval_runtime": 299.5634,
5
+ "eval_samples_per_second": 26.899,
6
+ "eval_steps_per_second": 0.421,
7
+ "total_flos": 1502299029504000.0,
8
+ "train_loss": 0.5779525436286543,
9
+ "train_runtime": 48927.2984,
10
+ "train_samples_per_second": 9.387,
11
+ "train_steps_per_second": 0.018
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9987463435018804,
3
+ "eval_loss": 0.5801695585250854,
4
+ "eval_runtime": 299.5634,
5
+ "eval_samples_per_second": 26.899,
6
+ "eval_steps_per_second": 0.421
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9987463435018804,
3
+ "total_flos": 1502299029504000.0,
4
+ "train_loss": 0.5779525436286543,
5
+ "train_runtime": 48927.2984,
6
+ "train_samples_per_second": 9.387,
7
+ "train_steps_per_second": 0.018
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,689 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9987463435018804,
5
+ "eval_steps": 500,
6
+ "global_step": 897,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03343083994985374,
13
+ "grad_norm": 0.465455666565108,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7858,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.06686167989970748,
20
+ "grad_norm": 0.3429798043291091,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7098,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.10029251984956122,
27
+ "grad_norm": 0.250252156565685,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6871,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.13372335979941496,
34
+ "grad_norm": 0.24107134988270987,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6681,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.1671541997492687,
41
+ "grad_norm": 0.21806581310258916,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6633,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.20058503969912245,
48
+ "grad_norm": 0.22386397438534855,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.656,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.2340158796489762,
55
+ "grad_norm": 0.2243183236649086,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.651,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.26744671959882993,
62
+ "grad_norm": 0.2326019524196413,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6519,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.30087755954868367,
69
+ "grad_norm": 0.22646799402642662,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6437,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3343083994985374,
76
+ "grad_norm": 0.23209116325221912,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6392,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.36773923944839115,
83
+ "grad_norm": 0.22907297757221068,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6329,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4011700793982449,
90
+ "grad_norm": 0.22166520300122122,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.632,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.43460091934809864,
97
+ "grad_norm": 0.24079199771015034,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6194,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.4680317592979524,
104
+ "grad_norm": 0.23095015490130272,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6172,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5014625992478061,
111
+ "grad_norm": 0.22783375101823392,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6214,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.5348934391976599,
118
+ "grad_norm": 0.25829648332235927,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6194,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.5683242791475136,
125
+ "grad_norm": 0.23696584513088445,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6159,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.6017551190973673,
132
+ "grad_norm": 0.24388808303408932,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6177,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.6351859590472211,
139
+ "grad_norm": 0.2324052967281535,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6084,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.6686167989970748,
146
+ "grad_norm": 0.23047425341157954,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6074,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.7020476389469286,
153
+ "grad_norm": 0.23604251749457175,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6044,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.7354784788967823,
160
+ "grad_norm": 0.23958101670923093,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6061,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.768909318846636,
167
+ "grad_norm": 0.256749568385238,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6052,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.8023401587964898,
174
+ "grad_norm": 0.2440390616960533,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6003,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.8357709987463435,
181
+ "grad_norm": 0.24502595940912716,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6122,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.8692018386961973,
188
+ "grad_norm": 0.2911977665906095,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.6069,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.902632678646051,
195
+ "grad_norm": 0.2535787166110667,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6044,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.9360635185959048,
202
+ "grad_norm": 0.23815820801537682,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6051,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.9694943585457585,
209
+ "grad_norm": 0.24190392037693448,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6027,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.9995821145006268,
216
+ "eval_loss": 0.6069105863571167,
217
+ "eval_runtime": 297.1615,
218
+ "eval_samples_per_second": 27.117,
219
+ "eval_steps_per_second": 0.424,
220
+ "step": 299
221
+ },
222
+ {
223
+ "epoch": 1.0029251984956122,
224
+ "grad_norm": 0.7245726510213032,
225
+ "learning_rate": 5e-06,
226
+ "loss": 0.6553,
227
+ "step": 300
228
+ },
229
+ {
230
+ "epoch": 1.036356038445466,
231
+ "grad_norm": 0.27066472051217805,
232
+ "learning_rate": 5e-06,
233
+ "loss": 0.5696,
234
+ "step": 310
235
+ },
236
+ {
237
+ "epoch": 1.0697868783953197,
238
+ "grad_norm": 0.23624656831823893,
239
+ "learning_rate": 5e-06,
240
+ "loss": 0.5745,
241
+ "step": 320
242
+ },
243
+ {
244
+ "epoch": 1.1032177183451735,
245
+ "grad_norm": 0.24234271753426892,
246
+ "learning_rate": 5e-06,
247
+ "loss": 0.5736,
248
+ "step": 330
249
+ },
250
+ {
251
+ "epoch": 1.1366485582950272,
252
+ "grad_norm": 0.24649256824581395,
253
+ "learning_rate": 5e-06,
254
+ "loss": 0.5709,
255
+ "step": 340
256
+ },
257
+ {
258
+ "epoch": 1.170079398244881,
259
+ "grad_norm": 0.25334180595905853,
260
+ "learning_rate": 5e-06,
261
+ "loss": 0.5644,
262
+ "step": 350
263
+ },
264
+ {
265
+ "epoch": 1.2035102381947347,
266
+ "grad_norm": 0.26316949320762967,
267
+ "learning_rate": 5e-06,
268
+ "loss": 0.5663,
269
+ "step": 360
270
+ },
271
+ {
272
+ "epoch": 1.2369410781445884,
273
+ "grad_norm": 0.2605173667942115,
274
+ "learning_rate": 5e-06,
275
+ "loss": 0.5722,
276
+ "step": 370
277
+ },
278
+ {
279
+ "epoch": 1.2703719180944422,
280
+ "grad_norm": 0.2312966165635924,
281
+ "learning_rate": 5e-06,
282
+ "loss": 0.576,
283
+ "step": 380
284
+ },
285
+ {
286
+ "epoch": 1.303802758044296,
287
+ "grad_norm": 0.23702825129111396,
288
+ "learning_rate": 5e-06,
289
+ "loss": 0.5687,
290
+ "step": 390
291
+ },
292
+ {
293
+ "epoch": 1.3372335979941496,
294
+ "grad_norm": 0.2308522015632982,
295
+ "learning_rate": 5e-06,
296
+ "loss": 0.5641,
297
+ "step": 400
298
+ },
299
+ {
300
+ "epoch": 1.3706644379440034,
301
+ "grad_norm": 0.24923916946383898,
302
+ "learning_rate": 5e-06,
303
+ "loss": 0.5645,
304
+ "step": 410
305
+ },
306
+ {
307
+ "epoch": 1.4040952778938571,
308
+ "grad_norm": 0.2546839256609035,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.5688,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.4375261178437109,
315
+ "grad_norm": 0.2415609699087316,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.5646,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.4709569577935646,
322
+ "grad_norm": 0.22725529712872503,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.5678,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.5043877977434184,
329
+ "grad_norm": 0.26364584659408963,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.5715,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.537818637693272,
336
+ "grad_norm": 0.23719272373058128,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.5666,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.5712494776431258,
343
+ "grad_norm": 0.23886844481475153,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.5601,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.6046803175929796,
350
+ "grad_norm": 0.23337130900300732,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5584,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.6381111575428333,
357
+ "grad_norm": 0.23593118182043984,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.5708,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.671541997492687,
364
+ "grad_norm": 0.247965831834247,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5713,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.7049728374425408,
371
+ "grad_norm": 0.252355451082656,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5628,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.7384036773923945,
378
+ "grad_norm": 0.24093218685685644,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.5655,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.7718345173422483,
385
+ "grad_norm": 0.2297986641883851,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.5599,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.805265357292102,
392
+ "grad_norm": 0.2355282077674634,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.5598,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.8386961972419558,
399
+ "grad_norm": 0.23565926815064536,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.5675,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.8721270371918095,
406
+ "grad_norm": 0.22987684078185938,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.5678,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.9055578771416632,
413
+ "grad_norm": 0.2391922454011988,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.5655,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.938988717091517,
420
+ "grad_norm": 0.2402971182270538,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.5588,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.9724195570413707,
427
+ "grad_norm": 0.2431684190506289,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.5543,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.9991642290012537,
434
+ "eval_loss": 0.5879825353622437,
435
+ "eval_runtime": 297.739,
436
+ "eval_samples_per_second": 27.064,
437
+ "eval_steps_per_second": 0.423,
438
+ "step": 598
439
+ },
440
+ {
441
+ "epoch": 2.0058503969912245,
442
+ "grad_norm": 0.30898456346377806,
443
+ "learning_rate": 5e-06,
444
+ "loss": 0.6129,
445
+ "step": 600
446
+ },
447
+ {
448
+ "epoch": 2.039281236941078,
449
+ "grad_norm": 0.3080648052374505,
450
+ "learning_rate": 5e-06,
451
+ "loss": 0.5387,
452
+ "step": 610
453
+ },
454
+ {
455
+ "epoch": 2.072712076890932,
456
+ "grad_norm": 0.2598126484485968,
457
+ "learning_rate": 5e-06,
458
+ "loss": 0.5284,
459
+ "step": 620
460
+ },
461
+ {
462
+ "epoch": 2.1061429168407857,
463
+ "grad_norm": 0.2409928257299915,
464
+ "learning_rate": 5e-06,
465
+ "loss": 0.5252,
466
+ "step": 630
467
+ },
468
+ {
469
+ "epoch": 2.1395737567906394,
470
+ "grad_norm": 0.2401108659858156,
471
+ "learning_rate": 5e-06,
472
+ "loss": 0.5296,
473
+ "step": 640
474
+ },
475
+ {
476
+ "epoch": 2.173004596740493,
477
+ "grad_norm": 0.23872635023154934,
478
+ "learning_rate": 5e-06,
479
+ "loss": 0.5325,
480
+ "step": 650
481
+ },
482
+ {
483
+ "epoch": 2.206435436690347,
484
+ "grad_norm": 0.24878774215286806,
485
+ "learning_rate": 5e-06,
486
+ "loss": 0.5253,
487
+ "step": 660
488
+ },
489
+ {
490
+ "epoch": 2.2398662766402007,
491
+ "grad_norm": 0.25564499539942276,
492
+ "learning_rate": 5e-06,
493
+ "loss": 0.5304,
494
+ "step": 670
495
+ },
496
+ {
497
+ "epoch": 2.2732971165900544,
498
+ "grad_norm": 0.24837362080494388,
499
+ "learning_rate": 5e-06,
500
+ "loss": 0.5253,
501
+ "step": 680
502
+ },
503
+ {
504
+ "epoch": 2.306727956539908,
505
+ "grad_norm": 0.25514616974853815,
506
+ "learning_rate": 5e-06,
507
+ "loss": 0.5293,
508
+ "step": 690
509
+ },
510
+ {
511
+ "epoch": 2.340158796489762,
512
+ "grad_norm": 0.24759745020055693,
513
+ "learning_rate": 5e-06,
514
+ "loss": 0.5423,
515
+ "step": 700
516
+ },
517
+ {
518
+ "epoch": 2.3735896364396156,
519
+ "grad_norm": 0.2621553483703068,
520
+ "learning_rate": 5e-06,
521
+ "loss": 0.5281,
522
+ "step": 710
523
+ },
524
+ {
525
+ "epoch": 2.4070204763894694,
526
+ "grad_norm": 0.25103305898665595,
527
+ "learning_rate": 5e-06,
528
+ "loss": 0.5262,
529
+ "step": 720
530
+ },
531
+ {
532
+ "epoch": 2.440451316339323,
533
+ "grad_norm": 0.24616309812116494,
534
+ "learning_rate": 5e-06,
535
+ "loss": 0.5332,
536
+ "step": 730
537
+ },
538
+ {
539
+ "epoch": 2.473882156289177,
540
+ "grad_norm": 0.26292695360317175,
541
+ "learning_rate": 5e-06,
542
+ "loss": 0.5286,
543
+ "step": 740
544
+ },
545
+ {
546
+ "epoch": 2.5073129962390306,
547
+ "grad_norm": 0.2556297707505491,
548
+ "learning_rate": 5e-06,
549
+ "loss": 0.5363,
550
+ "step": 750
551
+ },
552
+ {
553
+ "epoch": 2.5407438361888843,
554
+ "grad_norm": 0.2706578070225452,
555
+ "learning_rate": 5e-06,
556
+ "loss": 0.5382,
557
+ "step": 760
558
+ },
559
+ {
560
+ "epoch": 2.574174676138738,
561
+ "grad_norm": 0.27845630575003893,
562
+ "learning_rate": 5e-06,
563
+ "loss": 0.5289,
564
+ "step": 770
565
+ },
566
+ {
567
+ "epoch": 2.607605516088592,
568
+ "grad_norm": 0.2669132752987619,
569
+ "learning_rate": 5e-06,
570
+ "loss": 0.5233,
571
+ "step": 780
572
+ },
573
+ {
574
+ "epoch": 2.6410363560384456,
575
+ "grad_norm": 0.2586067280825215,
576
+ "learning_rate": 5e-06,
577
+ "loss": 0.5271,
578
+ "step": 790
579
+ },
580
+ {
581
+ "epoch": 2.6744671959882993,
582
+ "grad_norm": 0.2559890631197339,
583
+ "learning_rate": 5e-06,
584
+ "loss": 0.5361,
585
+ "step": 800
586
+ },
587
+ {
588
+ "epoch": 2.707898035938153,
589
+ "grad_norm": 0.24748957802636362,
590
+ "learning_rate": 5e-06,
591
+ "loss": 0.5317,
592
+ "step": 810
593
+ },
594
+ {
595
+ "epoch": 2.7413288758880068,
596
+ "grad_norm": 0.24421486038345067,
597
+ "learning_rate": 5e-06,
598
+ "loss": 0.536,
599
+ "step": 820
600
+ },
601
+ {
602
+ "epoch": 2.7747597158378605,
603
+ "grad_norm": 0.27039350090679615,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.5294,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.8081905557877143,
610
+ "grad_norm": 0.25751063997110557,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.5326,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.841621395737568,
617
+ "grad_norm": 0.24765515477831007,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5226,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.8750522356874217,
624
+ "grad_norm": 0.24426800544335395,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5254,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.9084830756372755,
631
+ "grad_norm": 0.24614474825906446,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5322,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.9419139155871292,
638
+ "grad_norm": 0.24941400328376895,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.524,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.975344755536983,
645
+ "grad_norm": 0.2815487127839382,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.5279,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.9987463435018804,
652
+ "eval_loss": 0.5801695585250854,
653
+ "eval_runtime": 299.2301,
654
+ "eval_samples_per_second": 26.929,
655
+ "eval_steps_per_second": 0.421,
656
+ "step": 897
657
+ },
658
+ {
659
+ "epoch": 2.9987463435018804,
660
+ "step": 897,
661
+ "total_flos": 1502299029504000.0,
662
+ "train_loss": 0.5779525436286543,
663
+ "train_runtime": 48927.2984,
664
+ "train_samples_per_second": 9.387,
665
+ "train_steps_per_second": 0.018
666
+ }
667
+ ],
668
+ "logging_steps": 10,
669
+ "max_steps": 897,
670
+ "num_input_tokens_seen": 0,
671
+ "num_train_epochs": 3,
672
+ "save_steps": 500,
673
+ "stateful_callbacks": {
674
+ "TrainerControl": {
675
+ "args": {
676
+ "should_epoch_stop": false,
677
+ "should_evaluate": false,
678
+ "should_log": false,
679
+ "should_save": true,
680
+ "should_training_stop": true
681
+ },
682
+ "attributes": {}
683
+ }
684
+ },
685
+ "total_flos": 1502299029504000.0,
686
+ "train_batch_size": 8,
687
+ "trial_name": null,
688
+ "trial_params": null
689
+ }
training_eval_loss.png ADDED
training_loss.png ADDED