sedrickkeh commited on
Commit
28793ce
·
verified ·
1 Parent(s): ddbce7a

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_camel_ai_biology
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # OH_DCFT_V3_wo_camel_ai_biology
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: 0.6422
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_camel_ai_biology
 
16
 
17
  # OH_DCFT_V3_wo_camel_ai_biology
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_camel_ai_biology dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.6422
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9945750452079567,
3
+ "eval_loss": 0.6422178745269775,
4
+ "eval_runtime": 223.8998,
5
+ "eval_samples_per_second": 49.915,
6
+ "eval_steps_per_second": 0.393,
7
+ "total_flos": 2079977499525120.0,
8
+ "train_loss": 0.6134321775029439,
9
+ "train_runtime": 37323.5248,
10
+ "train_samples_per_second": 17.067,
11
+ "train_steps_per_second": 0.033
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9945750452079567,
3
+ "eval_loss": 0.6422178745269775,
4
+ "eval_runtime": 223.8998,
5
+ "eval_samples_per_second": 49.915,
6
+ "eval_steps_per_second": 0.393
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9945750452079567,
3
+ "total_flos": 2079977499525120.0,
4
+ "train_loss": 0.6134321775029439,
5
+ "train_runtime": 37323.5248,
6
+ "train_samples_per_second": 17.067,
7
+ "train_steps_per_second": 0.033
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,934 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9945750452079567,
5
+ "eval_steps": 500,
6
+ "global_step": 1242,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.024110910186859555,
13
+ "grad_norm": 2.685936547429143,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.9133,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04822182037371911,
20
+ "grad_norm": 2.8983680167236696,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7794,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.07233273056057866,
27
+ "grad_norm": 1.4715031186017837,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.759,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09644364074743822,
34
+ "grad_norm": 0.8377570160614484,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.7317,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.12055455093429777,
41
+ "grad_norm": 1.0172390996140888,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.728,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.14466546112115733,
48
+ "grad_norm": 2.076736903100202,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.7065,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16877637130801687,
55
+ "grad_norm": 0.9324814149418421,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.7025,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.19288728149487644,
62
+ "grad_norm": 0.8961533346444337,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.6948,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.21699819168173598,
69
+ "grad_norm": 0.9833679322557037,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.6997,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.24110910186859555,
76
+ "grad_norm": 0.6320425718923794,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.6781,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2652200120554551,
83
+ "grad_norm": 0.8047932595929222,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.6857,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.28933092224231466,
90
+ "grad_norm": 0.6873832051216665,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.6762,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.3134418324291742,
97
+ "grad_norm": 0.8515251273118922,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.6741,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.33755274261603374,
104
+ "grad_norm": 0.6815399625732373,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6786,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3616636528028933,
111
+ "grad_norm": 0.6231823130658575,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.6763,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3857745629897529,
118
+ "grad_norm": 0.552827319574485,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.6711,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.4098854731766124,
125
+ "grad_norm": 0.6826986498299203,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.6706,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.43399638336347196,
132
+ "grad_norm": 0.5574310360062503,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.6659,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.45810729355033153,
139
+ "grad_norm": 0.7613567669157012,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.6658,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4822182037371911,
146
+ "grad_norm": 0.5609659476480818,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.6598,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.5063291139240507,
153
+ "grad_norm": 1.078834895881199,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.6687,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5304400241109102,
160
+ "grad_norm": 0.6016551358752319,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.6667,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5545509342977697,
167
+ "grad_norm": 0.5329067498961892,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.6568,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5786618444846293,
174
+ "grad_norm": 0.5844269800148942,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.6656,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.6027727546714888,
181
+ "grad_norm": 0.713015217035973,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.6584,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.6268836648583485,
188
+ "grad_norm": 0.7063878216983879,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.665,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.650994575045208,
195
+ "grad_norm": 0.50774960805631,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.6615,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6751054852320675,
202
+ "grad_norm": 0.6111313528033431,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.6551,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6992163954189271,
209
+ "grad_norm": 0.6458858962308502,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.6535,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.7233273056057866,
216
+ "grad_norm": 0.6797329430329018,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.6616,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7474382157926461,
223
+ "grad_norm": 1.0271382997748104,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.6593,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7715491259795058,
230
+ "grad_norm": 0.5821025343959978,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.6556,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7956600361663653,
237
+ "grad_norm": 0.575144218324774,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.6522,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.8197709463532248,
244
+ "grad_norm": 0.4992177743591918,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.6472,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.8438818565400844,
251
+ "grad_norm": 0.5518799725500897,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.6486,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8679927667269439,
258
+ "grad_norm": 0.6827706978670125,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.6527,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8921036769138035,
265
+ "grad_norm": 0.5370276906753118,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.6564,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.9162145871006631,
272
+ "grad_norm": 0.5011748190469159,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.648,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.9403254972875226,
279
+ "grad_norm": 0.7289445343800255,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.645,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9644364074743822,
286
+ "grad_norm": 0.5223137931656774,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.6481,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9885473176612417,
293
+ "grad_norm": 0.5702001612329072,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.6417,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9981916817359855,
300
+ "eval_loss": 0.6491908431053162,
301
+ "eval_runtime": 223.3579,
302
+ "eval_samples_per_second": 50.036,
303
+ "eval_steps_per_second": 0.394,
304
+ "step": 414
305
+ },
306
+ {
307
+ "epoch": 1.0126582278481013,
308
+ "grad_norm": 0.6141037997267318,
309
+ "learning_rate": 5e-06,
310
+ "loss": 0.6207,
311
+ "step": 420
312
+ },
313
+ {
314
+ "epoch": 1.0367691380349608,
315
+ "grad_norm": 0.5738222179228437,
316
+ "learning_rate": 5e-06,
317
+ "loss": 0.6073,
318
+ "step": 430
319
+ },
320
+ {
321
+ "epoch": 1.0608800482218204,
322
+ "grad_norm": 0.6152321417799828,
323
+ "learning_rate": 5e-06,
324
+ "loss": 0.5963,
325
+ "step": 440
326
+ },
327
+ {
328
+ "epoch": 1.0849909584086799,
329
+ "grad_norm": 0.6230797448075694,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.6035,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.1091018685955394,
336
+ "grad_norm": 0.5547485435536735,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.6043,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.1332127787823991,
343
+ "grad_norm": 0.6897788261093171,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.6059,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.1573236889692586,
350
+ "grad_norm": 0.5319379437293987,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.5991,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1814345991561181,
357
+ "grad_norm": 0.5927433636509655,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.6033,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.2055455093429777,
364
+ "grad_norm": 0.6178241976987927,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.6,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.2296564195298372,
371
+ "grad_norm": 0.5009847922110348,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.5987,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.253767329716697,
378
+ "grad_norm": 0.6865827636690425,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.6039,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.2778782399035564,
385
+ "grad_norm": 0.6419339118636196,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.5977,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.301989150090416,
392
+ "grad_norm": 0.5403820568820131,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.6053,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.3261000602772754,
399
+ "grad_norm": 0.496944344094317,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.6043,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.350210970464135,
406
+ "grad_norm": 0.6835364259470225,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.6015,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.3743218806509945,
413
+ "grad_norm": 0.5433357613957998,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.5979,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.3984327908378542,
420
+ "grad_norm": 0.48293592352088544,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.6039,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.4225437010247137,
427
+ "grad_norm": 0.5167692584382013,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6029,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.4466546112115732,
434
+ "grad_norm": 0.5467014681458703,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6056,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.4707655213984328,
441
+ "grad_norm": 0.48669984975762765,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6053,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.4948764315852923,
448
+ "grad_norm": 0.5052139384494145,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.607,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.518987341772152,
455
+ "grad_norm": 0.5189039466272587,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6079,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.5430982519590115,
462
+ "grad_norm": 0.5340411087467901,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.5966,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.567209162145871,
469
+ "grad_norm": 0.6320951914134804,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.6119,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.5913200723327305,
476
+ "grad_norm": 0.5402636477743581,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.6018,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.61543098251959,
483
+ "grad_norm": 0.6023321834042192,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6023,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.6395418927064496,
490
+ "grad_norm": 0.49282224066247415,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6002,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.663652802893309,
497
+ "grad_norm": 0.6838051107799483,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.601,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.6877637130801688,
504
+ "grad_norm": 0.4809683173497573,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6012,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.7118746232670283,
511
+ "grad_norm": 0.5130004764470846,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6019,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.7359855334538878,
518
+ "grad_norm": 0.5222089493788711,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6029,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.7600964436407476,
525
+ "grad_norm": 0.5537154673186192,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.6039,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.784207353827607,
532
+ "grad_norm": 0.5081950888314039,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.5973,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.8083182640144666,
539
+ "grad_norm": 0.5806567422134803,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6072,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.8324291742013261,
546
+ "grad_norm": 0.5192410257029635,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.6026,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.8565400843881856,
553
+ "grad_norm": 0.5487344170749389,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.6009,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.8806509945750451,
560
+ "grad_norm": 0.5324805374861366,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.5994,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.9047619047619047,
567
+ "grad_norm": 0.6058321884008855,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6025,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.9288728149487642,
574
+ "grad_norm": 0.57365525151735,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6026,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.952983725135624,
581
+ "grad_norm": 0.5436955562661013,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.5953,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.9770946353224834,
588
+ "grad_norm": 0.6042343773815075,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.6,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.998794454490657,
595
+ "eval_loss": 0.6393378973007202,
596
+ "eval_runtime": 225.3367,
597
+ "eval_samples_per_second": 49.597,
598
+ "eval_steps_per_second": 0.391,
599
+ "step": 829
600
+ },
601
+ {
602
+ "epoch": 2.001205545509343,
603
+ "grad_norm": 0.9670296692720087,
604
+ "learning_rate": 5e-06,
605
+ "loss": 0.6016,
606
+ "step": 830
607
+ },
608
+ {
609
+ "epoch": 2.0253164556962027,
610
+ "grad_norm": 0.6837527713124405,
611
+ "learning_rate": 5e-06,
612
+ "loss": 0.5631,
613
+ "step": 840
614
+ },
615
+ {
616
+ "epoch": 2.049427365883062,
617
+ "grad_norm": 0.5935688974373606,
618
+ "learning_rate": 5e-06,
619
+ "loss": 0.5531,
620
+ "step": 850
621
+ },
622
+ {
623
+ "epoch": 2.0735382760699217,
624
+ "grad_norm": 0.5980530217682797,
625
+ "learning_rate": 5e-06,
626
+ "loss": 0.5554,
627
+ "step": 860
628
+ },
629
+ {
630
+ "epoch": 2.097649186256781,
631
+ "grad_norm": 0.5752374885434699,
632
+ "learning_rate": 5e-06,
633
+ "loss": 0.5557,
634
+ "step": 870
635
+ },
636
+ {
637
+ "epoch": 2.1217600964436407,
638
+ "grad_norm": 0.5042143345935887,
639
+ "learning_rate": 5e-06,
640
+ "loss": 0.5522,
641
+ "step": 880
642
+ },
643
+ {
644
+ "epoch": 2.1458710066305002,
645
+ "grad_norm": 0.5980920545311946,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.553,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.1699819168173597,
652
+ "grad_norm": 0.5290062022586566,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.5541,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.1940928270042193,
659
+ "grad_norm": 0.6029389321066391,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.5527,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.2182037371910788,
666
+ "grad_norm": 0.5761620842575014,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.561,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.2423146473779383,
673
+ "grad_norm": 0.5382086109948551,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.5528,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.2664255575647982,
680
+ "grad_norm": 0.5536204411197307,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.5552,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.2905364677516578,
687
+ "grad_norm": 0.7414422036930762,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.557,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.3146473779385173,
694
+ "grad_norm": 0.6072913873182035,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.5573,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.338758288125377,
701
+ "grad_norm": 0.5786725716853928,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.5577,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.3628691983122363,
708
+ "grad_norm": 0.5958758621711483,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.5573,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.386980108499096,
715
+ "grad_norm": 0.5427800525323759,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.5605,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.4110910186859553,
722
+ "grad_norm": 0.5008520202035274,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.55,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.435201928872815,
729
+ "grad_norm": 0.5438627458062395,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.5591,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.4593128390596743,
736
+ "grad_norm": 0.523458598668171,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.5523,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.483423749246534,
743
+ "grad_norm": 0.562845339140823,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.5513,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.507534659433394,
750
+ "grad_norm": 0.71192454951128,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.5617,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.5316455696202533,
757
+ "grad_norm": 0.5488684911452221,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.5594,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.555756479807113,
764
+ "grad_norm": 0.6322721667592042,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.5603,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.5798673899939724,
771
+ "grad_norm": 0.5208011078844106,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.5564,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.603978300180832,
778
+ "grad_norm": 0.5150689754075237,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.5624,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.6280892103676914,
785
+ "grad_norm": 0.5338754237375813,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.5628,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.652200120554551,
792
+ "grad_norm": 0.5072044155960452,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.5606,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.6763110307414104,
799
+ "grad_norm": 0.7238515722776927,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.5557,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.70042194092827,
806
+ "grad_norm": 0.5147434745712806,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.553,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.7245328511151294,
813
+ "grad_norm": 0.5564967074947503,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.5635,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.748643761301989,
820
+ "grad_norm": 0.5501220049253929,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.5583,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.7727546714888485,
827
+ "grad_norm": 0.5103459117518057,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.5597,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.7968655816757084,
834
+ "grad_norm": 0.5479118611862815,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.5579,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.820976491862568,
841
+ "grad_norm": 0.5471001762934908,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.5591,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.8450874020494274,
848
+ "grad_norm": 0.6232136492982399,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.5606,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.869198312236287,
855
+ "grad_norm": 0.5669388319949817,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.5649,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.8933092224231465,
862
+ "grad_norm": 0.6969387028585086,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.5651,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.917420132610006,
869
+ "grad_norm": 0.6374387529410114,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.56,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.9415310427968655,
876
+ "grad_norm": 0.560816628841587,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.5594,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.965641952983725,
883
+ "grad_norm": 0.6033572013760955,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.5604,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.9897528631705845,
890
+ "grad_norm": 0.5557325437050415,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.5631,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.9945750452079567,
897
+ "eval_loss": 0.6422178745269775,
898
+ "eval_runtime": 225.1456,
899
+ "eval_samples_per_second": 49.639,
900
+ "eval_steps_per_second": 0.391,
901
+ "step": 1242
902
+ },
903
+ {
904
+ "epoch": 2.9945750452079567,
905
+ "step": 1242,
906
+ "total_flos": 2079977499525120.0,
907
+ "train_loss": 0.6134321775029439,
908
+ "train_runtime": 37323.5248,
909
+ "train_samples_per_second": 17.067,
910
+ "train_steps_per_second": 0.033
911
+ }
912
+ ],
913
+ "logging_steps": 10,
914
+ "max_steps": 1242,
915
+ "num_input_tokens_seen": 0,
916
+ "num_train_epochs": 3,
917
+ "save_steps": 500,
918
+ "stateful_callbacks": {
919
+ "TrainerControl": {
920
+ "args": {
921
+ "should_epoch_stop": false,
922
+ "should_evaluate": false,
923
+ "should_log": false,
924
+ "should_save": true,
925
+ "should_training_stop": true
926
+ },
927
+ "attributes": {}
928
+ }
929
+ },
930
+ "total_flos": 2079977499525120.0,
931
+ "train_batch_size": 8,
932
+ "trial_name": null,
933
+ "trial_params": null
934
+ }
training_eval_loss.png ADDED
training_loss.png ADDED