sedrickkeh commited on
Commit
698af45
·
verified ·
1 Parent(s): 580ed51

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +903 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: seed_code_multiple_samples_random_scale_up_4K
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # seed_code_multiple_samples_random_scale_up_4K
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: seed_code_multiple_samples_random_scale_up_4K
 
16
 
17
  # seed_code_multiple_samples_random_scale_up_4K
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/seed_code_multiple_samples_random_scale_up_4K dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.968,
3
+ "total_flos": 121724209528832.0,
4
+ "train_loss": 0.9151467346563572,
5
+ "train_runtime": 7021.3239,
6
+ "train_samples_per_second": 1.709,
7
+ "train_steps_per_second": 0.018
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.968,
3
+ "total_flos": 121724209528832.0,
4
+ "train_loss": 0.9151467346563572,
5
+ "train_runtime": 7021.3239,
6
+ "train_samples_per_second": 1.709,
7
+ "train_steps_per_second": 0.018
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,903 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.968,
5
+ "eval_steps": 500,
6
+ "global_step": 123,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.024,
13
+ "grad_norm": 6.8362836837768555,
14
+ "learning_rate": 7.692307692307694e-07,
15
+ "loss": 1.2519,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.048,
20
+ "grad_norm": 6.583799362182617,
21
+ "learning_rate": 1.5384615384615387e-06,
22
+ "loss": 1.23,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.072,
27
+ "grad_norm": 6.952097415924072,
28
+ "learning_rate": 2.307692307692308e-06,
29
+ "loss": 1.2785,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.096,
34
+ "grad_norm": 6.371545314788818,
35
+ "learning_rate": 3.0769230769230774e-06,
36
+ "loss": 1.2499,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.12,
41
+ "grad_norm": 4.713391304016113,
42
+ "learning_rate": 3.846153846153847e-06,
43
+ "loss": 1.2259,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.144,
48
+ "grad_norm": 3.5113883018493652,
49
+ "learning_rate": 4.615384615384616e-06,
50
+ "loss": 1.1784,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.168,
55
+ "grad_norm": 2.6190996170043945,
56
+ "learning_rate": 5.384615384615385e-06,
57
+ "loss": 1.1433,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.192,
62
+ "grad_norm": 4.008308410644531,
63
+ "learning_rate": 6.153846153846155e-06,
64
+ "loss": 1.1378,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.216,
69
+ "grad_norm": 4.964306831359863,
70
+ "learning_rate": 6.923076923076923e-06,
71
+ "loss": 1.1729,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.24,
76
+ "grad_norm": 4.513827323913574,
77
+ "learning_rate": 7.692307692307694e-06,
78
+ "loss": 1.1446,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.264,
83
+ "grad_norm": 3.6050338745117188,
84
+ "learning_rate": 8.461538461538462e-06,
85
+ "loss": 1.0779,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.288,
90
+ "grad_norm": 3.471524715423584,
91
+ "learning_rate": 9.230769230769232e-06,
92
+ "loss": 1.0671,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.312,
97
+ "grad_norm": 2.42974591255188,
98
+ "learning_rate": 1e-05,
99
+ "loss": 1.0223,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.336,
104
+ "grad_norm": 1.8660697937011719,
105
+ "learning_rate": 9.997960964140946e-06,
106
+ "loss": 1.0106,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.36,
111
+ "grad_norm": 1.853407621383667,
112
+ "learning_rate": 9.991845519630679e-06,
113
+ "loss": 1.0557,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.384,
118
+ "grad_norm": 1.5663851499557495,
119
+ "learning_rate": 9.981658654313458e-06,
120
+ "loss": 0.9931,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.408,
125
+ "grad_norm": 1.4195172786712646,
126
+ "learning_rate": 9.96740867674275e-06,
127
+ "loss": 0.993,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.432,
132
+ "grad_norm": 1.153138518333435,
133
+ "learning_rate": 9.949107209404664e-06,
134
+ "loss": 1.0047,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.456,
139
+ "grad_norm": 1.4434843063354492,
140
+ "learning_rate": 9.926769179238467e-06,
141
+ "loss": 0.9929,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.48,
146
+ "grad_norm": 1.1956053972244263,
147
+ "learning_rate": 9.900412805461968e-06,
148
+ "loss": 0.9942,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.504,
153
+ "grad_norm": 1.0062505006790161,
154
+ "learning_rate": 9.870059584711668e-06,
155
+ "loss": 0.9831,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.528,
160
+ "grad_norm": 1.0054383277893066,
161
+ "learning_rate": 9.835734273509787e-06,
162
+ "loss": 0.9784,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.552,
167
+ "grad_norm": 0.9153076410293579,
168
+ "learning_rate": 9.797464868072489e-06,
169
+ "loss": 0.9665,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.576,
174
+ "grad_norm": 0.9883344769477844,
175
+ "learning_rate": 9.755282581475769e-06,
176
+ "loss": 0.9633,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.6,
181
+ "grad_norm": 0.9623836874961853,
182
+ "learning_rate": 9.709221818197626e-06,
183
+ "loss": 0.9732,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.624,
188
+ "grad_norm": 0.8564513325691223,
189
+ "learning_rate": 9.659320146057263e-06,
190
+ "loss": 0.9188,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.648,
195
+ "grad_norm": 0.7836757302284241,
196
+ "learning_rate": 9.60561826557425e-06,
197
+ "loss": 0.9723,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.672,
202
+ "grad_norm": 0.8154799938201904,
203
+ "learning_rate": 9.548159976772593e-06,
204
+ "loss": 0.9103,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.696,
209
+ "grad_norm": 0.8699765205383301,
210
+ "learning_rate": 9.486992143456792e-06,
211
+ "loss": 0.9487,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.72,
216
+ "grad_norm": 0.6717429757118225,
217
+ "learning_rate": 9.422164654989073e-06,
218
+ "loss": 0.9657,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.744,
223
+ "grad_norm": 0.7567694187164307,
224
+ "learning_rate": 9.353730385598887e-06,
225
+ "loss": 0.9785,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.768,
230
+ "grad_norm": 0.7300078868865967,
231
+ "learning_rate": 9.281745151257946e-06,
232
+ "loss": 0.9331,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.792,
237
+ "grad_norm": 0.8414798378944397,
238
+ "learning_rate": 9.206267664155906e-06,
239
+ "loss": 0.9369,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.816,
244
+ "grad_norm": 0.7341222763061523,
245
+ "learning_rate": 9.12735948481387e-06,
246
+ "loss": 0.9246,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.84,
251
+ "grad_norm": 0.7759191393852234,
252
+ "learning_rate": 9.045084971874738e-06,
253
+ "loss": 0.935,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.864,
258
+ "grad_norm": 0.9772646427154541,
259
+ "learning_rate": 8.959511229611377e-06,
260
+ "loss": 0.9506,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.888,
265
+ "grad_norm": 0.7034265995025635,
266
+ "learning_rate": 8.870708053195414e-06,
267
+ "loss": 0.9332,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.912,
272
+ "grad_norm": 0.6552270650863647,
273
+ "learning_rate": 8.778747871771293e-06,
274
+ "loss": 0.8891,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.936,
279
+ "grad_norm": 0.7311168313026428,
280
+ "learning_rate": 8.683705689382025e-06,
281
+ "loss": 0.9656,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.96,
286
+ "grad_norm": 0.6239702701568604,
287
+ "learning_rate": 8.585659023794818e-06,
288
+ "loss": 0.9594,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.984,
293
+ "grad_norm": 0.7404515743255615,
294
+ "learning_rate": 8.48468784327647e-06,
295
+ "loss": 0.9467,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.016,
300
+ "grad_norm": 1.015267252922058,
301
+ "learning_rate": 8.380874501370098e-06,
302
+ "loss": 1.4435,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.04,
307
+ "grad_norm": 0.7437450885772705,
308
+ "learning_rate": 8.274303669726427e-06,
309
+ "loss": 0.9858,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.064,
314
+ "grad_norm": 0.5530978441238403,
315
+ "learning_rate": 8.165062269044353e-06,
316
+ "loss": 0.7881,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.088,
321
+ "grad_norm": 0.6483109593391418,
322
+ "learning_rate": 8.053239398177191e-06,
323
+ "loss": 0.8529,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.112,
328
+ "grad_norm": 0.6724779009819031,
329
+ "learning_rate": 7.938926261462366e-06,
330
+ "loss": 0.8778,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.1360000000000001,
335
+ "grad_norm": 0.7351576089859009,
336
+ "learning_rate": 7.822216094333847e-06,
337
+ "loss": 0.9103,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.16,
342
+ "grad_norm": 0.6864327192306519,
343
+ "learning_rate": 7.703204087277989e-06,
344
+ "loss": 0.848,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.184,
349
+ "grad_norm": 0.8479780554771423,
350
+ "learning_rate": 7.5819873081948105e-06,
351
+ "loss": 0.896,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.208,
356
+ "grad_norm": 0.6257553100585938,
357
+ "learning_rate": 7.45866462322802e-06,
358
+ "loss": 0.8881,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.232,
363
+ "grad_norm": 0.6846205592155457,
364
+ "learning_rate": 7.333336616128369e-06,
365
+ "loss": 0.9257,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.256,
370
+ "grad_norm": 0.970287561416626,
371
+ "learning_rate": 7.206105506216107e-06,
372
+ "loss": 0.8823,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.28,
377
+ "grad_norm": 0.6447298526763916,
378
+ "learning_rate": 7.0770750650094335e-06,
379
+ "loss": 0.822,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.304,
384
+ "grad_norm": 2.3928756713867188,
385
+ "learning_rate": 6.946350531586959e-06,
386
+ "loss": 0.7433,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.328,
391
+ "grad_norm": 0.8941048979759216,
392
+ "learning_rate": 6.814038526753205e-06,
393
+ "loss": 0.9697,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.3519999999999999,
398
+ "grad_norm": 0.6773728728294373,
399
+ "learning_rate": 6.680246966077151e-06,
400
+ "loss": 0.8388,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.376,
405
+ "grad_norm": 0.6578003764152527,
406
+ "learning_rate": 6.545084971874738e-06,
407
+ "loss": 0.898,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.4,
412
+ "grad_norm": 0.674293041229248,
413
+ "learning_rate": 6.408662784207149e-06,
414
+ "loss": 0.9156,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.424,
419
+ "grad_norm": 0.6401296854019165,
420
+ "learning_rate": 6.271091670967437e-06,
421
+ "loss": 0.8781,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.448,
426
+ "grad_norm": 0.6086285710334778,
427
+ "learning_rate": 6.132483837128823e-06,
428
+ "loss": 0.8464,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.472,
433
+ "grad_norm": 0.6196046471595764,
434
+ "learning_rate": 5.9929523332287275e-06,
435
+ "loss": 0.8604,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.496,
440
+ "grad_norm": 0.6998230814933777,
441
+ "learning_rate": 5.85261096316312e-06,
442
+ "loss": 0.9152,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.52,
447
+ "grad_norm": 0.645214855670929,
448
+ "learning_rate": 5.711574191366427e-06,
449
+ "loss": 0.8257,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.544,
454
+ "grad_norm": 0.7682178616523743,
455
+ "learning_rate": 5.569957049452703e-06,
456
+ "loss": 0.893,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.568,
461
+ "grad_norm": 0.5541701912879944,
462
+ "learning_rate": 5.4278750423942e-06,
463
+ "loss": 0.8719,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.592,
468
+ "grad_norm": 0.5373249053955078,
469
+ "learning_rate": 5.285444054313841e-06,
470
+ "loss": 0.8374,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.616,
475
+ "grad_norm": 0.6957194805145264,
476
+ "learning_rate": 5.142780253968481e-06,
477
+ "loss": 0.9636,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.6400000000000001,
482
+ "grad_norm": 0.4742963910102844,
483
+ "learning_rate": 5e-06,
484
+ "loss": 0.7453,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.6640000000000001,
489
+ "grad_norm": 0.6149660348892212,
490
+ "learning_rate": 4.85721974603152e-06,
491
+ "loss": 0.8727,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.688,
496
+ "grad_norm": 0.6649055480957031,
497
+ "learning_rate": 4.71455594568616e-06,
498
+ "loss": 0.8197,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.712,
503
+ "grad_norm": 0.5363019704818726,
504
+ "learning_rate": 4.572124957605803e-06,
505
+ "loss": 0.8977,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.736,
510
+ "grad_norm": 0.5486201643943787,
511
+ "learning_rate": 4.430042950547298e-06,
512
+ "loss": 0.8524,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.76,
517
+ "grad_norm": 0.7598503232002258,
518
+ "learning_rate": 4.2884258086335755e-06,
519
+ "loss": 0.8718,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.784,
524
+ "grad_norm": 0.5470713973045349,
525
+ "learning_rate": 4.147389036836881e-06,
526
+ "loss": 0.8436,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.808,
531
+ "grad_norm": 0.5422508120536804,
532
+ "learning_rate": 4.007047666771274e-06,
533
+ "loss": 0.9016,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.8319999999999999,
538
+ "grad_norm": 0.563028872013092,
539
+ "learning_rate": 3.867516162871177e-06,
540
+ "loss": 0.8374,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.8559999999999999,
545
+ "grad_norm": 0.5209132432937622,
546
+ "learning_rate": 3.7289083290325668e-06,
547
+ "loss": 0.833,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.88,
552
+ "grad_norm": 0.5739846229553223,
553
+ "learning_rate": 3.5913372157928515e-06,
554
+ "loss": 0.9076,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.904,
559
+ "grad_norm": 0.5330556035041809,
560
+ "learning_rate": 3.4549150281252635e-06,
561
+ "loss": 0.8753,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.928,
566
+ "grad_norm": 0.4843089282512665,
567
+ "learning_rate": 3.319753033922849e-06,
568
+ "loss": 0.8169,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.952,
573
+ "grad_norm": 0.5041735172271729,
574
+ "learning_rate": 3.1859614732467957e-06,
575
+ "loss": 0.8877,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.976,
580
+ "grad_norm": 0.5104906558990479,
581
+ "learning_rate": 3.053649468413043e-06,
582
+ "loss": 0.7909,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.008,
587
+ "grad_norm": 1.0316483974456787,
588
+ "learning_rate": 2.9229249349905686e-06,
589
+ "loss": 1.3689,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.032,
594
+ "grad_norm": 0.5285851955413818,
595
+ "learning_rate": 2.7938944937838924e-06,
596
+ "loss": 0.8718,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.056,
601
+ "grad_norm": 0.5638172626495361,
602
+ "learning_rate": 2.6666633838716317e-06,
603
+ "loss": 0.8144,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.08,
608
+ "grad_norm": 0.4385935962200165,
609
+ "learning_rate": 2.5413353767719805e-06,
610
+ "loss": 0.7497,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.104,
615
+ "grad_norm": 0.5555351376533508,
616
+ "learning_rate": 2.418012691805191e-06,
617
+ "loss": 0.9051,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.128,
622
+ "grad_norm": 0.5720311999320984,
623
+ "learning_rate": 2.296795912722014e-06,
624
+ "loss": 0.8908,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.152,
629
+ "grad_norm": 0.46188703179359436,
630
+ "learning_rate": 2.1777839056661555e-06,
631
+ "loss": 0.7216,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.176,
636
+ "grad_norm": 0.48220935463905334,
637
+ "learning_rate": 2.061073738537635e-06,
638
+ "loss": 0.8029,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.2,
643
+ "grad_norm": 0.49016672372817993,
644
+ "learning_rate": 1.946760601822809e-06,
645
+ "loss": 0.9015,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.224,
650
+ "grad_norm": 0.44178417325019836,
651
+ "learning_rate": 1.8349377309556487e-06,
652
+ "loss": 0.7919,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.248,
657
+ "grad_norm": 0.5433825850486755,
658
+ "learning_rate": 1.7256963302735752e-06,
659
+ "loss": 0.7993,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.2720000000000002,
664
+ "grad_norm": 0.39549779891967773,
665
+ "learning_rate": 1.6191254986299044e-06,
666
+ "loss": 0.7369,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 2.296,
671
+ "grad_norm": 0.48636099696159363,
672
+ "learning_rate": 1.5153121567235334e-06,
673
+ "loss": 0.9214,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 2.32,
678
+ "grad_norm": 0.4830661118030548,
679
+ "learning_rate": 1.4143409762051829e-06,
680
+ "loss": 0.8425,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 2.344,
685
+ "grad_norm": 0.42800870537757874,
686
+ "learning_rate": 1.3162943106179748e-06,
687
+ "loss": 0.7417,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 2.368,
692
+ "grad_norm": 0.46301019191741943,
693
+ "learning_rate": 1.2212521282287093e-06,
694
+ "loss": 0.8874,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 2.392,
699
+ "grad_norm": 0.4442095458507538,
700
+ "learning_rate": 1.1292919468045876e-06,
701
+ "loss": 0.8052,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 2.416,
706
+ "grad_norm": 0.49116918444633484,
707
+ "learning_rate": 1.0404887703886252e-06,
708
+ "loss": 0.8252,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 2.44,
713
+ "grad_norm": 0.45165371894836426,
714
+ "learning_rate": 9.549150281252633e-07,
715
+ "loss": 0.7867,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 2.464,
720
+ "grad_norm": 0.4509302079677582,
721
+ "learning_rate": 8.7264051518613e-07,
722
+ "loss": 0.9062,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 2.488,
727
+ "grad_norm": 0.45219430327415466,
728
+ "learning_rate": 7.937323358440935e-07,
729
+ "loss": 0.7844,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 2.512,
734
+ "grad_norm": 0.39615580439567566,
735
+ "learning_rate": 7.182548487420555e-07,
736
+ "loss": 0.7702,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 2.536,
741
+ "grad_norm": 0.5083522796630859,
742
+ "learning_rate": 6.462696144011149e-07,
743
+ "loss": 0.9273,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 2.56,
748
+ "grad_norm": 0.40505877137184143,
749
+ "learning_rate": 5.778353450109286e-07,
750
+ "loss": 0.8128,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 2.584,
755
+ "grad_norm": 0.4423372447490692,
756
+ "learning_rate": 5.130078565432089e-07,
757
+ "loss": 0.7965,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 2.608,
762
+ "grad_norm": 0.448724627494812,
763
+ "learning_rate": 4.5184002322740784e-07,
764
+ "loss": 0.7753,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 2.632,
769
+ "grad_norm": 0.4123077690601349,
770
+ "learning_rate": 3.9438173442575e-07,
771
+ "loss": 0.8232,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 2.656,
776
+ "grad_norm": 0.4331120550632477,
777
+ "learning_rate": 3.406798539427386e-07,
778
+ "loss": 0.8859,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 2.68,
783
+ "grad_norm": 0.463981956243515,
784
+ "learning_rate": 2.9077818180237693e-07,
785
+ "loss": 0.81,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 2.7039999999999997,
790
+ "grad_norm": 0.4227185547351837,
791
+ "learning_rate": 2.447174185242324e-07,
792
+ "loss": 0.7866,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 2.7279999999999998,
797
+ "grad_norm": 0.4594978392124176,
798
+ "learning_rate": 2.0253513192751374e-07,
799
+ "loss": 0.8428,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 2.752,
804
+ "grad_norm": 0.4640582799911499,
805
+ "learning_rate": 1.6426572649021477e-07,
806
+ "loss": 0.8939,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 2.776,
811
+ "grad_norm": 0.410780668258667,
812
+ "learning_rate": 1.2994041528833267e-07,
813
+ "loss": 0.7411,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 2.8,
818
+ "grad_norm": 0.4083250164985657,
819
+ "learning_rate": 9.958719453803278e-08,
820
+ "loss": 0.8683,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 2.824,
825
+ "grad_norm": 0.36987847089767456,
826
+ "learning_rate": 7.32308207615351e-08,
827
+ "loss": 0.7558,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 2.848,
832
+ "grad_norm": 0.3830074965953827,
833
+ "learning_rate": 5.089279059533658e-08,
834
+ "loss": 0.8281,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 2.872,
839
+ "grad_norm": 0.4141235947608948,
840
+ "learning_rate": 3.25913232572489e-08,
841
+ "loss": 0.8886,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 2.896,
846
+ "grad_norm": 0.3976007103919983,
847
+ "learning_rate": 1.834134568654333e-08,
848
+ "loss": 0.7874,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 2.92,
853
+ "grad_norm": 0.447281152009964,
854
+ "learning_rate": 8.15448036932176e-09,
855
+ "loss": 0.8983,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 2.944,
860
+ "grad_norm": 0.3919880986213684,
861
+ "learning_rate": 2.0390358590538507e-09,
862
+ "loss": 0.6968,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 2.968,
867
+ "grad_norm": 0.42730164527893066,
868
+ "learning_rate": 0.0,
869
+ "loss": 0.8298,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 2.968,
874
+ "step": 123,
875
+ "total_flos": 121724209528832.0,
876
+ "train_loss": 0.9151467346563572,
877
+ "train_runtime": 7021.3239,
878
+ "train_samples_per_second": 1.709,
879
+ "train_steps_per_second": 0.018
880
+ }
881
+ ],
882
+ "logging_steps": 1.0,
883
+ "max_steps": 123,
884
+ "num_input_tokens_seen": 0,
885
+ "num_train_epochs": 3,
886
+ "save_steps": 500,
887
+ "stateful_callbacks": {
888
+ "TrainerControl": {
889
+ "args": {
890
+ "should_epoch_stop": false,
891
+ "should_evaluate": false,
892
+ "should_log": false,
893
+ "should_save": true,
894
+ "should_training_stop": true
895
+ },
896
+ "attributes": {}
897
+ }
898
+ },
899
+ "total_flos": 121724209528832.0,
900
+ "train_batch_size": 1,
901
+ "trial_name": null,
902
+ "trial_params": null
903
+ }
training_loss.png ADDED