sedrickkeh commited on
Commit
628f1a1
·
verified ·
1 Parent(s): d3153ec

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 +693 -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_all_scale_up_1K
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # seed_code_multiple_samples_all_scale_up_1K
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_all_scale_up_1K
 
16
 
17
  # seed_code_multiple_samples_all_scale_up_1K
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_all_scale_up_1K dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.976,
3
+ "total_flos": 91659381276672.0,
4
+ "train_loss": 0.945604988323745,
5
+ "train_runtime": 5318.5414,
6
+ "train_samples_per_second": 1.692,
7
+ "train_steps_per_second": 0.017
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.976,
3
+ "total_flos": 91659381276672.0,
4
+ "train_loss": 0.945604988323745,
5
+ "train_runtime": 5318.5414,
6
+ "train_samples_per_second": 1.692,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,693 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.976,
5
+ "eval_steps": 500,
6
+ "global_step": 93,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.032,
13
+ "grad_norm": 6.902911186218262,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.274,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.064,
20
+ "grad_norm": 6.865423202514648,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.2584,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.096,
27
+ "grad_norm": 6.873320579528809,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.2997,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.128,
34
+ "grad_norm": 6.20452880859375,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 1.2787,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.16,
41
+ "grad_norm": 4.477367401123047,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.1893,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.192,
48
+ "grad_norm": 2.854663133621216,
49
+ "learning_rate": 6e-06,
50
+ "loss": 1.1767,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.224,
55
+ "grad_norm": 2.8232390880584717,
56
+ "learning_rate": 7e-06,
57
+ "loss": 1.1806,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.256,
62
+ "grad_norm": 5.816140651702881,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 1.158,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.288,
69
+ "grad_norm": 5.778530597686768,
70
+ "learning_rate": 9e-06,
71
+ "loss": 1.1352,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.32,
76
+ "grad_norm": 5.842033863067627,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.1387,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.352,
83
+ "grad_norm": 5.925730228424072,
84
+ "learning_rate": 9.996418774081658e-06,
85
+ "loss": 1.1677,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.384,
90
+ "grad_norm": 3.952319383621216,
91
+ "learning_rate": 9.985680226398261e-06,
92
+ "loss": 1.1415,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.416,
97
+ "grad_norm": 2.6014835834503174,
98
+ "learning_rate": 9.967799739815925e-06,
99
+ "loss": 1.0675,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.448,
104
+ "grad_norm": 2.5148086547851562,
105
+ "learning_rate": 9.942802927959444e-06,
106
+ "loss": 1.0578,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.48,
111
+ "grad_norm": 2.052213430404663,
112
+ "learning_rate": 9.910725598521014e-06,
113
+ "loss": 1.0096,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.512,
118
+ "grad_norm": 1.4976890087127686,
119
+ "learning_rate": 9.871613701966067e-06,
120
+ "loss": 1.0094,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.544,
125
+ "grad_norm": 1.1822410821914673,
126
+ "learning_rate": 9.825523265709667e-06,
127
+ "loss": 1.0001,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.576,
132
+ "grad_norm": 1.2348859310150146,
133
+ "learning_rate": 9.772520313857777e-06,
134
+ "loss": 0.9683,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.608,
139
+ "grad_norm": 1.1384820938110352,
140
+ "learning_rate": 9.712680772628365e-06,
141
+ "loss": 0.983,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.64,
146
+ "grad_norm": 1.017440915107727,
147
+ "learning_rate": 9.646090361587828e-06,
148
+ "loss": 0.97,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.672,
153
+ "grad_norm": 0.9060385227203369,
154
+ "learning_rate": 9.572844470858537e-06,
155
+ "loss": 0.9922,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.704,
160
+ "grad_norm": 0.9758835434913635,
161
+ "learning_rate": 9.493048024473413e-06,
162
+ "loss": 0.9464,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.736,
167
+ "grad_norm": 1.1663302183151245,
168
+ "learning_rate": 9.406815330073244e-06,
169
+ "loss": 0.982,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.768,
174
+ "grad_norm": 0.9243867993354797,
175
+ "learning_rate": 9.314269915162115e-06,
176
+ "loss": 0.9922,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.8,
181
+ "grad_norm": 0.9539313316345215,
182
+ "learning_rate": 9.215544350155423e-06,
183
+ "loss": 0.9401,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.832,
188
+ "grad_norm": 0.7756137847900391,
189
+ "learning_rate": 9.110780058474052e-06,
190
+ "loss": 0.9571,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.864,
195
+ "grad_norm": 0.7239847183227539,
196
+ "learning_rate": 9.000127113956673e-06,
197
+ "loss": 0.9731,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.896,
202
+ "grad_norm": 0.7880154848098755,
203
+ "learning_rate": 8.883744025880429e-06,
204
+ "loss": 0.9277,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.928,
209
+ "grad_norm": 0.7989363670349121,
210
+ "learning_rate": 8.761797511897907e-06,
211
+ "loss": 0.9404,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.96,
216
+ "grad_norm": 0.8506297469139099,
217
+ "learning_rate": 8.634462259215719e-06,
218
+ "loss": 0.9388,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.992,
223
+ "grad_norm": 0.8318315744400024,
224
+ "learning_rate": 8.501920674356755e-06,
225
+ "loss": 0.9318,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.024,
230
+ "grad_norm": 1.70693039894104,
231
+ "learning_rate": 8.364362621864595e-06,
232
+ "loss": 1.7235,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.056,
237
+ "grad_norm": 0.7298498749732971,
238
+ "learning_rate": 8.221985152324385e-06,
239
+ "loss": 0.8678,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.088,
244
+ "grad_norm": 0.7523313164710999,
245
+ "learning_rate": 8.07499222008977e-06,
246
+ "loss": 0.8889,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.12,
251
+ "grad_norm": 0.7242347002029419,
252
+ "learning_rate": 7.923594391120237e-06,
253
+ "loss": 0.9157,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.152,
258
+ "grad_norm": 0.8468252420425415,
259
+ "learning_rate": 7.768008541347423e-06,
260
+ "loss": 0.9081,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.184,
265
+ "grad_norm": 0.6322146058082581,
266
+ "learning_rate": 7.608457546002423e-06,
267
+ "loss": 0.8875,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.216,
272
+ "grad_norm": 0.7224799990653992,
273
+ "learning_rate": 7.445169960349167e-06,
274
+ "loss": 0.8787,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.248,
279
+ "grad_norm": 0.8994417190551758,
280
+ "learning_rate": 7.278379692281209e-06,
281
+ "loss": 0.9457,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.28,
286
+ "grad_norm": 0.5251118540763855,
287
+ "learning_rate": 7.10832566725092e-06,
288
+ "loss": 0.8881,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.312,
293
+ "grad_norm": 0.7077475190162659,
294
+ "learning_rate": 6.9352514860110876e-06,
295
+ "loss": 0.8929,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.3439999999999999,
300
+ "grad_norm": 0.6465011835098267,
301
+ "learning_rate": 6.759405075659165e-06,
302
+ "loss": 0.7808,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.376,
307
+ "grad_norm": 0.714865505695343,
308
+ "learning_rate": 6.58103833448412e-06,
309
+ "loss": 0.8973,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.408,
314
+ "grad_norm": 0.5610604882240295,
315
+ "learning_rate": 6.4004067711245366e-06,
316
+ "loss": 0.9228,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.44,
321
+ "grad_norm": 0.6022524833679199,
322
+ "learning_rate": 6.2177691385549595e-06,
323
+ "loss": 0.857,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.472,
328
+ "grad_norm": 0.72687166929245,
329
+ "learning_rate": 6.033387063424765e-06,
330
+ "loss": 0.843,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.504,
335
+ "grad_norm": 0.6550407409667969,
336
+ "learning_rate": 5.8475246712804845e-06,
337
+ "loss": 1.0347,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.536,
342
+ "grad_norm": 0.5872577428817749,
343
+ "learning_rate": 5.660448208208513e-06,
344
+ "loss": 0.817,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.568,
349
+ "grad_norm": 0.6337549090385437,
350
+ "learning_rate": 5.472425659440157e-06,
351
+ "loss": 0.8407,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.6,
356
+ "grad_norm": 0.6403087377548218,
357
+ "learning_rate": 5.2837263654653715e-06,
358
+ "loss": 0.8921,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.6320000000000001,
363
+ "grad_norm": 0.6125657558441162,
364
+ "learning_rate": 5.094620636205096e-06,
365
+ "loss": 0.9579,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.6640000000000001,
370
+ "grad_norm": 0.5235335826873779,
371
+ "learning_rate": 4.905379363794907e-06,
372
+ "loss": 0.7933,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.696,
377
+ "grad_norm": 0.6453654766082764,
378
+ "learning_rate": 4.71627363453463e-06,
379
+ "loss": 0.97,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.728,
384
+ "grad_norm": 0.5285298228263855,
385
+ "learning_rate": 4.527574340559844e-06,
386
+ "loss": 0.8357,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.76,
391
+ "grad_norm": 0.44597020745277405,
392
+ "learning_rate": 4.33955179179149e-06,
393
+ "loss": 0.828,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.792,
398
+ "grad_norm": 0.6450824737548828,
399
+ "learning_rate": 4.152475328719517e-06,
400
+ "loss": 0.8928,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.8239999999999998,
405
+ "grad_norm": 0.5392605662345886,
406
+ "learning_rate": 3.966612936575235e-06,
407
+ "loss": 0.9052,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.8559999999999999,
412
+ "grad_norm": 0.5523377060890198,
413
+ "learning_rate": 3.782230861445041e-06,
414
+ "loss": 0.9586,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.888,
419
+ "grad_norm": 0.537310779094696,
420
+ "learning_rate": 3.5995932288754655e-06,
421
+ "loss": 0.8434,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.92,
426
+ "grad_norm": 10.150139808654785,
427
+ "learning_rate": 3.4189616655158803e-06,
428
+ "loss": 0.8777,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.952,
433
+ "grad_norm": 0.5695199370384216,
434
+ "learning_rate": 3.240594924340835e-06,
435
+ "loss": 0.8699,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.984,
440
+ "grad_norm": 0.5820671319961548,
441
+ "learning_rate": 3.0647485139889145e-06,
442
+ "loss": 0.8321,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.016,
447
+ "grad_norm": 0.9486154913902283,
448
+ "learning_rate": 2.89167433274908e-06,
449
+ "loss": 1.5436,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.048,
454
+ "grad_norm": 0.5092023611068726,
455
+ "learning_rate": 2.721620307718793e-06,
456
+ "loss": 0.8582,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.08,
461
+ "grad_norm": 0.5217841863632202,
462
+ "learning_rate": 2.554830039650834e-06,
463
+ "loss": 0.8665,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.112,
468
+ "grad_norm": 0.5346829891204834,
469
+ "learning_rate": 2.391542453997578e-06,
470
+ "loss": 0.8705,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.144,
475
+ "grad_norm": 0.5108064413070679,
476
+ "learning_rate": 2.2319914586525776e-06,
477
+ "loss": 0.7992,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.176,
482
+ "grad_norm": 0.4857538044452667,
483
+ "learning_rate": 2.0764056088797646e-06,
484
+ "loss": 0.8735,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.208,
489
+ "grad_norm": 0.5583701729774475,
490
+ "learning_rate": 1.9250077799102323e-06,
491
+ "loss": 0.8379,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.24,
496
+ "grad_norm": 0.44473886489868164,
497
+ "learning_rate": 1.7780148476756148e-06,
498
+ "loss": 0.8338,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.2720000000000002,
503
+ "grad_norm": 0.4547748267650604,
504
+ "learning_rate": 1.6356373781354058e-06,
505
+ "loss": 0.7843,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.304,
510
+ "grad_norm": 0.4426772892475128,
511
+ "learning_rate": 1.4980793256432474e-06,
512
+ "loss": 0.8256,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.336,
517
+ "grad_norm": 0.4569498896598816,
518
+ "learning_rate": 1.3655377407842813e-06,
519
+ "loss": 0.8289,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.368,
524
+ "grad_norm": 0.46035248041152954,
525
+ "learning_rate": 1.2382024881020937e-06,
526
+ "loss": 0.8025,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.4,
531
+ "grad_norm": 0.4538329839706421,
532
+ "learning_rate": 1.1162559741195733e-06,
533
+ "loss": 0.9191,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.432,
538
+ "grad_norm": 0.4397728443145752,
539
+ "learning_rate": 9.998728860433277e-07,
540
+ "loss": 0.8216,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.464,
545
+ "grad_norm": 0.46339666843414307,
546
+ "learning_rate": 8.892199415259501e-07,
547
+ "loss": 0.8265,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.496,
552
+ "grad_norm": 0.4591324031352997,
553
+ "learning_rate": 7.844556498445788e-07,
554
+ "loss": 0.8353,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.528,
559
+ "grad_norm": 0.4275136888027191,
560
+ "learning_rate": 6.857300848378857e-07,
561
+ "loss": 0.8233,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.56,
566
+ "grad_norm": 0.42812904715538025,
567
+ "learning_rate": 5.931846699267558e-07,
568
+ "loss": 0.918,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.592,
573
+ "grad_norm": 0.41314032673835754,
574
+ "learning_rate": 5.0695197552659e-07,
575
+ "loss": 0.7847,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.624,
580
+ "grad_norm": 0.442142516374588,
581
+ "learning_rate": 4.271555291414636e-07,
582
+ "loss": 0.8077,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.656,
587
+ "grad_norm": 0.43055617809295654,
588
+ "learning_rate": 3.539096384121743e-07,
589
+ "loss": 0.8602,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.6879999999999997,
594
+ "grad_norm": 0.39766573905944824,
595
+ "learning_rate": 2.873192273716369e-07,
596
+ "loss": 0.846,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.7199999999999998,
601
+ "grad_norm": 0.4134579002857208,
602
+ "learning_rate": 2.274796861422246e-07,
603
+ "loss": 0.808,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.752,
608
+ "grad_norm": 0.39045432209968567,
609
+ "learning_rate": 1.7447673429033361e-07,
610
+ "loss": 0.8078,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.784,
615
+ "grad_norm": 0.433301717042923,
616
+ "learning_rate": 1.2838629803393343e-07,
617
+ "loss": 0.8601,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.816,
622
+ "grad_norm": 0.4349207282066345,
623
+ "learning_rate": 8.927440147898703e-08,
624
+ "loss": 0.8478,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.848,
629
+ "grad_norm": 0.4573710560798645,
630
+ "learning_rate": 5.7197072040557356e-08,
631
+ "loss": 0.9191,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.88,
636
+ "grad_norm": 0.40317612886428833,
637
+ "learning_rate": 3.220026018407541e-08,
638
+ "loss": 0.7321,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.912,
643
+ "grad_norm": 0.4268146753311157,
644
+ "learning_rate": 1.431977360173975e-08,
645
+ "loss": 0.8163,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.944,
650
+ "grad_norm": 0.4728689193725586,
651
+ "learning_rate": 3.5812259183426457e-09,
652
+ "loss": 0.8683,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.976,
657
+ "grad_norm": 0.4204527735710144,
658
+ "learning_rate": 0.0,
659
+ "loss": 0.8822,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.976,
664
+ "step": 93,
665
+ "total_flos": 91659381276672.0,
666
+ "train_loss": 0.945604988323745,
667
+ "train_runtime": 5318.5414,
668
+ "train_samples_per_second": 1.692,
669
+ "train_steps_per_second": 0.017
670
+ }
671
+ ],
672
+ "logging_steps": 1.0,
673
+ "max_steps": 93,
674
+ "num_input_tokens_seen": 0,
675
+ "num_train_epochs": 3,
676
+ "save_steps": 500,
677
+ "stateful_callbacks": {
678
+ "TrainerControl": {
679
+ "args": {
680
+ "should_epoch_stop": false,
681
+ "should_evaluate": false,
682
+ "should_log": false,
683
+ "should_save": true,
684
+ "should_training_stop": true
685
+ },
686
+ "attributes": {}
687
+ }
688
+ },
689
+ "total_flos": 91659381276672.0,
690
+ "train_batch_size": 1,
691
+ "trial_name": null,
692
+ "trial_params": null
693
+ }
training_loss.png ADDED