sedrickkeh commited on
Commit
d936354
·
verified ·
1 Parent(s): 2feff8d

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 +588 -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: multiple_samples_sharpening_numina_aime
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # multiple_samples_sharpening_numina_aime
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: multiple_samples_sharpening_numina_aime
 
16
 
17
  # multiple_samples_sharpening_numina_aime
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/multiple_samples_sharpening_numina_aime dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.980891719745223,
3
+ "total_flos": 47460738555904.0,
4
+ "train_loss": 0.6236666376009966,
5
+ "train_runtime": 2174.9739,
6
+ "train_samples_per_second": 3.448,
7
+ "train_steps_per_second": 0.036
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.980891719745223,
3
+ "total_flos": 47460738555904.0,
4
+ "train_loss": 0.6236666376009966,
5
+ "train_runtime": 2174.9739,
6
+ "train_samples_per_second": 3.448,
7
+ "train_steps_per_second": 0.036
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.980891719745223,
5
+ "eval_steps": 500,
6
+ "global_step": 78,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03821656050955414,
13
+ "grad_norm": 6.475443363189697,
14
+ "learning_rate": 1.25e-06,
15
+ "loss": 0.9435,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07643312101910828,
20
+ "grad_norm": 6.0149922370910645,
21
+ "learning_rate": 2.5e-06,
22
+ "loss": 0.9088,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11464968152866242,
27
+ "grad_norm": 6.234716892242432,
28
+ "learning_rate": 3.7500000000000005e-06,
29
+ "loss": 0.946,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.15286624203821655,
34
+ "grad_norm": 5.534856796264648,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.9178,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.1910828025477707,
41
+ "grad_norm": 4.338842868804932,
42
+ "learning_rate": 6.25e-06,
43
+ "loss": 0.8717,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.22929936305732485,
48
+ "grad_norm": 2.4903976917266846,
49
+ "learning_rate": 7.500000000000001e-06,
50
+ "loss": 0.7575,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.267515923566879,
55
+ "grad_norm": 3.8526647090911865,
56
+ "learning_rate": 8.750000000000001e-06,
57
+ "loss": 0.7954,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.3057324840764331,
62
+ "grad_norm": 4.179830551147461,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.8056,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.34394904458598724,
69
+ "grad_norm": 3.9865660667419434,
70
+ "learning_rate": 9.994965332706574e-06,
71
+ "loss": 0.7168,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.3821656050955414,
76
+ "grad_norm": 4.04654598236084,
77
+ "learning_rate": 9.979871469976197e-06,
78
+ "loss": 0.7573,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.42038216560509556,
83
+ "grad_norm": 2.9917404651641846,
84
+ "learning_rate": 9.954748808839675e-06,
85
+ "loss": 0.7598,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.4585987261146497,
90
+ "grad_norm": 2.017793655395508,
91
+ "learning_rate": 9.91964794299315e-06,
92
+ "loss": 0.7146,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.4968152866242038,
97
+ "grad_norm": 2.0348641872406006,
98
+ "learning_rate": 9.874639560909118e-06,
99
+ "loss": 0.7697,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.535031847133758,
104
+ "grad_norm": 1.8617016077041626,
105
+ "learning_rate": 9.819814303479268e-06,
106
+ "loss": 0.6807,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5732484076433121,
111
+ "grad_norm": 1.5839647054672241,
112
+ "learning_rate": 9.755282581475769e-06,
113
+ "loss": 0.6682,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6114649681528662,
118
+ "grad_norm": 1.2628346681594849,
119
+ "learning_rate": 9.681174353198687e-06,
120
+ "loss": 0.6205,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6496815286624203,
125
+ "grad_norm": 1.4339826107025146,
126
+ "learning_rate": 9.597638862757255e-06,
127
+ "loss": 0.6606,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6878980891719745,
132
+ "grad_norm": 1.0776035785675049,
133
+ "learning_rate": 9.504844339512096e-06,
134
+ "loss": 0.6367,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7261146496815286,
139
+ "grad_norm": 1.2484275102615356,
140
+ "learning_rate": 9.40297765928369e-06,
141
+ "loss": 0.7081,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7643312101910829,
146
+ "grad_norm": 1.166043996810913,
147
+ "learning_rate": 9.292243968009332e-06,
148
+ "loss": 0.6139,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.802547770700637,
153
+ "grad_norm": 1.0878933668136597,
154
+ "learning_rate": 9.172866268606514e-06,
155
+ "loss": 0.6364,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8407643312101911,
160
+ "grad_norm": 0.8449444770812988,
161
+ "learning_rate": 9.045084971874738e-06,
162
+ "loss": 0.6327,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.8789808917197452,
167
+ "grad_norm": 0.9466868042945862,
168
+ "learning_rate": 8.90915741234015e-06,
169
+ "loss": 0.7027,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9171974522292994,
174
+ "grad_norm": 0.9680841565132141,
175
+ "learning_rate": 8.765357330018056e-06,
176
+ "loss": 0.6549,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9554140127388535,
181
+ "grad_norm": 0.7421926259994507,
182
+ "learning_rate": 8.613974319136959e-06,
183
+ "loss": 0.6129,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.9936305732484076,
188
+ "grad_norm": 0.8124146461486816,
189
+ "learning_rate": 8.455313244934324e-06,
190
+ "loss": 0.609,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.0318471337579618,
195
+ "grad_norm": 1.6263659000396729,
196
+ "learning_rate": 8.289693629698564e-06,
197
+ "loss": 0.9629,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.070063694267516,
202
+ "grad_norm": 0.7524719834327698,
203
+ "learning_rate": 8.117449009293668e-06,
204
+ "loss": 0.6027,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.10828025477707,
209
+ "grad_norm": 0.592254102230072,
210
+ "learning_rate": 7.938926261462366e-06,
211
+ "loss": 0.5297,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.1464968152866242,
216
+ "grad_norm": 0.7852796912193298,
217
+ "learning_rate": 7.754484907260513e-06,
218
+ "loss": 0.6182,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.1847133757961783,
223
+ "grad_norm": 0.830742359161377,
224
+ "learning_rate": 7.564496387029532e-06,
225
+ "loss": 0.6581,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.2229299363057324,
230
+ "grad_norm": 0.6159372925758362,
231
+ "learning_rate": 7.369343312364994e-06,
232
+ "loss": 0.6236,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.2611464968152866,
237
+ "grad_norm": 0.7226252555847168,
238
+ "learning_rate": 7.169418695587791e-06,
239
+ "loss": 0.618,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.2993630573248407,
244
+ "grad_norm": 0.6193709373474121,
245
+ "learning_rate": 6.965125158269619e-06,
246
+ "loss": 0.542,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.3375796178343948,
251
+ "grad_norm": 0.7392263412475586,
252
+ "learning_rate": 6.7568741204067145e-06,
253
+ "loss": 0.53,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.3757961783439492,
258
+ "grad_norm": 0.6274488568305969,
259
+ "learning_rate": 6.545084971874738e-06,
260
+ "loss": 0.6762,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.4140127388535033,
265
+ "grad_norm": 0.5716177821159363,
266
+ "learning_rate": 6.330184227833376e-06,
267
+ "loss": 0.5749,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.4522292993630574,
272
+ "grad_norm": 0.7565421462059021,
273
+ "learning_rate": 6.112604669781572e-06,
274
+ "loss": 0.5814,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.4904458598726116,
279
+ "grad_norm": 0.7007409334182739,
280
+ "learning_rate": 5.892784473993184e-06,
281
+ "loss": 0.6141,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.5286624203821657,
286
+ "grad_norm": 0.5515427589416504,
287
+ "learning_rate": 5.671166329088278e-06,
288
+ "loss": 0.4922,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.5668789808917198,
293
+ "grad_norm": 0.701950192451477,
294
+ "learning_rate": 5.448196544517168e-06,
295
+ "loss": 0.5835,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.605095541401274,
300
+ "grad_norm": 0.6372572779655457,
301
+ "learning_rate": 5.224324151752575e-06,
302
+ "loss": 0.5014,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.643312101910828,
307
+ "grad_norm": 0.6354508996009827,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.6538,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.6815286624203822,
314
+ "grad_norm": 0.5548213720321655,
315
+ "learning_rate": 4.775675848247427e-06,
316
+ "loss": 0.5819,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.7197452229299364,
321
+ "grad_norm": 0.4872737228870392,
322
+ "learning_rate": 4.551803455482833e-06,
323
+ "loss": 0.4779,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.7579617834394905,
328
+ "grad_norm": 0.5852910876274109,
329
+ "learning_rate": 4.3288336709117246e-06,
330
+ "loss": 0.6624,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.7961783439490446,
335
+ "grad_norm": 0.49762701988220215,
336
+ "learning_rate": 4.107215526006818e-06,
337
+ "loss": 0.5426,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.8343949044585988,
342
+ "grad_norm": 0.5693338513374329,
343
+ "learning_rate": 3.887395330218429e-06,
344
+ "loss": 0.5471,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.872611464968153,
349
+ "grad_norm": 0.6038720607757568,
350
+ "learning_rate": 3.669815772166625e-06,
351
+ "loss": 0.6022,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.910828025477707,
356
+ "grad_norm": 0.49600663781166077,
357
+ "learning_rate": 3.4549150281252635e-06,
358
+ "loss": 0.507,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.9490445859872612,
363
+ "grad_norm": 0.5460913181304932,
364
+ "learning_rate": 3.2431258795932863e-06,
365
+ "loss": 0.5469,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.9872611464968153,
370
+ "grad_norm": 0.530115008354187,
371
+ "learning_rate": 3.0348748417303826e-06,
372
+ "loss": 0.5327,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 2.0254777070063694,
377
+ "grad_norm": 1.14858877658844,
378
+ "learning_rate": 2.83058130441221e-06,
379
+ "loss": 0.837,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 2.0636942675159236,
384
+ "grad_norm": 0.5498645901679993,
385
+ "learning_rate": 2.6306566876350072e-06,
386
+ "loss": 0.5906,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 2.1019108280254777,
391
+ "grad_norm": 0.5188542604446411,
392
+ "learning_rate": 2.43550361297047e-06,
393
+ "loss": 0.5788,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 2.140127388535032,
398
+ "grad_norm": 0.4956539273262024,
399
+ "learning_rate": 2.245515092739488e-06,
400
+ "loss": 0.5361,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 2.178343949044586,
405
+ "grad_norm": 0.6037235260009766,
406
+ "learning_rate": 2.061073738537635e-06,
407
+ "loss": 0.5584,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.21656050955414,
412
+ "grad_norm": 0.4257795810699463,
413
+ "learning_rate": 1.8825509907063328e-06,
414
+ "loss": 0.4353,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.254777070063694,
419
+ "grad_norm": 0.5109358429908752,
420
+ "learning_rate": 1.7103063703014372e-06,
421
+ "loss": 0.5412,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.2929936305732483,
426
+ "grad_norm": 0.4674205780029297,
427
+ "learning_rate": 1.544686755065677e-06,
428
+ "loss": 0.5459,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.3312101910828025,
433
+ "grad_norm": 0.47286278009414673,
434
+ "learning_rate": 1.3860256808630429e-06,
435
+ "loss": 0.4947,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.3694267515923566,
440
+ "grad_norm": 0.49508610367774963,
441
+ "learning_rate": 1.234642669981946e-06,
442
+ "loss": 0.4856,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.4076433121019107,
447
+ "grad_norm": 0.42003560066223145,
448
+ "learning_rate": 1.0908425876598512e-06,
449
+ "loss": 0.4792,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.445859872611465,
454
+ "grad_norm": 0.48869258165359497,
455
+ "learning_rate": 9.549150281252633e-07,
456
+ "loss": 0.5505,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.484076433121019,
461
+ "grad_norm": 0.5102881789207458,
462
+ "learning_rate": 8.271337313934869e-07,
463
+ "loss": 0.4618,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.522292993630573,
468
+ "grad_norm": 0.5060379505157471,
469
+ "learning_rate": 7.077560319906696e-07,
470
+ "loss": 0.5975,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.5605095541401273,
475
+ "grad_norm": 0.4596272110939026,
476
+ "learning_rate": 5.9702234071631e-07,
477
+ "loss": 0.5184,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.5987261146496814,
482
+ "grad_norm": 0.4477904736995697,
483
+ "learning_rate": 4.951556604879049e-07,
484
+ "loss": 0.4971,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.6369426751592355,
489
+ "grad_norm": 0.4290829002857208,
490
+ "learning_rate": 4.0236113724274716e-07,
491
+ "loss": 0.4872,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.6751592356687897,
496
+ "grad_norm": 0.4998835325241089,
497
+ "learning_rate": 3.18825646801314e-07,
498
+ "loss": 0.4768,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.713375796178344,
503
+ "grad_norm": 0.5172039270401001,
504
+ "learning_rate": 2.447174185242324e-07,
505
+ "loss": 0.5693,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.7515923566878984,
510
+ "grad_norm": 0.4305104613304138,
511
+ "learning_rate": 1.801856965207338e-07,
512
+ "loss": 0.5935,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.789808917197452,
517
+ "grad_norm": 0.4256463348865509,
518
+ "learning_rate": 1.253604390908819e-07,
519
+ "loss": 0.511,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.8280254777070066,
524
+ "grad_norm": 0.5269811153411865,
525
+ "learning_rate": 8.035205700685167e-08,
526
+ "loss": 0.577,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.8662420382165603,
531
+ "grad_norm": 0.4299260377883911,
532
+ "learning_rate": 4.52511911603265e-08,
533
+ "loss": 0.5992,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.904458598726115,
538
+ "grad_norm": 0.45451387763023376,
539
+ "learning_rate": 2.012853002380466e-08,
540
+ "loss": 0.5475,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.9426751592356686,
545
+ "grad_norm": 0.4655923843383789,
546
+ "learning_rate": 5.034667293427053e-09,
547
+ "loss": 0.5231,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.980891719745223,
552
+ "grad_norm": 0.4951322376728058,
553
+ "learning_rate": 0.0,
554
+ "loss": 0.5876,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.980891719745223,
559
+ "step": 78,
560
+ "total_flos": 47460738555904.0,
561
+ "train_loss": 0.6236666376009966,
562
+ "train_runtime": 2174.9739,
563
+ "train_samples_per_second": 3.448,
564
+ "train_steps_per_second": 0.036
565
+ }
566
+ ],
567
+ "logging_steps": 1.0,
568
+ "max_steps": 78,
569
+ "num_input_tokens_seen": 0,
570
+ "num_train_epochs": 3,
571
+ "save_steps": 500,
572
+ "stateful_callbacks": {
573
+ "TrainerControl": {
574
+ "args": {
575
+ "should_epoch_stop": false,
576
+ "should_evaluate": false,
577
+ "should_log": false,
578
+ "should_save": true,
579
+ "should_training_stop": true
580
+ },
581
+ "attributes": {}
582
+ }
583
+ },
584
+ "total_flos": 47460738555904.0,
585
+ "train_batch_size": 1,
586
+ "trial_name": null,
587
+ "trial_params": null
588
+ }
training_loss.png ADDED