sedrickkeh commited on
Commit
4f038d0
·
verified ·
1 Parent(s): 0aa629e

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: 1k_globalbatchsize32_lr5e6_epochs3
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 1k_globalbatchsize32_lr5e6_epochs3
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: 1k_globalbatchsize32_lr5e6_epochs3
 
16
 
17
  # 1k_globalbatchsize32_lr5e6_epochs3
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/openthoughts_1000 dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.976,
3
+ "total_flos": 5.107931021941146e+16,
4
+ "train_loss": 0.6129485577024439,
5
+ "train_runtime": 3284.9265,
6
+ "train_samples_per_second": 0.91,
7
+ "train_steps_per_second": 0.028
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.976,
3
+ "total_flos": 5.107931021941146e+16,
4
+ "train_loss": 0.6129485577024439,
5
+ "train_runtime": 3284.9265,
6
+ "train_samples_per_second": 0.91,
7
+ "train_steps_per_second": 0.028
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": 5.849673926536721,
14
+ "learning_rate": 5.000000000000001e-07,
15
+ "loss": 0.8186,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.064,
20
+ "grad_norm": 5.8970181550625895,
21
+ "learning_rate": 1.0000000000000002e-06,
22
+ "loss": 0.8458,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.096,
27
+ "grad_norm": 5.697363226671905,
28
+ "learning_rate": 1.5e-06,
29
+ "loss": 0.8305,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.128,
34
+ "grad_norm": 5.841753636905696,
35
+ "learning_rate": 2.0000000000000003e-06,
36
+ "loss": 0.868,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.16,
41
+ "grad_norm": 5.671243517334994,
42
+ "learning_rate": 2.5e-06,
43
+ "loss": 0.8036,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.192,
48
+ "grad_norm": 4.599014608569536,
49
+ "learning_rate": 3e-06,
50
+ "loss": 0.8808,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.224,
55
+ "grad_norm": 4.220193980086825,
56
+ "learning_rate": 3.5e-06,
57
+ "loss": 0.8373,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.256,
62
+ "grad_norm": 2.379366858517578,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.7709,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.288,
69
+ "grad_norm": 2.195706729610227,
70
+ "learning_rate": 4.5e-06,
71
+ "loss": 0.7403,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.32,
76
+ "grad_norm": 3.8473606579954094,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7736,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.352,
83
+ "grad_norm": 4.215166044150153,
84
+ "learning_rate": 4.998209387040829e-06,
85
+ "loss": 0.8299,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.384,
90
+ "grad_norm": 4.295222651552718,
91
+ "learning_rate": 4.992840113199131e-06,
92
+ "loss": 0.7895,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.416,
97
+ "grad_norm": 3.8988289446476796,
98
+ "learning_rate": 4.983899869907963e-06,
99
+ "loss": 0.723,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.448,
104
+ "grad_norm": 3.839958855257017,
105
+ "learning_rate": 4.971401463979722e-06,
106
+ "loss": 0.7461,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.48,
111
+ "grad_norm": 3.069526753856086,
112
+ "learning_rate": 4.955362799260507e-06,
113
+ "loss": 0.6986,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.512,
118
+ "grad_norm": 2.7386584473852658,
119
+ "learning_rate": 4.935806850983034e-06,
120
+ "loss": 0.7205,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.544,
125
+ "grad_norm": 2.02702044199497,
126
+ "learning_rate": 4.912761632854834e-06,
127
+ "loss": 0.7043,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.576,
132
+ "grad_norm": 1.5415003473808875,
133
+ "learning_rate": 4.8862601569288885e-06,
134
+ "loss": 0.6786,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.608,
139
+ "grad_norm": 1.6945417207348286,
140
+ "learning_rate": 4.8563403863141825e-06,
141
+ "loss": 0.7001,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.64,
146
+ "grad_norm": 1.3996088584254769,
147
+ "learning_rate": 4.823045180793914e-06,
148
+ "loss": 0.6194,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.672,
153
+ "grad_norm": 1.7673568712274899,
154
+ "learning_rate": 4.786422235429269e-06,
155
+ "loss": 0.6456,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.704,
160
+ "grad_norm": 1.623347448295577,
161
+ "learning_rate": 4.746524012236706e-06,
162
+ "loss": 0.6652,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.736,
167
+ "grad_norm": 1.2829766714727795,
168
+ "learning_rate": 4.703407665036622e-06,
169
+ "loss": 0.6032,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.768,
174
+ "grad_norm": 1.3613789016207494,
175
+ "learning_rate": 4.657134957581057e-06,
176
+ "loss": 0.7089,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.8,
181
+ "grad_norm": 0.9373480619558588,
182
+ "learning_rate": 4.607772175077712e-06,
183
+ "loss": 0.6395,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.832,
188
+ "grad_norm": 1.12602050571956,
189
+ "learning_rate": 4.555390029237026e-06,
190
+ "loss": 0.7021,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.864,
195
+ "grad_norm": 1.0086309702493645,
196
+ "learning_rate": 4.5000635569783365e-06,
197
+ "loss": 0.6345,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.896,
202
+ "grad_norm": 1.234160112595515,
203
+ "learning_rate": 4.4418720129402145e-06,
204
+ "loss": 0.6273,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.928,
209
+ "grad_norm": 0.9735941294239923,
210
+ "learning_rate": 4.3808987559489536e-06,
211
+ "loss": 0.6497,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.96,
216
+ "grad_norm": 0.8806041823335348,
217
+ "learning_rate": 4.317231129607859e-06,
218
+ "loss": 0.6714,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.992,
223
+ "grad_norm": 0.9271923458351733,
224
+ "learning_rate": 4.2509603371783776e-06,
225
+ "loss": 0.6328,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.024,
230
+ "grad_norm": 1.5098478417524255,
231
+ "learning_rate": 4.1821813109322975e-06,
232
+ "loss": 0.9666,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.056,
237
+ "grad_norm": 0.8108394298004445,
238
+ "learning_rate": 4.110992576162193e-06,
239
+ "loss": 0.5684,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.088,
244
+ "grad_norm": 0.8548590696244006,
245
+ "learning_rate": 4.037496110044885e-06,
246
+ "loss": 0.5749,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.12,
251
+ "grad_norm": 0.8745126302896333,
252
+ "learning_rate": 3.961797195560118e-06,
253
+ "loss": 0.614,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.152,
258
+ "grad_norm": 0.7435496429501566,
259
+ "learning_rate": 3.884004270673711e-06,
260
+ "loss": 0.5273,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.184,
265
+ "grad_norm": 0.7685963393034175,
266
+ "learning_rate": 3.8042287730012117e-06,
267
+ "loss": 0.6375,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.216,
272
+ "grad_norm": 0.8434136566563109,
273
+ "learning_rate": 3.7225849801745835e-06,
274
+ "loss": 0.6295,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.248,
279
+ "grad_norm": 0.7860421945854131,
280
+ "learning_rate": 3.6391898461406045e-06,
281
+ "loss": 0.5147,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.28,
286
+ "grad_norm": 0.6986247608098803,
287
+ "learning_rate": 3.55416283362546e-06,
288
+ "loss": 0.5539,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.312,
293
+ "grad_norm": 0.6004937658413751,
294
+ "learning_rate": 3.4676257430055438e-06,
295
+ "loss": 0.4879,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.3439999999999999,
300
+ "grad_norm": 0.6936826995472081,
301
+ "learning_rate": 3.3797025378295826e-06,
302
+ "loss": 0.627,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.376,
307
+ "grad_norm": 0.5956362371010271,
308
+ "learning_rate": 3.29051916724206e-06,
309
+ "loss": 0.4996,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.408,
314
+ "grad_norm": 0.6859466931561792,
315
+ "learning_rate": 3.2002033855622683e-06,
316
+ "loss": 0.6106,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.44,
321
+ "grad_norm": 0.843708683499078,
322
+ "learning_rate": 3.1088845692774798e-06,
323
+ "loss": 0.644,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.472,
328
+ "grad_norm": 0.6343088750841447,
329
+ "learning_rate": 3.0166935317123824e-06,
330
+ "loss": 0.5099,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.504,
335
+ "grad_norm": 0.7271302183612709,
336
+ "learning_rate": 2.9237623356402423e-06,
337
+ "loss": 0.5716,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.536,
342
+ "grad_norm": 0.7366637555716543,
343
+ "learning_rate": 2.8302241041042564e-06,
344
+ "loss": 0.5895,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.568,
349
+ "grad_norm": 0.8301563843419107,
350
+ "learning_rate": 2.7362128297200784e-06,
351
+ "loss": 0.6191,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.6,
356
+ "grad_norm": 0.6840596491206852,
357
+ "learning_rate": 2.6418631827326857e-06,
358
+ "loss": 0.5595,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.6320000000000001,
363
+ "grad_norm": 0.7095662290542607,
364
+ "learning_rate": 2.547310318102548e-06,
365
+ "loss": 0.5506,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.6640000000000001,
370
+ "grad_norm": 0.7447871051048682,
371
+ "learning_rate": 2.4526896818974534e-06,
372
+ "loss": 0.6013,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.696,
377
+ "grad_norm": 0.78939028510505,
378
+ "learning_rate": 2.358136817267315e-06,
379
+ "loss": 0.5804,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.728,
384
+ "grad_norm": 0.7221168629786532,
385
+ "learning_rate": 2.263787170279922e-06,
386
+ "loss": 0.5112,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.76,
391
+ "grad_norm": 0.6843052552942253,
392
+ "learning_rate": 2.169775895895745e-06,
393
+ "loss": 0.5302,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.792,
398
+ "grad_norm": 0.6466865515836445,
399
+ "learning_rate": 2.0762376643597586e-06,
400
+ "loss": 0.5912,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.8239999999999998,
405
+ "grad_norm": 0.6241622145357679,
406
+ "learning_rate": 1.9833064682876175e-06,
407
+ "loss": 0.524,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.8559999999999999,
412
+ "grad_norm": 0.6681670660427579,
413
+ "learning_rate": 1.8911154307225204e-06,
414
+ "loss": 0.567,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.888,
419
+ "grad_norm": 0.6084101203959995,
420
+ "learning_rate": 1.7997966144377328e-06,
421
+ "loss": 0.4889,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.92,
426
+ "grad_norm": 0.6661890505529855,
427
+ "learning_rate": 1.7094808327579401e-06,
428
+ "loss": 0.5566,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.952,
433
+ "grad_norm": 0.7309734200574032,
434
+ "learning_rate": 1.6202974621704176e-06,
435
+ "loss": 0.6002,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.984,
440
+ "grad_norm": 0.6816696022945047,
441
+ "learning_rate": 1.5323742569944573e-06,
442
+ "loss": 0.5745,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.016,
447
+ "grad_norm": 1.3649323993886235,
448
+ "learning_rate": 1.44583716637454e-06,
449
+ "loss": 0.8374,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.048,
454
+ "grad_norm": 0.6467643294360865,
455
+ "learning_rate": 1.3608101538593965e-06,
456
+ "loss": 0.5162,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.08,
461
+ "grad_norm": 0.685164030556072,
462
+ "learning_rate": 1.277415019825417e-06,
463
+ "loss": 0.5509,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.112,
468
+ "grad_norm": 0.6039417194223102,
469
+ "learning_rate": 1.195771226998789e-06,
470
+ "loss": 0.505,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.144,
475
+ "grad_norm": 0.6457046464618058,
476
+ "learning_rate": 1.1159957293262888e-06,
477
+ "loss": 0.5505,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.176,
482
+ "grad_norm": 0.51006085110857,
483
+ "learning_rate": 1.0382028044398823e-06,
484
+ "loss": 0.4181,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.208,
489
+ "grad_norm": 0.5817319940273514,
490
+ "learning_rate": 9.625038899551162e-07,
491
+ "loss": 0.5063,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.24,
496
+ "grad_norm": 0.616719797907229,
497
+ "learning_rate": 8.890074238378074e-07,
498
+ "loss": 0.5717,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.2720000000000002,
503
+ "grad_norm": 0.5698471944044463,
504
+ "learning_rate": 8.178186890677029e-07,
505
+ "loss": 0.5182,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.304,
510
+ "grad_norm": 0.6181330817750901,
511
+ "learning_rate": 7.490396628216237e-07,
512
+ "loss": 0.5755,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.336,
517
+ "grad_norm": 0.5507693283896078,
518
+ "learning_rate": 6.827688703921407e-07,
519
+ "loss": 0.4823,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.368,
524
+ "grad_norm": 0.5955200432739955,
525
+ "learning_rate": 6.191012440510469e-07,
526
+ "loss": 0.53,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.4,
531
+ "grad_norm": 0.5637517004790812,
532
+ "learning_rate": 5.581279870597866e-07,
533
+ "loss": 0.4502,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.432,
538
+ "grad_norm": 0.7466890560657303,
539
+ "learning_rate": 4.999364430216639e-07,
540
+ "loss": 0.6202,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.464,
545
+ "grad_norm": 0.5634548289522667,
546
+ "learning_rate": 4.4460997076297504e-07,
547
+ "loss": 0.4654,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.496,
552
+ "grad_norm": 0.5460988308014747,
553
+ "learning_rate": 3.922278249222894e-07,
554
+ "loss": 0.4881,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 2.528,
559
+ "grad_norm": 0.5526022579328083,
560
+ "learning_rate": 3.4286504241894283e-07,
561
+ "loss": 0.4975,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 2.56,
566
+ "grad_norm": 0.622419564871221,
567
+ "learning_rate": 2.965923349633779e-07,
568
+ "loss": 0.605,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 2.592,
573
+ "grad_norm": 0.6459977525358341,
574
+ "learning_rate": 2.53475987763295e-07,
575
+ "loss": 0.5747,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 2.624,
580
+ "grad_norm": 0.577093639398248,
581
+ "learning_rate": 2.135777645707318e-07,
582
+ "loss": 0.4929,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 2.656,
587
+ "grad_norm": 0.5651216938831269,
588
+ "learning_rate": 1.7695481920608716e-07,
589
+ "loss": 0.5086,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 2.6879999999999997,
594
+ "grad_norm": 0.6067146555637166,
595
+ "learning_rate": 1.4365961368581844e-07,
596
+ "loss": 0.565,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 2.7199999999999998,
601
+ "grad_norm": 0.6317650182194224,
602
+ "learning_rate": 1.137398430711123e-07,
603
+ "loss": 0.603,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 2.752,
608
+ "grad_norm": 0.44966045140241284,
609
+ "learning_rate": 8.723836714516681e-08,
610
+ "loss": 0.3893,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 2.784,
615
+ "grad_norm": 0.5953264863370202,
616
+ "learning_rate": 6.419314901696671e-08,
617
+ "loss": 0.5293,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 2.816,
622
+ "grad_norm": 0.5479215502914991,
623
+ "learning_rate": 4.4637200739493514e-08,
624
+ "loss": 0.5167,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 2.848,
629
+ "grad_norm": 0.48730983980669906,
630
+ "learning_rate": 2.8598536020278678e-08,
631
+ "loss": 0.4821,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 2.88,
636
+ "grad_norm": 0.6545838078994339,
637
+ "learning_rate": 1.6100130092037704e-08,
638
+ "loss": 0.645,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 2.912,
643
+ "grad_norm": 0.5375454814372095,
644
+ "learning_rate": 7.159886800869875e-09,
645
+ "loss": 0.4611,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 2.944,
650
+ "grad_norm": 0.5959972228051752,
651
+ "learning_rate": 1.7906129591713228e-09,
652
+ "loss": 0.5646,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 2.976,
657
+ "grad_norm": 0.5297891060878839,
658
+ "learning_rate": 0.0,
659
+ "loss": 0.4423,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 2.976,
664
+ "step": 93,
665
+ "total_flos": 5.107931021941146e+16,
666
+ "train_loss": 0.6129485577024439,
667
+ "train_runtime": 3284.9265,
668
+ "train_samples_per_second": 0.91,
669
+ "train_steps_per_second": 0.028
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": 5.107931021941146e+16,
690
+ "train_batch_size": 1,
691
+ "trial_name": null,
692
+ "trial_params": null
693
+ }
training_loss.png ADDED