Text Generation
Transformers
PyTorch
English
llama
code
text-generation-inference
Inference Endpoints
Pasta009 commited on
Commit
5b28a27
1 Parent(s): 4fe37b9

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -496
trainer_state.json DELETED
@@ -1,496 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
- "eval_steps": 500,
6
- "global_step": 784,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.03,
13
- "learning_rate": 1.99919725148484e-05,
14
- "loss": 0.5476,
15
- "step": 10
16
- },
17
- {
18
- "epoch": 0.05,
19
- "learning_rate": 1.9967902947497158e-05,
20
- "loss": 0.4891,
21
- "step": 20
22
- },
23
- {
24
- "epoch": 0.08,
25
- "learning_rate": 1.9927829941565187e-05,
26
- "loss": 0.4573,
27
- "step": 30
28
- },
29
- {
30
- "epoch": 0.1,
31
- "learning_rate": 1.9871817834144506e-05,
32
- "loss": 0.4521,
33
- "step": 40
34
- },
35
- {
36
- "epoch": 0.13,
37
- "learning_rate": 1.9799956552507235e-05,
38
- "loss": 0.4565,
39
- "step": 50
40
- },
41
- {
42
- "epoch": 0.15,
43
- "learning_rate": 1.971236146972764e-05,
44
- "loss": 0.4528,
45
- "step": 60
46
- },
47
- {
48
- "epoch": 0.18,
49
- "learning_rate": 1.9609173219450998e-05,
50
- "loss": 0.4456,
51
- "step": 70
52
- },
53
- {
54
- "epoch": 0.2,
55
- "learning_rate": 1.949055747010669e-05,
56
- "loss": 0.4407,
57
- "step": 80
58
- },
59
- {
60
- "epoch": 0.23,
61
- "learning_rate": 1.9356704658928036e-05,
62
- "loss": 0.4251,
63
- "step": 90
64
- },
65
- {
66
- "epoch": 0.26,
67
- "learning_rate": 1.9207829686205882e-05,
68
- "loss": 0.4372,
69
- "step": 100
70
- },
71
- {
72
- "epoch": 0.28,
73
- "learning_rate": 1.904417157026683e-05,
74
- "loss": 0.4439,
75
- "step": 110
76
- },
77
- {
78
- "epoch": 0.31,
79
- "learning_rate": 1.8865993063730003e-05,
80
- "loss": 0.4305,
81
- "step": 120
82
- },
83
- {
84
- "epoch": 0.33,
85
- "learning_rate": 1.867358023165851e-05,
86
- "loss": 0.4395,
87
- "step": 130
88
- },
89
- {
90
- "epoch": 0.36,
91
- "learning_rate": 1.8467241992282842e-05,
92
- "loss": 0.4402,
93
- "step": 140
94
- },
95
- {
96
- "epoch": 0.38,
97
- "learning_rate": 1.824730962103356e-05,
98
- "loss": 0.4382,
99
- "step": 150
100
- },
101
- {
102
- "epoch": 0.41,
103
- "learning_rate": 1.8014136218679566e-05,
104
- "loss": 0.4359,
105
- "step": 160
106
- },
107
- {
108
- "epoch": 0.43,
109
- "learning_rate": 1.7768096144425903e-05,
110
- "loss": 0.4202,
111
- "step": 170
112
- },
113
- {
114
- "epoch": 0.46,
115
- "learning_rate": 1.7509584414881114e-05,
116
- "loss": 0.4181,
117
- "step": 180
118
- },
119
- {
120
- "epoch": 0.48,
121
- "learning_rate": 1.7239016069859292e-05,
122
- "loss": 0.4263,
123
- "step": 190
124
- },
125
- {
126
- "epoch": 0.51,
127
- "learning_rate": 1.6956825506034866e-05,
128
- "loss": 0.4227,
129
- "step": 200
130
- },
131
- {
132
- "epoch": 0.54,
133
- "learning_rate": 1.6663465779520042e-05,
134
- "loss": 0.4165,
135
- "step": 210
136
- },
137
- {
138
- "epoch": 0.56,
139
- "learning_rate": 1.635940787848455e-05,
140
- "loss": 0.4213,
141
- "step": 220
142
- },
143
- {
144
- "epoch": 0.59,
145
- "learning_rate": 1.6045139966985562e-05,
146
- "loss": 0.4197,
147
- "step": 230
148
- },
149
- {
150
- "epoch": 0.61,
151
- "learning_rate": 1.5721166601221697e-05,
152
- "loss": 0.4257,
153
- "step": 240
154
- },
155
- {
156
- "epoch": 0.64,
157
- "learning_rate": 1.5388007919469604e-05,
158
- "loss": 0.4216,
159
- "step": 250
160
- },
161
- {
162
- "epoch": 0.66,
163
- "learning_rate": 1.504619880700346e-05,
164
- "loss": 0.4171,
165
- "step": 260
166
- },
167
- {
168
- "epoch": 0.69,
169
- "learning_rate": 1.4696288037338258e-05,
170
- "loss": 0.42,
171
- "step": 270
172
- },
173
- {
174
- "epoch": 0.71,
175
- "learning_rate": 1.4338837391175582e-05,
176
- "loss": 0.4179,
177
- "step": 280
178
- },
179
- {
180
- "epoch": 0.74,
181
- "learning_rate": 1.397442075446633e-05,
182
- "loss": 0.4183,
183
- "step": 290
184
- },
185
- {
186
- "epoch": 0.77,
187
- "learning_rate": 1.3603623197038536e-05,
188
- "loss": 0.4291,
189
- "step": 300
190
- },
191
- {
192
- "epoch": 0.79,
193
- "learning_rate": 1.3227040033269501e-05,
194
- "loss": 0.4142,
195
- "step": 310
196
- },
197
- {
198
- "epoch": 0.82,
199
- "learning_rate": 1.2845275866310325e-05,
200
- "loss": 0.4154,
201
- "step": 320
202
- },
203
- {
204
- "epoch": 0.84,
205
- "learning_rate": 1.2458943617397346e-05,
206
- "loss": 0.4199,
207
- "step": 330
208
- },
209
- {
210
- "epoch": 0.87,
211
- "learning_rate": 1.206866354180891e-05,
212
- "loss": 0.4213,
213
- "step": 340
214
- },
215
- {
216
- "epoch": 0.89,
217
- "learning_rate": 1.1675062233047365e-05,
218
- "loss": 0.4039,
219
- "step": 350
220
- },
221
- {
222
- "epoch": 0.92,
223
- "learning_rate": 1.1278771616845061e-05,
224
- "loss": 0.4065,
225
- "step": 360
226
- },
227
- {
228
- "epoch": 0.94,
229
- "learning_rate": 1.0880427936609455e-05,
230
- "loss": 0.4117,
231
- "step": 370
232
- },
233
- {
234
- "epoch": 0.97,
235
- "learning_rate": 1.0480670731936209e-05,
236
- "loss": 0.4132,
237
- "step": 380
238
- },
239
- {
240
- "epoch": 0.99,
241
- "learning_rate": 1.0080141811830277e-05,
242
- "loss": 0.4099,
243
- "step": 390
244
- },
245
- {
246
- "epoch": 1.02,
247
- "learning_rate": 9.67948422428345e-06,
248
- "loss": 0.3254,
249
- "step": 400
250
- },
251
- {
252
- "epoch": 1.05,
253
- "learning_rate": 9.279341223862705e-06,
254
- "loss": 0.2853,
255
- "step": 410
256
- },
257
- {
258
- "epoch": 1.07,
259
- "learning_rate": 8.880355238966923e-06,
260
- "loss": 0.2822,
261
- "step": 420
262
- },
263
- {
264
- "epoch": 1.1,
265
- "learning_rate": 8.483166840409996e-06,
266
- "loss": 0.2859,
267
- "step": 430
268
- },
269
- {
270
- "epoch": 1.12,
271
- "learning_rate": 8.08841371298628e-06,
272
- "loss": 0.2797,
273
- "step": 440
274
- },
275
- {
276
- "epoch": 1.15,
277
- "learning_rate": 7.696729631669563e-06,
278
- "loss": 0.2731,
279
- "step": 450
280
- },
281
- {
282
- "epoch": 1.17,
283
- "learning_rate": 7.308743444089232e-06,
284
- "loss": 0.27,
285
- "step": 460
286
- },
287
- {
288
- "epoch": 1.2,
289
- "learning_rate": 6.925078060917245e-06,
290
- "loss": 0.2809,
291
- "step": 470
292
- },
293
- {
294
- "epoch": 1.22,
295
- "learning_rate": 6.546349455786926e-06,
296
- "loss": 0.28,
297
- "step": 480
298
- },
299
- {
300
- "epoch": 1.25,
301
- "learning_rate": 6.173165676349103e-06,
302
- "loss": 0.2863,
303
- "step": 490
304
- },
305
- {
306
- "epoch": 1.28,
307
- "learning_rate": 5.806125868053433e-06,
308
- "loss": 0.2804,
309
- "step": 500
310
- },
311
- {
312
- "epoch": 1.3,
313
- "learning_rate": 5.4458193122221405e-06,
314
- "loss": 0.2797,
315
- "step": 510
316
- },
317
- {
318
- "epoch": 1.33,
319
- "learning_rate": 5.092824479960625e-06,
320
- "loss": 0.2861,
321
- "step": 520
322
- },
323
- {
324
- "epoch": 1.35,
325
- "learning_rate": 4.747708103423791e-06,
326
- "loss": 0.2777,
327
- "step": 530
328
- },
329
- {
330
- "epoch": 1.38,
331
- "learning_rate": 4.411024265929283e-06,
332
- "loss": 0.2791,
333
- "step": 540
334
- },
335
- {
336
- "epoch": 1.4,
337
- "learning_rate": 4.083313512378368e-06,
338
- "loss": 0.275,
339
- "step": 550
340
- },
341
- {
342
- "epoch": 1.43,
343
- "learning_rate": 3.7651019814126656e-06,
344
- "loss": 0.2787,
345
- "step": 560
346
- },
347
- {
348
- "epoch": 1.45,
349
- "learning_rate": 3.456900560700158e-06,
350
- "loss": 0.2777,
351
- "step": 570
352
- },
353
- {
354
- "epoch": 1.48,
355
- "learning_rate": 3.1592040667065393e-06,
356
- "loss": 0.2727,
357
- "step": 580
358
- },
359
- {
360
- "epoch": 1.51,
361
- "learning_rate": 2.8724904502688566e-06,
362
- "loss": 0.2748,
363
- "step": 590
364
- },
365
- {
366
- "epoch": 1.53,
367
- "learning_rate": 2.597220029246846e-06,
368
- "loss": 0.2809,
369
- "step": 600
370
- },
371
- {
372
- "epoch": 1.56,
373
- "learning_rate": 2.333834749484e-06,
374
- "loss": 0.2706,
375
- "step": 610
376
- },
377
- {
378
- "epoch": 1.58,
379
- "learning_rate": 2.082757475264804e-06,
380
- "loss": 0.2748,
381
- "step": 620
382
- },
383
- {
384
- "epoch": 1.61,
385
- "learning_rate": 1.8443913104073984e-06,
386
- "loss": 0.273,
387
- "step": 630
388
- },
389
- {
390
- "epoch": 1.63,
391
- "learning_rate": 1.6191189510815942e-06,
392
- "loss": 0.2788,
393
- "step": 640
394
- },
395
- {
396
- "epoch": 1.66,
397
- "learning_rate": 1.4073020713912988e-06,
398
- "loss": 0.2741,
399
- "step": 650
400
- },
401
- {
402
- "epoch": 1.68,
403
- "learning_rate": 1.209280742707828e-06,
404
- "loss": 0.2749,
405
- "step": 660
406
- },
407
- {
408
- "epoch": 1.71,
409
- "learning_rate": 1.0253728876863256e-06,
410
- "loss": 0.2739,
411
- "step": 670
412
- },
413
- {
414
- "epoch": 1.73,
415
- "learning_rate": 8.558737698418762e-07,
416
- "loss": 0.27,
417
- "step": 680
418
- },
419
- {
420
- "epoch": 1.76,
421
- "learning_rate": 7.010555195048241e-07,
422
- "loss": 0.2683,
423
- "step": 690
424
- },
425
- {
426
- "epoch": 1.79,
427
- "learning_rate": 5.611666969163243e-07,
428
- "loss": 0.2701,
429
- "step": 700
430
- },
431
- {
432
- "epoch": 1.81,
433
- "learning_rate": 4.3643189316561864e-07,
434
- "loss": 0.2705,
435
- "step": 710
436
- },
437
- {
438
- "epoch": 1.84,
439
- "learning_rate": 3.2705136960970554e-07,
440
- "loss": 0.2695,
441
- "step": 720
442
- },
443
- {
444
- "epoch": 1.86,
445
- "learning_rate": 2.3320073635432984e-07,
446
- "loss": 0.2747,
447
- "step": 730
448
- },
449
- {
450
- "epoch": 1.89,
451
- "learning_rate": 1.55030670312476e-07,
452
- "loss": 0.273,
453
- "step": 740
454
- },
455
- {
456
- "epoch": 1.91,
457
- "learning_rate": 9.26666732930348e-08,
458
- "loss": 0.2721,
459
- "step": 750
460
- },
461
- {
462
- "epoch": 1.94,
463
- "learning_rate": 4.6208870508017703e-08,
464
- "loss": 0.2798,
465
- "step": 760
466
- },
467
- {
468
- "epoch": 1.96,
469
- "learning_rate": 1.5731849821833955e-08,
470
- "loss": 0.2738,
471
- "step": 770
472
- },
473
- {
474
- "epoch": 1.99,
475
- "learning_rate": 1.2845420006879494e-09,
476
- "loss": 0.2722,
477
- "step": 780
478
- },
479
- {
480
- "epoch": 2.0,
481
- "step": 784,
482
- "total_flos": 1134283296079872.0,
483
- "train_loss": 0.3541707301474347,
484
- "train_runtime": 33786.0741,
485
- "train_samples_per_second": 5.938,
486
- "train_steps_per_second": 0.023
487
- }
488
- ],
489
- "logging_steps": 10,
490
- "max_steps": 784,
491
- "num_train_epochs": 2,
492
- "save_steps": 500,
493
- "total_flos": 1134283296079872.0,
494
- "trial_name": null,
495
- "trial_params": null
496
- }