TitleOS commited on
Commit
cc73e34
·
verified ·
1 Parent(s): b8a8a59

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -478
trainer_state.json DELETED
@@ -1,478 +0,0 @@
1
- {
2
- "best_global_step": 600,
3
- "best_metric": 1.4698271751403809,
4
- "best_model_checkpoint": "output\\galactic_reasoning_1b\\checkpoint-600",
5
- "epoch": 0.06,
6
- "eval_steps": 200,
7
- "global_step": 600,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.001,
14
- "grad_norm": 0.06737130880355835,
15
- "learning_rate": 9e-06,
16
- "loss": 1.9371,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.002,
21
- "grad_norm": 0.07842425256967545,
22
- "learning_rate": 1.9e-05,
23
- "loss": 1.9399,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.003,
28
- "grad_norm": 0.10731378942728043,
29
- "learning_rate": 2.9e-05,
30
- "loss": 1.9374,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.004,
35
- "grad_norm": 0.12309419363737106,
36
- "learning_rate": 3.9000000000000006e-05,
37
- "loss": 1.9112,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.005,
42
- "grad_norm": 0.11017554998397827,
43
- "learning_rate": 4.9e-05,
44
- "loss": 1.871,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.006,
49
- "grad_norm": 0.16252341866493225,
50
- "learning_rate": 5.9e-05,
51
- "loss": 1.8408,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.007,
56
- "grad_norm": 0.1429395228624344,
57
- "learning_rate": 6.9e-05,
58
- "loss": 1.8236,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.008,
63
- "grad_norm": 0.15082544088363647,
64
- "learning_rate": 7.900000000000001e-05,
65
- "loss": 1.7789,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.009,
70
- "grad_norm": 0.16160228848457336,
71
- "learning_rate": 8.900000000000001e-05,
72
- "loss": 1.744,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.01,
77
- "grad_norm": 0.17471027374267578,
78
- "learning_rate": 9.900000000000001e-05,
79
- "loss": 1.7349,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.011,
84
- "grad_norm": 0.16684666275978088,
85
- "learning_rate": 9.990909090909092e-05,
86
- "loss": 1.6772,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.012,
91
- "grad_norm": 0.1762007474899292,
92
- "learning_rate": 9.980808080808081e-05,
93
- "loss": 1.6622,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.013,
98
- "grad_norm": 0.17090925574302673,
99
- "learning_rate": 9.970707070707072e-05,
100
- "loss": 1.6644,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.014,
105
- "grad_norm": 0.18479526042938232,
106
- "learning_rate": 9.960606060606061e-05,
107
- "loss": 1.642,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.015,
112
- "grad_norm": 0.18685005605220795,
113
- "learning_rate": 9.950505050505052e-05,
114
- "loss": 1.6376,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.016,
119
- "grad_norm": 0.18370380997657776,
120
- "learning_rate": 9.940404040404041e-05,
121
- "loss": 1.6296,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.017,
126
- "grad_norm": 0.20909732580184937,
127
- "learning_rate": 9.93030303030303e-05,
128
- "loss": 1.6176,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.018,
133
- "grad_norm": 0.20230641961097717,
134
- "learning_rate": 9.920202020202021e-05,
135
- "loss": 1.6112,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.019,
140
- "grad_norm": 0.21034330129623413,
141
- "learning_rate": 9.91010101010101e-05,
142
- "loss": 1.6239,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.02,
147
- "grad_norm": 0.19535459578037262,
148
- "learning_rate": 9.900000000000001e-05,
149
- "loss": 1.6168,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.02,
154
- "eval_loss": 1.5481634140014648,
155
- "eval_runtime": 2829.9217,
156
- "eval_samples_per_second": 0.353,
157
- "eval_steps_per_second": 0.044,
158
- "step": 200
159
- },
160
- {
161
- "epoch": 0.021,
162
- "grad_norm": 0.20927906036376953,
163
- "learning_rate": 9.88989898989899e-05,
164
- "loss": 1.6216,
165
- "step": 210
166
- },
167
- {
168
- "epoch": 0.022,
169
- "grad_norm": 0.21300119161605835,
170
- "learning_rate": 9.87979797979798e-05,
171
- "loss": 1.5735,
172
- "step": 220
173
- },
174
- {
175
- "epoch": 0.023,
176
- "grad_norm": 0.23267202079296112,
177
- "learning_rate": 9.86969696969697e-05,
178
- "loss": 1.5988,
179
- "step": 230
180
- },
181
- {
182
- "epoch": 0.024,
183
- "grad_norm": 0.204238161444664,
184
- "learning_rate": 9.859595959595959e-05,
185
- "loss": 1.5656,
186
- "step": 240
187
- },
188
- {
189
- "epoch": 0.025,
190
- "grad_norm": 0.20555658638477325,
191
- "learning_rate": 9.84949494949495e-05,
192
- "loss": 1.5992,
193
- "step": 250
194
- },
195
- {
196
- "epoch": 0.026,
197
- "grad_norm": 0.19925552606582642,
198
- "learning_rate": 9.839393939393939e-05,
199
- "loss": 1.6159,
200
- "step": 260
201
- },
202
- {
203
- "epoch": 0.027,
204
- "grad_norm": 0.23314008116722107,
205
- "learning_rate": 9.82929292929293e-05,
206
- "loss": 1.604,
207
- "step": 270
208
- },
209
- {
210
- "epoch": 0.028,
211
- "grad_norm": 0.22813379764556885,
212
- "learning_rate": 9.81919191919192e-05,
213
- "loss": 1.5875,
214
- "step": 280
215
- },
216
- {
217
- "epoch": 0.029,
218
- "grad_norm": 0.22509580850601196,
219
- "learning_rate": 9.80909090909091e-05,
220
- "loss": 1.5872,
221
- "step": 290
222
- },
223
- {
224
- "epoch": 0.03,
225
- "grad_norm": 0.234571173787117,
226
- "learning_rate": 9.7989898989899e-05,
227
- "loss": 1.5947,
228
- "step": 300
229
- },
230
- {
231
- "epoch": 0.031,
232
- "grad_norm": 0.22278717160224915,
233
- "learning_rate": 9.78888888888889e-05,
234
- "loss": 1.5646,
235
- "step": 310
236
- },
237
- {
238
- "epoch": 0.032,
239
- "grad_norm": 0.21856215596199036,
240
- "learning_rate": 9.77878787878788e-05,
241
- "loss": 1.5572,
242
- "step": 320
243
- },
244
- {
245
- "epoch": 0.033,
246
- "grad_norm": 0.2208547592163086,
247
- "learning_rate": 9.76868686868687e-05,
248
- "loss": 1.5826,
249
- "step": 330
250
- },
251
- {
252
- "epoch": 0.034,
253
- "grad_norm": 0.2255655825138092,
254
- "learning_rate": 9.758585858585859e-05,
255
- "loss": 1.5816,
256
- "step": 340
257
- },
258
- {
259
- "epoch": 0.035,
260
- "grad_norm": 0.22580045461654663,
261
- "learning_rate": 9.748484848484849e-05,
262
- "loss": 1.5714,
263
- "step": 350
264
- },
265
- {
266
- "epoch": 0.036,
267
- "grad_norm": 0.2218249887228012,
268
- "learning_rate": 9.738383838383839e-05,
269
- "loss": 1.5463,
270
- "step": 360
271
- },
272
- {
273
- "epoch": 0.037,
274
- "grad_norm": 0.22902308404445648,
275
- "learning_rate": 9.728282828282829e-05,
276
- "loss": 1.5746,
277
- "step": 370
278
- },
279
- {
280
- "epoch": 0.038,
281
- "grad_norm": 0.21486122906208038,
282
- "learning_rate": 9.718181818181818e-05,
283
- "loss": 1.546,
284
- "step": 380
285
- },
286
- {
287
- "epoch": 0.039,
288
- "grad_norm": 0.21602007746696472,
289
- "learning_rate": 9.708080808080808e-05,
290
- "loss": 1.567,
291
- "step": 390
292
- },
293
- {
294
- "epoch": 0.04,
295
- "grad_norm": 0.2287064790725708,
296
- "learning_rate": 9.697979797979798e-05,
297
- "loss": 1.5585,
298
- "step": 400
299
- },
300
- {
301
- "epoch": 0.04,
302
- "eval_loss": 1.498089075088501,
303
- "eval_runtime": 2796.1826,
304
- "eval_samples_per_second": 0.358,
305
- "eval_steps_per_second": 0.045,
306
- "step": 400
307
- },
308
- {
309
- "epoch": 0.041,
310
- "grad_norm": 0.24416211247444153,
311
- "learning_rate": 9.687878787878788e-05,
312
- "loss": 1.5738,
313
- "step": 410
314
- },
315
- {
316
- "epoch": 0.042,
317
- "grad_norm": 0.2305736094713211,
318
- "learning_rate": 9.677777777777778e-05,
319
- "loss": 1.5628,
320
- "step": 420
321
- },
322
- {
323
- "epoch": 0.043,
324
- "grad_norm": 0.22666579484939575,
325
- "learning_rate": 9.667676767676768e-05,
326
- "loss": 1.5457,
327
- "step": 430
328
- },
329
- {
330
- "epoch": 0.044,
331
- "grad_norm": 0.24341981112957,
332
- "learning_rate": 9.657575757575758e-05,
333
- "loss": 1.5488,
334
- "step": 440
335
- },
336
- {
337
- "epoch": 0.045,
338
- "grad_norm": 0.250980406999588,
339
- "learning_rate": 9.647474747474749e-05,
340
- "loss": 1.5539,
341
- "step": 450
342
- },
343
- {
344
- "epoch": 0.046,
345
- "grad_norm": 0.24837073683738708,
346
- "learning_rate": 9.637373737373738e-05,
347
- "loss": 1.5556,
348
- "step": 460
349
- },
350
- {
351
- "epoch": 0.047,
352
- "grad_norm": 0.24370302259922028,
353
- "learning_rate": 9.627272727272729e-05,
354
- "loss": 1.5351,
355
- "step": 470
356
- },
357
- {
358
- "epoch": 0.048,
359
- "grad_norm": 0.2494235634803772,
360
- "learning_rate": 9.617171717171718e-05,
361
- "loss": 1.5729,
362
- "step": 480
363
- },
364
- {
365
- "epoch": 0.049,
366
- "grad_norm": 0.2377675473690033,
367
- "learning_rate": 9.607070707070707e-05,
368
- "loss": 1.5694,
369
- "step": 490
370
- },
371
- {
372
- "epoch": 0.05,
373
- "grad_norm": 0.23179057240486145,
374
- "learning_rate": 9.596969696969698e-05,
375
- "loss": 1.5497,
376
- "step": 500
377
- },
378
- {
379
- "epoch": 0.051,
380
- "grad_norm": 0.24259260296821594,
381
- "learning_rate": 9.586868686868687e-05,
382
- "loss": 1.538,
383
- "step": 510
384
- },
385
- {
386
- "epoch": 0.052,
387
- "grad_norm": 0.22587579488754272,
388
- "learning_rate": 9.576767676767678e-05,
389
- "loss": 1.5477,
390
- "step": 520
391
- },
392
- {
393
- "epoch": 0.053,
394
- "grad_norm": 0.2444010227918625,
395
- "learning_rate": 9.566666666666667e-05,
396
- "loss": 1.5616,
397
- "step": 530
398
- },
399
- {
400
- "epoch": 0.054,
401
- "grad_norm": 0.2342791110277176,
402
- "learning_rate": 9.556565656565656e-05,
403
- "loss": 1.5338,
404
- "step": 540
405
- },
406
- {
407
- "epoch": 0.055,
408
- "grad_norm": 0.22708754241466522,
409
- "learning_rate": 9.546464646464647e-05,
410
- "loss": 1.5249,
411
- "step": 550
412
- },
413
- {
414
- "epoch": 0.056,
415
- "grad_norm": 0.22712530195713043,
416
- "learning_rate": 9.536363636363636e-05,
417
- "loss": 1.5264,
418
- "step": 560
419
- },
420
- {
421
- "epoch": 0.057,
422
- "grad_norm": 0.24947647750377655,
423
- "learning_rate": 9.526262626262627e-05,
424
- "loss": 1.5329,
425
- "step": 570
426
- },
427
- {
428
- "epoch": 0.058,
429
- "grad_norm": 0.24310064315795898,
430
- "learning_rate": 9.516161616161616e-05,
431
- "loss": 1.5239,
432
- "step": 580
433
- },
434
- {
435
- "epoch": 0.059,
436
- "grad_norm": 0.23869813978672028,
437
- "learning_rate": 9.506060606060607e-05,
438
- "loss": 1.5123,
439
- "step": 590
440
- },
441
- {
442
- "epoch": 0.06,
443
- "grad_norm": 0.24522405862808228,
444
- "learning_rate": 9.495959595959596e-05,
445
- "loss": 1.5214,
446
- "step": 600
447
- },
448
- {
449
- "epoch": 0.06,
450
- "eval_loss": 1.4698271751403809,
451
- "eval_runtime": 2801.7352,
452
- "eval_samples_per_second": 0.357,
453
- "eval_steps_per_second": 0.045,
454
- "step": 600
455
- }
456
- ],
457
- "logging_steps": 10,
458
- "max_steps": 10000,
459
- "num_input_tokens_seen": 0,
460
- "num_train_epochs": 9223372036854775807,
461
- "save_steps": 200,
462
- "stateful_callbacks": {
463
- "TrainerControl": {
464
- "args": {
465
- "should_epoch_stop": false,
466
- "should_evaluate": false,
467
- "should_log": false,
468
- "should_save": true,
469
- "should_training_stop": false
470
- },
471
- "attributes": {}
472
- }
473
- },
474
- "total_flos": 1.3364964130445722e+17,
475
- "train_batch_size": 4,
476
- "trial_name": null,
477
- "trial_params": null
478
- }