QuantaSparkLabs commited on
Commit
21907c4
·
verified ·
1 Parent(s): 25085cf

Delete checkpoint-500/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-500/trainer_state.json +0 -384
checkpoint-500/trainer_state.json DELETED
@@ -1,384 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 62.5,
6
- "eval_steps": 500,
7
- "global_step": 500,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 1.25,
14
- "grad_norm": 0.05793992057442665,
15
- "learning_rate": 0.009949685534591196,
16
- "loss": 1.206215763092041,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 2.5,
21
- "grad_norm": 0.15641599893569946,
22
- "learning_rate": 0.009823899371069183,
23
- "loss": 1.1944643020629884,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 3.75,
28
- "grad_norm": 0.25837442278862,
29
- "learning_rate": 0.00969811320754717,
30
- "loss": 1.1607371330261231,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 5.0,
35
- "grad_norm": 0.34708642959594727,
36
- "learning_rate": 0.009572327044025157,
37
- "loss": 1.101412010192871,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 6.25,
42
- "grad_norm": 0.4044564962387085,
43
- "learning_rate": 0.009446540880503144,
44
- "loss": 1.0188076972961426,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 7.5,
49
- "grad_norm": 0.4182046055793762,
50
- "learning_rate": 0.009320754716981133,
51
- "loss": 0.9222237586975097,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 8.75,
56
- "grad_norm": 0.38868534564971924,
57
- "learning_rate": 0.00919496855345912,
58
- "loss": 0.8254497528076172,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 10.0,
63
- "grad_norm": 0.3328922390937805,
64
- "learning_rate": 0.009069182389937107,
65
- "loss": 0.7411866188049316,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 11.25,
70
- "grad_norm": 0.27316856384277344,
71
- "learning_rate": 0.008943396226415094,
72
- "loss": 0.6766499042510986,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 12.5,
77
- "grad_norm": 0.21604125201702118,
78
- "learning_rate": 0.008817610062893081,
79
- "loss": 0.6312645435333252,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 13.75,
84
- "grad_norm": 0.17572654783725739,
85
- "learning_rate": 0.00869182389937107,
86
- "loss": 0.6011325359344483,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 15.0,
91
- "grad_norm": 0.15216749906539917,
92
- "learning_rate": 0.008566037735849057,
93
- "loss": 0.5812094688415528,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 16.25,
98
- "grad_norm": 0.12060005962848663,
99
- "learning_rate": 0.008440251572327044,
100
- "loss": 0.5678437232971192,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 17.5,
105
- "grad_norm": 0.11622311919927597,
106
- "learning_rate": 0.008314465408805032,
107
- "loss": 0.5585259437561035,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 18.75,
112
- "grad_norm": 0.08831977844238281,
113
- "learning_rate": 0.008188679245283019,
114
- "loss": 0.5519348621368408,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 20.0,
119
- "grad_norm": 0.09614107757806778,
120
- "learning_rate": 0.008062893081761007,
121
- "loss": 0.5471037864685059,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 21.25,
126
- "grad_norm": 0.07089235633611679,
127
- "learning_rate": 0.007937106918238995,
128
- "loss": 0.5432851314544678,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 22.5,
133
- "grad_norm": 0.061037734150886536,
134
- "learning_rate": 0.007811320754716982,
135
- "loss": 0.5403900146484375,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 23.75,
140
- "grad_norm": 0.09448318183422089,
141
- "learning_rate": 0.00768553459119497,
142
- "loss": 0.53807373046875,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 25.0,
147
- "grad_norm": 0.050825681537389755,
148
- "learning_rate": 0.007559748427672957,
149
- "loss": 0.5360239028930665,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 26.25,
154
- "grad_norm": 0.11754798144102097,
155
- "learning_rate": 0.007433962264150943,
156
- "loss": 0.5343667507171631,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 27.5,
161
- "grad_norm": 0.04136759415268898,
162
- "learning_rate": 0.00730817610062893,
163
- "loss": 0.5332566738128662,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 28.75,
168
- "grad_norm": 0.061312805861234665,
169
- "learning_rate": 0.007182389937106918,
170
- "loss": 0.5320106983184815,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 30.0,
175
- "grad_norm": 0.045437928289175034,
176
- "learning_rate": 0.007056603773584905,
177
- "loss": 0.5310849666595459,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 31.25,
182
- "grad_norm": 0.041931431740522385,
183
- "learning_rate": 0.006930817610062893,
184
- "loss": 0.5302073001861572,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 32.5,
189
- "grad_norm": 0.07813303917646408,
190
- "learning_rate": 0.00680503144654088,
191
- "loss": 0.5294707775115967,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 33.75,
196
- "grad_norm": 0.03454748913645744,
197
- "learning_rate": 0.006679245283018867,
198
- "loss": 0.5287383079528809,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 35.0,
203
- "grad_norm": 0.03431857377290726,
204
- "learning_rate": 0.006553459119496855,
205
- "loss": 0.5282272815704345,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 36.25,
210
- "grad_norm": 0.08966688811779022,
211
- "learning_rate": 0.006427672955974842,
212
- "loss": 0.5277254581451416,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 37.5,
217
- "grad_norm": 0.052265942096710205,
218
- "learning_rate": 0.00630188679245283,
219
- "loss": 0.5272915840148926,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 38.75,
224
- "grad_norm": 0.0515151284635067,
225
- "learning_rate": 0.0061761006289308175,
226
- "loss": 0.5268842697143554,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 40.0,
231
- "grad_norm": 0.036997534334659576,
232
- "learning_rate": 0.006050314465408805,
233
- "loss": 0.5264564514160156,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 41.25,
238
- "grad_norm": 0.043620988726615906,
239
- "learning_rate": 0.0059245283018867926,
240
- "loss": 0.5261125564575195,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 42.5,
245
- "grad_norm": 0.027620961889624596,
246
- "learning_rate": 0.00579874213836478,
247
- "loss": 0.5258570194244385,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 43.75,
252
- "grad_norm": 0.05584390088915825,
253
- "learning_rate": 0.005672955974842768,
254
- "loss": 0.5256526470184326,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 45.0,
259
- "grad_norm": 0.04482174292206764,
260
- "learning_rate": 0.005547169811320755,
261
- "loss": 0.5253445148468018,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 46.25,
266
- "grad_norm": 0.026756955310702324,
267
- "learning_rate": 0.005421383647798742,
268
- "loss": 0.5251789093017578,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 47.5,
273
- "grad_norm": 0.044440966099500656,
274
- "learning_rate": 0.00529559748427673,
275
- "loss": 0.5248369216918946,
276
- "step": 380
277
- },
278
- {
279
- "epoch": 48.75,
280
- "grad_norm": 0.018594520166516304,
281
- "learning_rate": 0.005169811320754717,
282
- "loss": 0.5247899055480957,
283
- "step": 390
284
- },
285
- {
286
- "epoch": 50.0,
287
- "grad_norm": 0.08508243411779404,
288
- "learning_rate": 0.005044025157232705,
289
- "loss": 0.5245010852813721,
290
- "step": 400
291
- },
292
- {
293
- "epoch": 51.25,
294
- "grad_norm": 0.0452226921916008,
295
- "learning_rate": 0.004918238993710692,
296
- "loss": 0.5243758201599121,
297
- "step": 410
298
- },
299
- {
300
- "epoch": 52.5,
301
- "grad_norm": 0.01639331877231598,
302
- "learning_rate": 0.004792452830188679,
303
- "loss": 0.5242112636566162,
304
- "step": 420
305
- },
306
- {
307
- "epoch": 53.75,
308
- "grad_norm": 0.04810582846403122,
309
- "learning_rate": 0.004666666666666667,
310
- "loss": 0.523947811126709,
311
- "step": 430
312
- },
313
- {
314
- "epoch": 55.0,
315
- "grad_norm": 0.06734395027160645,
316
- "learning_rate": 0.004540880503144654,
317
- "loss": 0.5240691661834717,
318
- "step": 440
319
- },
320
- {
321
- "epoch": 56.25,
322
- "grad_norm": 0.08076826483011246,
323
- "learning_rate": 0.004415094339622642,
324
- "loss": 0.5238540649414063,
325
- "step": 450
326
- },
327
- {
328
- "epoch": 57.5,
329
- "grad_norm": 0.04151872172951698,
330
- "learning_rate": 0.004289308176100629,
331
- "loss": 0.5237194061279297,
332
- "step": 460
333
- },
334
- {
335
- "epoch": 58.75,
336
- "grad_norm": 0.034729089587926865,
337
- "learning_rate": 0.004163522012578616,
338
- "loss": 0.5235513687133789,
339
- "step": 470
340
- },
341
- {
342
- "epoch": 60.0,
343
- "grad_norm": 0.1251593828201294,
344
- "learning_rate": 0.004037735849056604,
345
- "loss": 0.5235977172851562,
346
- "step": 480
347
- },
348
- {
349
- "epoch": 61.25,
350
- "grad_norm": 0.0236071664839983,
351
- "learning_rate": 0.003911949685534591,
352
- "loss": 0.5233771800994873,
353
- "step": 490
354
- },
355
- {
356
- "epoch": 62.5,
357
- "grad_norm": 0.03458293899893761,
358
- "learning_rate": 0.003786163522012579,
359
- "loss": 0.5233054161071777,
360
- "step": 500
361
- }
362
- ],
363
- "logging_steps": 10,
364
- "max_steps": 800,
365
- "num_input_tokens_seen": 0,
366
- "num_train_epochs": 100,
367
- "save_steps": 50,
368
- "stateful_callbacks": {
369
- "TrainerControl": {
370
- "args": {
371
- "should_epoch_stop": false,
372
- "should_evaluate": false,
373
- "should_log": false,
374
- "should_save": true,
375
- "should_training_stop": false
376
- },
377
- "attributes": {}
378
- }
379
- },
380
- "total_flos": 27005184.0,
381
- "train_batch_size": 128,
382
- "trial_name": null,
383
- "trial_params": null
384
- }