brildev7 commited on
Commit
1a97193
·
verified ·
1 Parent(s): 91b00cc

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -357
trainer_state.json DELETED
@@ -1,357 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 43.146067415730336,
5
- "eval_steps": 500,
6
- "global_step": 960,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.9,
13
- "grad_norm": 7.640738010406494,
14
- "learning_rate": 0.0002,
15
- "loss": 4.2661,
16
- "step": 20
17
- },
18
- {
19
- "epoch": 1.8,
20
- "grad_norm": 2.9313442707061768,
21
- "learning_rate": 0.0002,
22
- "loss": 2.306,
23
- "step": 40
24
- },
25
- {
26
- "epoch": 2.7,
27
- "grad_norm": 0.9562789797782898,
28
- "learning_rate": 0.0002,
29
- "loss": 2.0093,
30
- "step": 60
31
- },
32
- {
33
- "epoch": 3.6,
34
- "grad_norm": 1.4072426557540894,
35
- "learning_rate": 0.0002,
36
- "loss": 1.8391,
37
- "step": 80
38
- },
39
- {
40
- "epoch": 4.49,
41
- "grad_norm": 1.1522574424743652,
42
- "learning_rate": 0.0002,
43
- "loss": 1.7152,
44
- "step": 100
45
- },
46
- {
47
- "epoch": 5.39,
48
- "grad_norm": 0.9669118523597717,
49
- "learning_rate": 0.0002,
50
- "loss": 1.5656,
51
- "step": 120
52
- },
53
- {
54
- "epoch": 6.29,
55
- "grad_norm": 1.1254830360412598,
56
- "learning_rate": 0.0002,
57
- "loss": 1.4272,
58
- "step": 140
59
- },
60
- {
61
- "epoch": 7.19,
62
- "grad_norm": 1.4298350811004639,
63
- "learning_rate": 0.0002,
64
- "loss": 1.2586,
65
- "step": 160
66
- },
67
- {
68
- "epoch": 8.09,
69
- "grad_norm": 1.3048124313354492,
70
- "learning_rate": 0.0002,
71
- "loss": 1.1003,
72
- "step": 180
73
- },
74
- {
75
- "epoch": 8.99,
76
- "grad_norm": 1.5784626007080078,
77
- "learning_rate": 0.0002,
78
- "loss": 0.941,
79
- "step": 200
80
- },
81
- {
82
- "epoch": 9.89,
83
- "grad_norm": 1.6184762716293335,
84
- "learning_rate": 0.0002,
85
- "loss": 0.7854,
86
- "step": 220
87
- },
88
- {
89
- "epoch": 10.79,
90
- "grad_norm": 2.039607048034668,
91
- "learning_rate": 0.0002,
92
- "loss": 0.6663,
93
- "step": 240
94
- },
95
- {
96
- "epoch": 11.69,
97
- "grad_norm": 1.9069631099700928,
98
- "learning_rate": 0.0002,
99
- "loss": 0.5598,
100
- "step": 260
101
- },
102
- {
103
- "epoch": 12.58,
104
- "grad_norm": 3.269792079925537,
105
- "learning_rate": 0.0002,
106
- "loss": 0.4746,
107
- "step": 280
108
- },
109
- {
110
- "epoch": 13.48,
111
- "grad_norm": 1.695237159729004,
112
- "learning_rate": 0.0002,
113
- "loss": 0.3884,
114
- "step": 300
115
- },
116
- {
117
- "epoch": 14.38,
118
- "grad_norm": 1.7961617708206177,
119
- "learning_rate": 0.0002,
120
- "loss": 0.3197,
121
- "step": 320
122
- },
123
- {
124
- "epoch": 15.28,
125
- "grad_norm": 1.6906554698944092,
126
- "learning_rate": 0.0002,
127
- "loss": 0.2876,
128
- "step": 340
129
- },
130
- {
131
- "epoch": 16.18,
132
- "grad_norm": 1.5338362455368042,
133
- "learning_rate": 0.0002,
134
- "loss": 0.2476,
135
- "step": 360
136
- },
137
- {
138
- "epoch": 17.08,
139
- "grad_norm": 1.482823371887207,
140
- "learning_rate": 0.0002,
141
- "loss": 0.2152,
142
- "step": 380
143
- },
144
- {
145
- "epoch": 17.98,
146
- "grad_norm": 1.6050206422805786,
147
- "learning_rate": 0.0002,
148
- "loss": 0.1864,
149
- "step": 400
150
- },
151
- {
152
- "epoch": 18.88,
153
- "grad_norm": 1.7870419025421143,
154
- "learning_rate": 0.0002,
155
- "loss": 0.1527,
156
- "step": 420
157
- },
158
- {
159
- "epoch": 19.78,
160
- "grad_norm": 1.6181118488311768,
161
- "learning_rate": 0.0002,
162
- "loss": 0.1387,
163
- "step": 440
164
- },
165
- {
166
- "epoch": 20.67,
167
- "grad_norm": 1.545577049255371,
168
- "learning_rate": 0.0002,
169
- "loss": 0.1291,
170
- "step": 460
171
- },
172
- {
173
- "epoch": 21.57,
174
- "grad_norm": 1.4766790866851807,
175
- "learning_rate": 0.0002,
176
- "loss": 0.1216,
177
- "step": 480
178
- },
179
- {
180
- "epoch": 22.47,
181
- "grad_norm": 1.2652430534362793,
182
- "learning_rate": 0.0002,
183
- "loss": 0.1125,
184
- "step": 500
185
- },
186
- {
187
- "epoch": 23.37,
188
- "grad_norm": 1.3792601823806763,
189
- "learning_rate": 0.0002,
190
- "loss": 0.1064,
191
- "step": 520
192
- },
193
- {
194
- "epoch": 24.27,
195
- "grad_norm": 1.1617250442504883,
196
- "learning_rate": 0.0002,
197
- "loss": 0.0965,
198
- "step": 540
199
- },
200
- {
201
- "epoch": 25.17,
202
- "grad_norm": 1.0318264961242676,
203
- "learning_rate": 0.0002,
204
- "loss": 0.0892,
205
- "step": 560
206
- },
207
- {
208
- "epoch": 26.07,
209
- "grad_norm": 1.0102779865264893,
210
- "learning_rate": 0.0002,
211
- "loss": 0.0866,
212
- "step": 580
213
- },
214
- {
215
- "epoch": 26.97,
216
- "grad_norm": 1.2883203029632568,
217
- "learning_rate": 0.0002,
218
- "loss": 0.0805,
219
- "step": 600
220
- },
221
- {
222
- "epoch": 27.87,
223
- "grad_norm": 1.1580032110214233,
224
- "learning_rate": 0.0002,
225
- "loss": 0.0748,
226
- "step": 620
227
- },
228
- {
229
- "epoch": 28.76,
230
- "grad_norm": 1.114597201347351,
231
- "learning_rate": 0.0002,
232
- "loss": 0.0745,
233
- "step": 640
234
- },
235
- {
236
- "epoch": 29.66,
237
- "grad_norm": 1.0546940565109253,
238
- "learning_rate": 0.0002,
239
- "loss": 0.0721,
240
- "step": 660
241
- },
242
- {
243
- "epoch": 30.56,
244
- "grad_norm": 1.0050326585769653,
245
- "learning_rate": 0.0002,
246
- "loss": 0.0697,
247
- "step": 680
248
- },
249
- {
250
- "epoch": 31.46,
251
- "grad_norm": 1.0160025358200073,
252
- "learning_rate": 0.0002,
253
- "loss": 0.0658,
254
- "step": 700
255
- },
256
- {
257
- "epoch": 32.36,
258
- "grad_norm": 0.9212460517883301,
259
- "learning_rate": 0.0002,
260
- "loss": 0.0643,
261
- "step": 720
262
- },
263
- {
264
- "epoch": 33.26,
265
- "grad_norm": 0.8616517186164856,
266
- "learning_rate": 0.0002,
267
- "loss": 0.0621,
268
- "step": 740
269
- },
270
- {
271
- "epoch": 34.16,
272
- "grad_norm": 0.8040679693222046,
273
- "learning_rate": 0.0002,
274
- "loss": 0.061,
275
- "step": 760
276
- },
277
- {
278
- "epoch": 35.06,
279
- "grad_norm": 0.7591003179550171,
280
- "learning_rate": 0.0002,
281
- "loss": 0.0589,
282
- "step": 780
283
- },
284
- {
285
- "epoch": 35.96,
286
- "grad_norm": 1.0100669860839844,
287
- "learning_rate": 0.0002,
288
- "loss": 0.055,
289
- "step": 800
290
- },
291
- {
292
- "epoch": 36.85,
293
- "grad_norm": 0.9912341237068176,
294
- "learning_rate": 0.0002,
295
- "loss": 0.0513,
296
- "step": 820
297
- },
298
- {
299
- "epoch": 37.75,
300
- "grad_norm": 0.9290223121643066,
301
- "learning_rate": 0.0002,
302
- "loss": 0.0515,
303
- "step": 840
304
- },
305
- {
306
- "epoch": 38.65,
307
- "grad_norm": 0.8802034854888916,
308
- "learning_rate": 0.0002,
309
- "loss": 0.0511,
310
- "step": 860
311
- },
312
- {
313
- "epoch": 39.55,
314
- "grad_norm": 0.8020614981651306,
315
- "learning_rate": 0.0002,
316
- "loss": 0.0506,
317
- "step": 880
318
- },
319
- {
320
- "epoch": 40.45,
321
- "grad_norm": 0.8280277848243713,
322
- "learning_rate": 0.0002,
323
- "loss": 0.0502,
324
- "step": 900
325
- },
326
- {
327
- "epoch": 41.35,
328
- "grad_norm": 0.7979443669319153,
329
- "learning_rate": 0.0002,
330
- "loss": 0.0496,
331
- "step": 920
332
- },
333
- {
334
- "epoch": 42.25,
335
- "grad_norm": 0.7503458857536316,
336
- "learning_rate": 0.0002,
337
- "loss": 0.0487,
338
- "step": 940
339
- },
340
- {
341
- "epoch": 43.15,
342
- "grad_norm": 0.7012200355529785,
343
- "learning_rate": 0.0002,
344
- "loss": 0.0469,
345
- "step": 960
346
- }
347
- ],
348
- "logging_steps": 20,
349
- "max_steps": 1000,
350
- "num_input_tokens_seen": 0,
351
- "num_train_epochs": 46,
352
- "save_steps": 20,
353
- "total_flos": 2.927218722298921e+18,
354
- "train_batch_size": 8,
355
- "trial_name": null,
356
- "trial_params": null
357
- }