kiddothe2b commited on
Commit
834e22d
1 Parent(s): 32e34dc

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +13 -0
  2. eval_results.json +9 -0
  3. train_results.json +7 -0
  4. trainer_state.json +418 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.6366230517315061,
4
+ "eval_loss": 1.943715214729309,
5
+ "eval_runtime": 50549.5801,
6
+ "eval_samples_per_second": 6.486,
7
+ "eval_steps_per_second": 0.811,
8
+ "perplexity": 6.98465230946612,
9
+ "train_loss": 2.156327223777771,
10
+ "train_runtime": 107381.8296,
11
+ "train_samples_per_second": 3.814,
12
+ "train_steps_per_second": 0.06
13
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.6366230517315061,
4
+ "eval_loss": 1.943715214729309,
5
+ "eval_runtime": 50549.5801,
6
+ "eval_samples_per_second": 6.486,
7
+ "eval_steps_per_second": 0.811,
8
+ "perplexity": 6.98465230946612
9
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 2.156327223777771,
4
+ "train_runtime": 107381.8296,
5
+ "train_samples_per_second": 3.814,
6
+ "train_steps_per_second": 0.06
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 6400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1.5625e-06,
13
+ "loss": 2.5618,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 3.125e-06,
19
+ "loss": 2.4474,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 4.6875000000000004e-06,
25
+ "loss": 2.3184,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 6.25e-06,
31
+ "loss": 2.2942,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 7.8125e-06,
37
+ "loss": 2.26,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 9.375000000000001e-06,
43
+ "loss": 2.2509,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "learning_rate": 1.09375e-05,
49
+ "loss": 2.2584,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 1.25e-05,
55
+ "loss": 2.2217,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.14,
60
+ "learning_rate": 1.4062500000000001e-05,
61
+ "loss": 2.2244,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.16,
66
+ "learning_rate": 1.5625e-05,
67
+ "loss": 2.181,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.17,
72
+ "learning_rate": 1.71875e-05,
73
+ "loss": 2.1925,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.19,
78
+ "learning_rate": 1.8750000000000002e-05,
79
+ "loss": 2.1933,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.2,
84
+ "learning_rate": 2.0312500000000002e-05,
85
+ "loss": 2.1838,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.22,
90
+ "learning_rate": 2.1875e-05,
91
+ "loss": 2.1899,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.23,
96
+ "learning_rate": 2.34375e-05,
97
+ "loss": 2.1938,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.25,
102
+ "learning_rate": 2.5e-05,
103
+ "loss": 2.1664,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.27,
108
+ "learning_rate": 2.6562500000000002e-05,
109
+ "loss": 2.1748,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.28,
114
+ "learning_rate": 2.8125000000000003e-05,
115
+ "loss": 2.184,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.3,
120
+ "learning_rate": 2.96875e-05,
121
+ "loss": 2.1452,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.31,
126
+ "learning_rate": 3.125e-05,
127
+ "loss": 2.155,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.33,
132
+ "learning_rate": 3.2812500000000005e-05,
133
+ "loss": 2.1591,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.34,
138
+ "learning_rate": 3.4375e-05,
139
+ "loss": 2.143,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.36,
144
+ "learning_rate": 3.59375e-05,
145
+ "loss": 2.1634,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.38,
150
+ "learning_rate": 3.7500000000000003e-05,
151
+ "loss": 2.1416,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.39,
156
+ "learning_rate": 3.90625e-05,
157
+ "loss": 2.1293,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.41,
162
+ "learning_rate": 4.0625000000000005e-05,
163
+ "loss": 2.1376,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.42,
168
+ "learning_rate": 4.21875e-05,
169
+ "loss": 2.1396,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.44,
174
+ "learning_rate": 4.375e-05,
175
+ "loss": 2.1207,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.45,
180
+ "learning_rate": 4.5312500000000004e-05,
181
+ "loss": 2.123,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.47,
186
+ "learning_rate": 4.6875e-05,
187
+ "loss": 2.1427,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.48,
192
+ "learning_rate": 4.8437500000000005e-05,
193
+ "loss": 2.1515,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.5,
198
+ "learning_rate": 5e-05,
199
+ "loss": 2.1454,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.52,
204
+ "learning_rate": 5.15625e-05,
205
+ "loss": 2.1264,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.53,
210
+ "learning_rate": 5.3125000000000004e-05,
211
+ "loss": 2.1426,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.55,
216
+ "learning_rate": 5.46875e-05,
217
+ "loss": 2.105,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.56,
222
+ "learning_rate": 5.6250000000000005e-05,
223
+ "loss": 2.1243,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.58,
228
+ "learning_rate": 5.78125e-05,
229
+ "loss": 2.1041,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.59,
234
+ "learning_rate": 5.9375e-05,
235
+ "loss": 2.124,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.61,
240
+ "learning_rate": 6.0937500000000004e-05,
241
+ "loss": 2.1276,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.62,
246
+ "learning_rate": 6.25e-05,
247
+ "loss": 2.1318,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.64,
252
+ "learning_rate": 6.40625e-05,
253
+ "loss": 2.1337,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.66,
258
+ "learning_rate": 6.562500000000001e-05,
259
+ "loss": 2.1159,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.67,
264
+ "learning_rate": 6.71875e-05,
265
+ "loss": 2.1183,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.69,
270
+ "learning_rate": 6.875e-05,
271
+ "loss": 2.1199,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.7,
276
+ "learning_rate": 7.031250000000001e-05,
277
+ "loss": 2.1157,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.72,
282
+ "learning_rate": 7.1875e-05,
283
+ "loss": 2.09,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.73,
288
+ "learning_rate": 7.34375e-05,
289
+ "loss": 2.1108,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.75,
294
+ "learning_rate": 7.500000000000001e-05,
295
+ "loss": 2.0931,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.77,
300
+ "learning_rate": 7.65625e-05,
301
+ "loss": 2.1224,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.78,
306
+ "learning_rate": 7.8125e-05,
307
+ "loss": 2.0918,
308
+ "step": 5000
309
+ },
310
+ {
311
+ "epoch": 0.8,
312
+ "learning_rate": 7.96875e-05,
313
+ "loss": 2.1121,
314
+ "step": 5100
315
+ },
316
+ {
317
+ "epoch": 0.81,
318
+ "learning_rate": 8.125000000000001e-05,
319
+ "loss": 2.1009,
320
+ "step": 5200
321
+ },
322
+ {
323
+ "epoch": 0.83,
324
+ "learning_rate": 8.28125e-05,
325
+ "loss": 2.1047,
326
+ "step": 5300
327
+ },
328
+ {
329
+ "epoch": 0.84,
330
+ "learning_rate": 8.4375e-05,
331
+ "loss": 2.0922,
332
+ "step": 5400
333
+ },
334
+ {
335
+ "epoch": 0.86,
336
+ "learning_rate": 8.593750000000001e-05,
337
+ "loss": 2.1091,
338
+ "step": 5500
339
+ },
340
+ {
341
+ "epoch": 0.88,
342
+ "learning_rate": 8.75e-05,
343
+ "loss": 2.1061,
344
+ "step": 5600
345
+ },
346
+ {
347
+ "epoch": 0.89,
348
+ "learning_rate": 8.90625e-05,
349
+ "loss": 2.1206,
350
+ "step": 5700
351
+ },
352
+ {
353
+ "epoch": 0.91,
354
+ "learning_rate": 9.062500000000001e-05,
355
+ "loss": 2.0945,
356
+ "step": 5800
357
+ },
358
+ {
359
+ "epoch": 0.92,
360
+ "learning_rate": 9.21875e-05,
361
+ "loss": 2.0924,
362
+ "step": 5900
363
+ },
364
+ {
365
+ "epoch": 0.94,
366
+ "learning_rate": 9.375e-05,
367
+ "loss": 2.1014,
368
+ "step": 6000
369
+ },
370
+ {
371
+ "epoch": 0.95,
372
+ "learning_rate": 9.53125e-05,
373
+ "loss": 2.0984,
374
+ "step": 6100
375
+ },
376
+ {
377
+ "epoch": 0.97,
378
+ "learning_rate": 9.687500000000001e-05,
379
+ "loss": 2.0709,
380
+ "step": 6200
381
+ },
382
+ {
383
+ "epoch": 0.98,
384
+ "learning_rate": 9.84375e-05,
385
+ "loss": 2.1051,
386
+ "step": 6300
387
+ },
388
+ {
389
+ "epoch": 1.0,
390
+ "learning_rate": 0.0001,
391
+ "loss": 2.1052,
392
+ "step": 6400
393
+ },
394
+ {
395
+ "epoch": 1.0,
396
+ "eval_accuracy": 0.6366426454087312,
397
+ "eval_loss": 1.9433484077453613,
398
+ "eval_runtime": 50910.5556,
399
+ "eval_samples_per_second": 6.44,
400
+ "eval_steps_per_second": 0.805,
401
+ "step": 6400
402
+ },
403
+ {
404
+ "epoch": 1.0,
405
+ "step": 6400,
406
+ "total_flos": 2.707934115004416e+17,
407
+ "train_loss": 2.156327223777771,
408
+ "train_runtime": 107381.8296,
409
+ "train_samples_per_second": 3.814,
410
+ "train_steps_per_second": 0.06
411
+ }
412
+ ],
413
+ "max_steps": 6400,
414
+ "num_train_epochs": 9223372036854775807,
415
+ "total_flos": 2.707934115004416e+17,
416
+ "trial_name": null,
417
+ "trial_params": null
418
+ }