mapama247 commited on
Commit
310282e
1 Parent(s): 8082383

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +283 -0
trainer_state.json ADDED
@@ -0,0 +1,283 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3609592914581299,
3
+ "best_model_checkpoint": "./output/20_epochs_sep/checkpoint-780",
4
+ "epoch": 20.0,
5
+ "global_step": 7800,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.166666666666667e-05,
13
+ "loss": 5.0549,
14
+ "step": 390
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.402883529663086,
19
+ "eval_runtime": 121.8218,
20
+ "eval_samples_per_second": 8.57,
21
+ "step": 390
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "learning_rate": 4.787234042553192e-05,
26
+ "loss": 1.2729,
27
+ "step": 780
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_loss": 1.3609592914581299,
32
+ "eval_runtime": 121.6763,
33
+ "eval_samples_per_second": 8.58,
34
+ "step": 780
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "learning_rate": 4.5212765957446815e-05,
39
+ "loss": 0.8899,
40
+ "step": 1170
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "eval_loss": 1.4757730960845947,
45
+ "eval_runtime": 121.8679,
46
+ "eval_samples_per_second": 8.567,
47
+ "step": 1170
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "learning_rate": 4.2553191489361704e-05,
52
+ "loss": 0.4533,
53
+ "step": 1560
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_loss": 1.7082480192184448,
58
+ "eval_runtime": 121.9437,
59
+ "eval_samples_per_second": 8.561,
60
+ "step": 1560
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "learning_rate": 3.9893617021276594e-05,
65
+ "loss": 0.182,
66
+ "step": 1950
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_loss": 1.9131618738174438,
71
+ "eval_runtime": 121.9168,
72
+ "eval_samples_per_second": 8.563,
73
+ "step": 1950
74
+ },
75
+ {
76
+ "epoch": 6.0,
77
+ "learning_rate": 3.723404255319149e-05,
78
+ "loss": 0.0838,
79
+ "step": 2340
80
+ },
81
+ {
82
+ "epoch": 6.0,
83
+ "eval_loss": 2.0302553176879883,
84
+ "eval_runtime": 121.9432,
85
+ "eval_samples_per_second": 8.561,
86
+ "step": 2340
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "learning_rate": 3.4574468085106386e-05,
91
+ "loss": 0.054,
92
+ "step": 2730
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "eval_loss": 2.1023058891296387,
97
+ "eval_runtime": 121.8944,
98
+ "eval_samples_per_second": 8.565,
99
+ "step": 2730
100
+ },
101
+ {
102
+ "epoch": 8.0,
103
+ "learning_rate": 3.191489361702128e-05,
104
+ "loss": 0.0396,
105
+ "step": 3120
106
+ },
107
+ {
108
+ "epoch": 8.0,
109
+ "eval_loss": 2.1586802005767822,
110
+ "eval_runtime": 121.8358,
111
+ "eval_samples_per_second": 8.569,
112
+ "step": 3120
113
+ },
114
+ {
115
+ "epoch": 9.0,
116
+ "learning_rate": 2.925531914893617e-05,
117
+ "loss": 0.0317,
118
+ "step": 3510
119
+ },
120
+ {
121
+ "epoch": 9.0,
122
+ "eval_loss": 2.2018632888793945,
123
+ "eval_runtime": 121.8177,
124
+ "eval_samples_per_second": 8.57,
125
+ "step": 3510
126
+ },
127
+ {
128
+ "epoch": 10.0,
129
+ "learning_rate": 2.6595744680851064e-05,
130
+ "loss": 0.0264,
131
+ "step": 3900
132
+ },
133
+ {
134
+ "epoch": 10.0,
135
+ "eval_loss": 2.2312045097351074,
136
+ "eval_runtime": 121.887,
137
+ "eval_samples_per_second": 8.565,
138
+ "step": 3900
139
+ },
140
+ {
141
+ "epoch": 11.0,
142
+ "learning_rate": 2.393617021276596e-05,
143
+ "loss": 0.0225,
144
+ "step": 4290
145
+ },
146
+ {
147
+ "epoch": 11.0,
148
+ "eval_loss": 2.2828288078308105,
149
+ "eval_runtime": 121.91,
150
+ "eval_samples_per_second": 8.564,
151
+ "step": 4290
152
+ },
153
+ {
154
+ "epoch": 12.0,
155
+ "learning_rate": 2.1276595744680852e-05,
156
+ "loss": 0.0209,
157
+ "step": 4680
158
+ },
159
+ {
160
+ "epoch": 12.0,
161
+ "eval_loss": 2.3354954719543457,
162
+ "eval_runtime": 121.9104,
163
+ "eval_samples_per_second": 8.564,
164
+ "step": 4680
165
+ },
166
+ {
167
+ "epoch": 13.0,
168
+ "learning_rate": 1.8617021276595745e-05,
169
+ "loss": 0.0203,
170
+ "step": 5070
171
+ },
172
+ {
173
+ "epoch": 13.0,
174
+ "eval_loss": 2.3210549354553223,
175
+ "eval_runtime": 121.9222,
176
+ "eval_samples_per_second": 8.563,
177
+ "step": 5070
178
+ },
179
+ {
180
+ "epoch": 14.0,
181
+ "learning_rate": 1.595744680851064e-05,
182
+ "loss": 0.0195,
183
+ "step": 5460
184
+ },
185
+ {
186
+ "epoch": 14.0,
187
+ "eval_loss": 2.3695647716522217,
188
+ "eval_runtime": 121.8891,
189
+ "eval_samples_per_second": 8.565,
190
+ "step": 5460
191
+ },
192
+ {
193
+ "epoch": 15.0,
194
+ "learning_rate": 1.3297872340425532e-05,
195
+ "loss": 0.0189,
196
+ "step": 5850
197
+ },
198
+ {
199
+ "epoch": 15.0,
200
+ "eval_loss": 2.402658224105835,
201
+ "eval_runtime": 121.8955,
202
+ "eval_samples_per_second": 8.565,
203
+ "step": 5850
204
+ },
205
+ {
206
+ "epoch": 16.0,
207
+ "learning_rate": 1.0638297872340426e-05,
208
+ "loss": 0.0184,
209
+ "step": 6240
210
+ },
211
+ {
212
+ "epoch": 16.0,
213
+ "eval_loss": 2.4124085903167725,
214
+ "eval_runtime": 121.8966,
215
+ "eval_samples_per_second": 8.565,
216
+ "step": 6240
217
+ },
218
+ {
219
+ "epoch": 17.0,
220
+ "learning_rate": 7.97872340425532e-06,
221
+ "loss": 0.0181,
222
+ "step": 6630
223
+ },
224
+ {
225
+ "epoch": 17.0,
226
+ "eval_loss": 2.4452691078186035,
227
+ "eval_runtime": 121.8236,
228
+ "eval_samples_per_second": 8.57,
229
+ "step": 6630
230
+ },
231
+ {
232
+ "epoch": 18.0,
233
+ "learning_rate": 5.319148936170213e-06,
234
+ "loss": 0.0176,
235
+ "step": 7020
236
+ },
237
+ {
238
+ "epoch": 18.0,
239
+ "eval_loss": 2.449826717376709,
240
+ "eval_runtime": 121.8997,
241
+ "eval_samples_per_second": 8.564,
242
+ "step": 7020
243
+ },
244
+ {
245
+ "epoch": 19.0,
246
+ "learning_rate": 2.6595744680851065e-06,
247
+ "loss": 0.0172,
248
+ "step": 7410
249
+ },
250
+ {
251
+ "epoch": 19.0,
252
+ "eval_loss": 2.4811935424804688,
253
+ "eval_runtime": 121.9376,
254
+ "eval_samples_per_second": 8.562,
255
+ "step": 7410
256
+ },
257
+ {
258
+ "epoch": 20.0,
259
+ "learning_rate": 0.0,
260
+ "loss": 0.0167,
261
+ "step": 7800
262
+ },
263
+ {
264
+ "epoch": 20.0,
265
+ "eval_loss": 2.5037059783935547,
266
+ "eval_runtime": 121.9361,
267
+ "eval_samples_per_second": 8.562,
268
+ "step": 7800
269
+ },
270
+ {
271
+ "epoch": 20.0,
272
+ "step": 7800,
273
+ "total_flos": 0,
274
+ "train_runtime": 22284.2589,
275
+ "train_samples_per_second": 0.35
276
+ }
277
+ ],
278
+ "max_steps": 7800,
279
+ "num_train_epochs": 20,
280
+ "total_flos": 0,
281
+ "trial_name": null,
282
+ "trial_params": null
283
+ }