AlexCuadron commited on
Commit
b4f8652
·
verified ·
1 Parent(s): bb76b54

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +266 -0
trainer_state.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.606060606060606,
5
+ "eval_steps": 500,
6
+ "global_step": 32,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12121212121212122,
13
+ "grad_norm": 2.50050950050354,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 0.8407,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.24242424242424243,
20
+ "grad_norm": 2.2383944988250732,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7878,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.36363636363636365,
27
+ "grad_norm": 2.1805531978607178,
28
+ "learning_rate": 7.500000000000001e-06,
29
+ "loss": 0.8026,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.48484848484848486,
34
+ "grad_norm": 2.0964150428771973,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.8133,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.6060606060606061,
41
+ "grad_norm": 1.5487000942230225,
42
+ "learning_rate": 9.968561049466214e-06,
43
+ "loss": 0.7608,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.7272727272727273,
48
+ "grad_norm": 1.7998461723327637,
49
+ "learning_rate": 9.874639560909118e-06,
50
+ "loss": 0.7272,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.8484848484848485,
55
+ "grad_norm": 1.9523899555206299,
56
+ "learning_rate": 9.719416651541839e-06,
57
+ "loss": 0.6923,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.9696969696969697,
62
+ "grad_norm": 4.303847312927246,
63
+ "learning_rate": 9.504844339512096e-06,
64
+ "loss": 0.6853,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.0,
69
+ "grad_norm": 4.303847312927246,
70
+ "learning_rate": 9.233620996141421e-06,
71
+ "loss": 0.6532,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.121212121212121,
76
+ "grad_norm": 2.6484241485595703,
77
+ "learning_rate": 8.90915741234015e-06,
78
+ "loss": 0.6334,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.2424242424242424,
83
+ "grad_norm": 1.0852004289627075,
84
+ "learning_rate": 8.535533905932739e-06,
85
+ "loss": 0.6171,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.3636363636363638,
90
+ "grad_norm": 87.41819763183594,
91
+ "learning_rate": 8.117449009293668e-06,
92
+ "loss": 0.5768,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.4848484848484849,
97
+ "grad_norm": 1.8918662071228027,
98
+ "learning_rate": 7.660160382576683e-06,
99
+ "loss": 0.5852,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.606060606060606,
104
+ "grad_norm": 1.3301656246185303,
105
+ "learning_rate": 7.169418695587791e-06,
106
+ "loss": 0.5752,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.7272727272727273,
111
+ "grad_norm": 0.9969548583030701,
112
+ "learning_rate": 6.651395309775837e-06,
113
+ "loss": 0.5949,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.8484848484848486,
118
+ "grad_norm": 0.9531848430633545,
119
+ "learning_rate": 6.112604669781572e-06,
120
+ "loss": 0.5568,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.9696969696969697,
125
+ "grad_norm": 0.8378441333770752,
126
+ "learning_rate": 5.559822380516539e-06,
127
+ "loss": 0.5506,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 2.0,
132
+ "grad_norm": 0.8378441333770752,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.5339,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 2.121212121212121,
139
+ "grad_norm": 1.51701021194458,
140
+ "learning_rate": 4.4401776194834615e-06,
141
+ "loss": 0.5415,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.242424242424242,
146
+ "grad_norm": 0.8446238040924072,
147
+ "learning_rate": 3.887395330218429e-06,
148
+ "loss": 0.5077,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.3636363636363638,
153
+ "grad_norm": 0.6361896395683289,
154
+ "learning_rate": 3.3486046902241663e-06,
155
+ "loss": 0.5249,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.484848484848485,
160
+ "grad_norm": 0.5378800630569458,
161
+ "learning_rate": 2.83058130441221e-06,
162
+ "loss": 0.5052,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.606060606060606,
167
+ "grad_norm": 0.49560996890068054,
168
+ "learning_rate": 2.339839617423318e-06,
169
+ "loss": 0.5087,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.7272727272727275,
174
+ "grad_norm": 0.5335824489593506,
175
+ "learning_rate": 1.8825509907063328e-06,
176
+ "loss": 0.4993,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.8484848484848486,
181
+ "grad_norm": 0.4428861141204834,
182
+ "learning_rate": 1.4644660940672628e-06,
183
+ "loss": 0.4946,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.9696969696969697,
188
+ "grad_norm": 0.47002682089805603,
189
+ "learning_rate": 1.0908425876598512e-06,
190
+ "loss": 0.4855,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 3.0,
195
+ "grad_norm": 0.47002682089805603,
196
+ "learning_rate": 7.663790038585794e-07,
197
+ "loss": 0.5004,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 3.121212121212121,
202
+ "grad_norm": 0.7940795421600342,
203
+ "learning_rate": 4.951556604879049e-07,
204
+ "loss": 0.4744,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 3.242424242424242,
209
+ "grad_norm": 0.4210236966609955,
210
+ "learning_rate": 2.8058334845816214e-07,
211
+ "loss": 0.4723,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 3.3636363636363638,
216
+ "grad_norm": 0.41588640213012695,
217
+ "learning_rate": 1.253604390908819e-07,
218
+ "loss": 0.5029,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 3.484848484848485,
223
+ "grad_norm": 0.42177480459213257,
224
+ "learning_rate": 3.143895053378698e-08,
225
+ "loss": 0.4881,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 3.606060606060606,
230
+ "grad_norm": 0.43024787306785583,
231
+ "learning_rate": 0.0,
232
+ "loss": 0.5004,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 3.606060606060606,
237
+ "step": 32,
238
+ "total_flos": 80439221420032.0,
239
+ "train_loss": 0.5935216061770916,
240
+ "train_runtime": 4011.9078,
241
+ "train_samples_per_second": 0.518,
242
+ "train_steps_per_second": 0.008
243
+ }
244
+ ],
245
+ "logging_steps": 1,
246
+ "max_steps": 32,
247
+ "num_input_tokens_seen": 0,
248
+ "num_train_epochs": 4,
249
+ "save_steps": 8,
250
+ "stateful_callbacks": {
251
+ "TrainerControl": {
252
+ "args": {
253
+ "should_epoch_stop": false,
254
+ "should_evaluate": false,
255
+ "should_log": false,
256
+ "should_save": true,
257
+ "should_training_stop": true
258
+ },
259
+ "attributes": {}
260
+ }
261
+ },
262
+ "total_flos": 80439221420032.0,
263
+ "train_batch_size": 2,
264
+ "trial_name": null,
265
+ "trial_params": null
266
+ }