lesso04 commited on
Commit
ee5159b
·
verified ·
1 Parent(s): 7fca018

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc20014b0620344b3d5b5258a4ee83d13b6326a3a1b9e2d9785a9fd4e1f62fb0
3
  size 18763860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc71546abbd186e6d73b370ed36acfc5d4c7541f7c58ef93e630614c82cfd517
3
  size 18763860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:049ef9d402621f8d67191fa7981b9705ec1748fcb4431765ca3a28fee3882315
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0649fc9945b60f12367a89b832d1d82096172aeb538f570741694839cb42a00
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.009376465072667605,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -101,6 +101,92 @@
101
  "eval_samples_per_second": 10.577,
102
  "eval_steps_per_second": 5.288,
103
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
  }
105
  ],
106
  "logging_steps": 1,
@@ -115,7 +201,7 @@
115
  "early_stopping_threshold": 0.0
116
  },
117
  "attributes": {
118
- "early_stopping_patience_counter": 0
119
  }
120
  },
121
  "TrainerControl": {
@@ -124,12 +210,12 @@
124
  "should_evaluate": false,
125
  "should_log": false,
126
  "should_save": true,
127
- "should_training_stop": false
128
  },
129
  "attributes": {}
130
  }
131
  },
132
- "total_flos": 437878643490816.0,
133
  "train_batch_size": 2,
134
  "trial_name": null,
135
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
+ "epoch": 0.01875293014533521,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
101
  "eval_samples_per_second": 10.577,
102
  "eval_steps_per_second": 5.288,
103
  "step": 10
104
+ },
105
+ {
106
+ "epoch": 0.010314111579934365,
107
+ "grad_norm": NaN,
108
+ "learning_rate": 0.00019781476007338058,
109
+ "loss": 0.0,
110
+ "step": 11
111
+ },
112
+ {
113
+ "epoch": 0.011251758087201125,
114
+ "grad_norm": NaN,
115
+ "learning_rate": 0.0001913545457642601,
116
+ "loss": 0.0,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.012189404594467886,
121
+ "grad_norm": NaN,
122
+ "learning_rate": 0.00018090169943749476,
123
+ "loss": 0.0,
124
+ "step": 13
125
+ },
126
+ {
127
+ "epoch": 0.013127051101734646,
128
+ "grad_norm": NaN,
129
+ "learning_rate": 0.00016691306063588583,
130
+ "loss": 0.0,
131
+ "step": 14
132
+ },
133
+ {
134
+ "epoch": 0.014064697609001406,
135
+ "grad_norm": NaN,
136
+ "learning_rate": 0.00015000000000000001,
137
+ "loss": 0.0,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.014064697609001406,
142
+ "eval_loss": NaN,
143
+ "eval_runtime": 42.9987,
144
+ "eval_samples_per_second": 10.465,
145
+ "eval_steps_per_second": 5.233,
146
+ "step": 15
147
+ },
148
+ {
149
+ "epoch": 0.015002344116268168,
150
+ "grad_norm": NaN,
151
+ "learning_rate": 0.00013090169943749476,
152
+ "loss": 0.0,
153
+ "step": 16
154
+ },
155
+ {
156
+ "epoch": 0.015939990623534926,
157
+ "grad_norm": NaN,
158
+ "learning_rate": 0.00011045284632676536,
159
+ "loss": 0.0,
160
+ "step": 17
161
+ },
162
+ {
163
+ "epoch": 0.016877637130801686,
164
+ "grad_norm": NaN,
165
+ "learning_rate": 8.954715367323468e-05,
166
+ "loss": 0.0,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.017815283638068447,
171
+ "grad_norm": NaN,
172
+ "learning_rate": 6.909830056250527e-05,
173
+ "loss": 0.0,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.01875293014533521,
178
+ "grad_norm": NaN,
179
+ "learning_rate": 5.000000000000002e-05,
180
+ "loss": 0.0,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.01875293014533521,
185
+ "eval_loss": NaN,
186
+ "eval_runtime": 44.4778,
187
+ "eval_samples_per_second": 10.117,
188
+ "eval_steps_per_second": 5.059,
189
+ "step": 20
190
  }
191
  ],
192
  "logging_steps": 1,
 
201
  "early_stopping_threshold": 0.0
202
  },
203
  "attributes": {
204
+ "early_stopping_patience_counter": 2
205
  }
206
  },
207
  "TrainerControl": {
 
210
  "should_evaluate": false,
211
  "should_log": false,
212
  "should_save": true,
213
+ "should_training_stop": true
214
  },
215
  "attributes": {}
216
  }
217
  },
218
+ "total_flos": 875757286981632.0,
219
  "train_batch_size": 2,
220
  "trial_name": null,
221
  "trial_params": null