ardaspear commited on
Commit
d6537f6
1 Parent(s): 61bea33

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b35e611a6d72a194af6ce69859542d2578ccc2ad5b8435f26c41a31fe9fcd54
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a186d72f8ba849efdafd46fcdd73a4c0f7481e522662212c1a69f68598c02b
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a4873462922d980d971f01e760503b69cb35034f956dad90d11f6778b2ccb0a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc13bb46d583a5eaaec7068ad1c85caa2ba47d474c5c6db37db75c6711e4b02
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.013358070500927645,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 13.362,
193
  "eval_steps_per_second": 1.672,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 6.519492429899366e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.014842300556586271,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 13.362,
193
  "eval_steps_per_second": 1.672,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.01424860853432282,
198
+ "grad_norm": NaN,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.0,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.014842300556586271,
205
+ "eval_loss": NaN,
206
+ "eval_runtime": 424.649,
207
+ "eval_samples_per_second": 13.362,
208
+ "eval_steps_per_second": 1.672,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 7.351060341876326e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null