mamung commited on
Commit
55fc57f
·
verified ·
1 Parent(s): b748d99

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518e2a59a672ebfdce25172ded580f4439db7c91c524a9045fa14876481c3a94
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26038e87d8aeb13c2d2d09623bbe22bb49c2482161d6eb3d482ef43db2b843a
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21b34790e22caaa0802ce3e48b112cc3e4875429c7787ef5ef3bc8e3e784d6a3
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c54e90fed14c551a28052384395c4fbd5aefd8aabca9a72fcbcbc32bf025ca0f
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1201220196b0eea01cc2e9383598f0df0fda082156bad64ee5af51ec629e09
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25dcb720489a6dcacdf3d1cc18c27188f9ede55d75d21b0750e7d6b79b7371e9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.1631912964641886,
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": 283.743,
193
  "eval_steps_per_second": 35.613,
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": 10039559454720.0,
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": 0.1813236627379873,
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": 283.743,
193
  "eval_steps_per_second": 35.613,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.17407071622846781,
198
+ "grad_norm": 0.037530913949012756,
199
+ "learning_rate": 2.1852399266194314e-06,
200
+ "loss": 10.3563,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.1813236627379873,
205
+ "eval_loss": 10.355225563049316,
206
+ "eval_runtime": 3.4386,
207
+ "eval_samples_per_second": 285.001,
208
+ "eval_steps_per_second": 35.77,
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": 11155066060800.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null