leixa commited on
Commit
cd6cf1b
·
verified ·
1 Parent(s): f4673e2

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:aa7195f4dda21dad2a467109e670a3a6e2577fe5ea469d36f3ebb0e856b4f6cc
3
  size 3029024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7881d2192a72d768e83a4c578c8d6e6b95e0aa93b422332fa3d3241d9c66e3ec
3
  size 3029024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91e7795cfa3a38197bb3414c404d5795d09d107f8d95a22142d3ed245d907cd5
3
  size 1663290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b362e17a533a6eb69210542e76ce89ff9a12db6193e4a9ece7bf4be0465589
3
  size 1663290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a0e4ce3ad5bf553f6053fd3f7c81391f47a630679113bc7ac3ecea8868321a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f19ada03c6be8119a9a936035f3b3c2c7dff686c34e43580093c58419306cea
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": 0.5128205128205128,
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": 116.688,
193
  "eval_steps_per_second": 14.98,
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": 37284992778240.0,
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": 0.5698005698005698,
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": 116.688,
193
  "eval_steps_per_second": 14.98,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.5470085470085471,
198
+ "grad_norm": 6.029376029968262,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 2.4233,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.5698005698005698,
205
+ "eval_loss": 2.3306732177734375,
206
+ "eval_runtime": 1.259,
207
+ "eval_samples_per_second": 117.55,
208
+ "eval_steps_per_second": 15.091,
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": 41046198190080.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null