leixa commited on
Commit
5a8dbfa
·
verified ·
1 Parent(s): 7caa60d

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 sha256:71a3bcec245e9bacb9705acb8464005f9b167684fd5abf38f960eedf0fd1a515
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4422302c5e3304f9ef52deadc346711d86ba33dc412eac5cd0b5f3c53fed81
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79ae6083463b577b2086f470d99f3defc1a873def7ff86ed61317c3f0453b937
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f6a6fed9faca22e21e4eddf5012bb21f4bcef9646215da8654ed7ff256f3cc
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e4977166362ff4825c86c829e9e5a8ae75df9ab05f42e119bdb7c534fc843e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc6846f8d7792f53afeb133ddd6619087b969a17df16f3944cdb56cafa0721f
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": 0.01170884017433162,
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": 9.007,
193
  "eval_steps_per_second": 1.127,
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": 1.1656540830302208e+17,
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": 0.013009822415924023,
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": 9.007,
193
  "eval_steps_per_second": 1.127,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.012489429519287061,
198
+ "grad_norm": 1.6445835828781128,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.5315,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.013009822415924023,
205
+ "eval_loss": 0.3398222029209137,
206
+ "eval_runtime": 718.5752,
207
+ "eval_samples_per_second": 9.008,
208
+ "eval_steps_per_second": 1.127,
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": 1.2944556391661568e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null