leixa commited on
Commit
f2efe18
·
verified ·
1 Parent(s): d2232ac

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 sha256:39780879b55af36d3fa91720510636d00c6e52a423e8f08e326a989983f210c7
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc18516462ead5002e9f5549971060761581de6472a82bad32982a349f2ae27
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae6db2f954da1f81b84ac81696b6881920d93a6c5ea5cc1763d5c384ef630497
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2f77f012263921bb45ed8b9b8cb85b7c2665b5dd6cd4b92939d23573d3dc17
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e78c0407e9b9da7ed46812d33357290c89503de08bb3783c4c0def49e11abbf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7164d3736e810228e5cb92983fde47cc89c40873a803d66b109e7a1c6766ce0a
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": 0.060749240634492066,
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": 4.336,
193
  "eval_steps_per_second": 0.542,
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": 1.1741738917114675e+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": 0.06749915626054674,
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": 4.336,
193
  "eval_steps_per_second": 0.542,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.06479919001012488,
198
+ "grad_norm": 9.620219230651855,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 4.6745,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.06749915626054674,
205
+ "eval_loss": 0.9605395197868347,
206
+ "eval_runtime": 287.8877,
207
+ "eval_samples_per_second": 4.335,
208
+ "eval_steps_per_second": 0.542,
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": 1.3038984859798733e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null