Nexspear commited on
Commit
4963cec
·
verified ·
1 Parent(s): 2da08da

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 sha256:687f4bca35f0d9df993f6d5b62109940fe0e84817db534ae8363cc0735fba861
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396a65161a5e1dad478eab1ec7451c51991b39c0fc408294cdeb4e7dd9ddb001
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16377976c107a6c66a499279562140fcb8371bea43a081943d633f33b2e65a86
3
  size 418030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d734b2c6baefab2efdad90f3486218f5d99f6407cddcee732b395904b322212
3
  size 418030
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba868925edaf5516534779d862378ff0c5b1a6e19d0ed88b5d7747286b450e1c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3deb59f4eaa352304276d8014ac6fbe0892eaba3c8b4e86358bfe44bf098648
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": 1.6513761467889907,
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": 731.69,
193
  "eval_steps_per_second": 95.438,
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": 1009785145344.0,
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": 1.834862385321101,
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": 731.69,
193
  "eval_steps_per_second": 95.438,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 1.761467889908257,
198
+ "grad_norm": 0.30095237493515015,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 6.7224,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 1.834862385321101,
205
+ "eval_loss": 6.840231895446777,
206
+ "eval_runtime": 0.0584,
207
+ "eval_samples_per_second": 788.113,
208
+ "eval_steps_per_second": 102.797,
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": 1110703589376.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null