leixa commited on
Commit
545716d
·
verified ·
1 Parent(s): b4dba73

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 sha256:48ae5bd7c4d6fe9409efbc4453b6728e02bc913dc9f4849177d6aeb59bafc70a
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95f7e794b6c94ba0094c446cdaf3ad418167fbbb4caea48d703ebe73be306c25
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cd8a1ecd181db264d4e28c8c51d617c76b2405f2046ad21641a769bd3116886
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c1ecffe4d7baceb9c30a728096344bde16bab65ce6a48f1ecd5706e6f4c995
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:b52a51c3b4c01f9b630403ebb6928c43e1ecb011855669002547cf6d66e6c4a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524d831f581d7d84c7abb4d185bae3e33c8f732dfd7030de6682f0668dfd8c11
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": 0.010552233556102708,
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": 6.544,
193
  "eval_steps_per_second": 0.818,
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": 1.159221252980736e+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": 0.011724703951225232,
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": 6.544,
193
  "eval_steps_per_second": 0.818,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.011255715793176222,
198
+ "grad_norm": 1.3977020978927612,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.8796,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.011724703951225232,
205
+ "eval_loss": 0.49200761318206787,
206
+ "eval_runtime": 1097.472,
207
+ "eval_samples_per_second": 6.544,
208
+ "eval_steps_per_second": 0.818,
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": 1.28802361442304e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null