Nexspear commited on
Commit
a53a70e
1 Parent(s): 3a963f8

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:d75dcfe6f7c9c47b4f2a40b78e53ebb5a275bdadf7224ccf72c4c8d5ce4348df
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78043dea6cb338a429be4c052d88155900ca23db041823edc36ac048bb4c9b0d
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e40a56b2b621478da56b1bd3359d9a4afb25e3dda81c3bca2f75d0960db6574
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf74c815d510ab1d130bfd3dc1e11cf57c690023c40ecdd2421c1939a677a9fa
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd984f4b4de98886636a6a9007958c72c44e7d3e141c18b4d25bda2d131f83c3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd49318ccc20e21bfc5390137f4a7225e8af4c65121f396f3a3a38c05495d065
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": 0.015471892728210418,
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": 28.489,
193
  "eval_steps_per_second": 3.565,
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": 1.822849014693888e+16,
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": 0.017190991920233798,
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": 28.489,
193
  "eval_steps_per_second": 3.565,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.016503352243424446,
198
+ "grad_norm": 2.28126859664917,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.5964,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.017190991920233798,
205
+ "eval_loss": 0.5866773128509521,
206
+ "eval_runtime": 171.925,
207
+ "eval_samples_per_second": 28.495,
208
+ "eval_steps_per_second": 3.566,
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": 2.02538779410432e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null