leixa commited on
Commit
3d7b8cb
·
verified ·
1 Parent(s): 6e93336

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:f6b56923beec83daf4b026ee2133d040a519081a62e227296483cd8df272210f
3
  size 891333320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13deb827311c7a5bd838b3a877a2fcc9af4b016dd3aae7c5b3c40828cdb31ab
3
  size 891333320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f37a9a57c9c4be5cff76268cd1a529e45c82fcd8a86b9154525a2af946d9382
3
  size 452984596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64656c874811bee768f769614475f0e1357cfac204fb06c7403d5a13a996fe02
3
  size 452984596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f07634e13278ce60c6592f28cbbf6ad4cbc5a47fd1171ae4cc47ef803f82b3e4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba69d3edb82d7fa70854881e84c1a5a63d1704c29946cf74bb0eddccebd5f067
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": 0.06500541711809317,
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": 2.568,
193
  "eval_steps_per_second": 0.322,
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": 2.48060382806016e+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": 0.07222824124232576,
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": 2.568,
193
  "eval_steps_per_second": 0.322,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.06933911159263272,
198
+ "grad_norm": 0.06964542716741562,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.0012,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.07222824124232576,
205
+ "eval_loss": 0.0003464781621005386,
206
+ "eval_runtime": 453.9994,
207
+ "eval_samples_per_second": 2.568,
208
+ "eval_steps_per_second": 0.322,
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": 2.7562264756224e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null