leixa commited on
Commit
dea6b94
·
verified ·
1 Parent(s): dab7dbc

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:b70c7ba46bb873261fd1b9db78f45e98b9db5e7e1dc4f19b33dbc60593d8dfc4
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb347431aeea43f067c7c51a09718e7017ecf492a03b878b649f7bbb06ecefb8
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7327c4355f0252777e59c7b73f1633a7b99a85dce16a29a468db53fa026d2a7b
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220304e7b2efa7d4aaef8b31b0ca6273983c38b9a824330fdc67233f8df1d273
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": 0.07610993657505286,
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": 7.724,
193
  "eval_steps_per_second": 0.969,
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": 1.1843508704064307e+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": 0.08456659619450317,
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": 7.724,
193
  "eval_steps_per_second": 0.969,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.08118393234672304,
198
+ "grad_norm": 0.8015875816345215,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.5421,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.08456659619450317,
205
+ "eval_loss": 1.5743869543075562,
206
+ "eval_runtime": 128.9426,
207
+ "eval_samples_per_second": 7.724,
208
+ "eval_steps_per_second": 0.969,
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": 1.315199833425838e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null