leixa commited on
Commit
85af770
·
verified ·
1 Parent(s): b9f7f41

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 sha256:921bb82ae17117b8621123cad231cc96b11b51415097c9afe198d94b22076dea
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628c2ef6f861f0ac658fd1ce12542b16b13fa6c06c98c094effc3c14fb13767b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5180a6a48f042324d7beea7da8cf40d05e7ca52e2c6f053e271ce03dee502e0
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf2d9e8f83ef4a760dba9ca57de9fea1f00be592b400e0511274bdbfb6e83d0
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ddb965365707e9cf823c0aae963aeebeb54a3819b41dd6759a3b8366ca82d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c958db52c8f3bef2b4496289cf5bdac6315e7c6f54a35496981ee742b7a992
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": 0.36217303822937624,
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": 6.329,
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": 1.3501196529775411e+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": 0.4024144869215292,
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": 6.329,
193
  "eval_steps_per_second": 0.818,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.386317907444668,
198
+ "grad_norm": 0.04322628304362297,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.0043,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.4024144869215292,
205
+ "eval_loss": 0.006113050039857626,
206
+ "eval_runtime": 33.0447,
207
+ "eval_samples_per_second": 6.325,
208
+ "eval_steps_per_second": 0.817,
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": 1.497199726905262e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null