flytech commited on
Commit
c06222a
·
1 Parent(s): 2f36a9f

Training in progress, step 4400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2029b015c12aeb25ab51b772c66ce116a93aac9dffe0a7d81f098cebb1ca6544
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ed39a0968d051dda074d794ca8bcc45816d6a238edb2ccbd4f057bb5f10468
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1117e46e99a5e490661d56a28e24aa8b00836571773c4cfecea4c0952ba0fee9
3
  size 127492797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda994f7860244e527838bd7988860c7751c42b91b0a4c1ea83eacb4d8e05605
3
  size 127492797
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:952e610382e9581298226b3dbae8a729cd9250e3805616b6f9a665a9442be060
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225d5a030ecae7c13bb65956499b03c5257cafc30b443a5742467364fdb55307
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1148c295890aef97427a11a5a53b94b8b59594e8519b33223027fa87b288829
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91eca19795b1c7d11478e04b13580f13e7f7063d5aa47ea25de94880cdd6fcc8
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 12.804878048780488,
5
  "eval_steps": 200,
6
- "global_step": 4200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -280,13 +280,26 @@
280
  "eval_samples_per_second": 7.922,
281
  "eval_steps_per_second": 0.517,
282
  "step": 4200
 
 
 
 
 
 
 
 
 
 
 
 
 
283
  }
284
  ],
285
  "logging_steps": 200,
286
  "max_steps": 4920,
287
  "num_train_epochs": 15,
288
  "save_steps": 200,
289
- "total_flos": 1.3530591192416256e+18,
290
  "trial_name": null,
291
  "trial_params": null
292
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 13.414634146341463,
5
  "eval_steps": 200,
6
+ "global_step": 4400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
280
  "eval_samples_per_second": 7.922,
281
  "eval_steps_per_second": 0.517,
282
  "step": 4200
283
+ },
284
+ {
285
+ "epoch": 13.41,
286
+ "learning_rate": 0.0002,
287
+ "loss": 0.0282,
288
+ "step": 4400
289
+ },
290
+ {
291
+ "epoch": 13.41,
292
+ "eval_runtime": 34.8362,
293
+ "eval_samples_per_second": 7.923,
294
+ "eval_steps_per_second": 0.517,
295
+ "step": 4400
296
  }
297
  ],
298
  "logging_steps": 200,
299
  "max_steps": 4920,
300
  "num_train_epochs": 15,
301
  "save_steps": 200,
302
+ "total_flos": 1.4173693942431744e+18,
303
  "trial_name": null,
304
  "trial_params": null
305
  }