ramdhanfirdaus commited on
Commit
a263dda
1 Parent(s): 4c1c564

Training in progress, step 2700, 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:cb833c87b5112d0139a3072a6b4f95cd4323cfd3d156ef6a8e841ebfac293362
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e2cdc75106d1ad5f42dc96e7ace20ebbd09c05bbb12e683edfe1e467ed2816
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:144c2af10cc322d858a390c1516fd6b81e604b7ee197aa471e1a7706f6ff4a4e
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76b030b5a876bdfcadcf5f497226e6adf7d57102b1edffdf58e5b318cf41c41
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7376cbf010a9f08e21c74d30e4ee024a7246fb9200b1adb483a435bf9cadb59a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e1dc4e8513a0bba3d4b52d1e66539d1d92aa1df08b8a7f141be24c582260ed
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.38627290725708,
3
- "best_model_checkpoint": "./outputs/checkpoint-2600",
4
- "epoch": 1.8943533697632058,
5
  "eval_steps": 100,
6
- "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -371,13 +371,27 @@
371
  "eval_samples_per_second": 43.582,
372
  "eval_steps_per_second": 5.453,
373
  "step": 2600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
374
  }
375
  ],
376
  "logging_steps": 100,
377
  "max_steps": 4116,
378
  "num_train_epochs": 3,
379
  "save_steps": 100,
380
- "total_flos": 1.549670670211154e+17,
381
  "trial_name": null,
382
  "trial_params": null
383
  }
 
1
  {
2
+ "best_metric": 1.3713726997375488,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2700",
4
+ "epoch": 1.9672131147540983,
5
  "eval_steps": 100,
6
+ "global_step": 2700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
371
  "eval_samples_per_second": 43.582,
372
  "eval_steps_per_second": 5.453,
373
  "step": 2600
374
+ },
375
+ {
376
+ "epoch": 1.97,
377
+ "learning_rate": 0.0002,
378
+ "loss": 1.3689,
379
+ "step": 2700
380
+ },
381
+ {
382
+ "epoch": 1.97,
383
+ "eval_loss": 1.3713726997375488,
384
+ "eval_runtime": 143.9492,
385
+ "eval_samples_per_second": 43.585,
386
+ "eval_steps_per_second": 5.453,
387
+ "step": 2700
388
  }
389
  ],
390
  "logging_steps": 100,
391
  "max_steps": 4116,
392
  "num_train_epochs": 3,
393
  "save_steps": 100,
394
+ "total_flos": 1.6093831259072102e+17,
395
  "trial_name": null,
396
  "trial_params": null
397
  }