DuongTrongChi commited on
Commit
7c5147c
1 Parent(s): 69ef8be

Training in progress, step 362, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8095535d287a5363ea56d6e1a990b793651e0842f91f0e62b2cde7ad796e3c97
3
  size 100198584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c0d97e659bc4443647ca4bb5214a3fd172de8cb97b76926060afaa1ce02b68
3
  size 100198584
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:165bc7411b625ca298d13e3c88f8745dc09872293291b602919d21265ad0ba3b
3
  size 50675604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c43689ac0cec244a4d403549cfe7f198290515d01fcc3fc5c91fcfe4ca6318
3
  size 50675604
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84cd725a97db95f8de6db3eaffde1002a056efc831c1635a52e2a74854a937e4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd284836fe01fb8da0367ba9e958c4168cceec88a256cdb9badb53073d3392b
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": 0.5274404164003287,
5
  "eval_steps": 500,
6
- "global_step": 361,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -2534,6 +2534,13 @@
2534
  "learning_rate": 1.1061643835616441e-05,
2535
  "loss": 1.1788,
2536
  "step": 361
 
 
 
 
 
 
 
2537
  }
2538
  ],
2539
  "logging_steps": 1,
@@ -2553,7 +2560,7 @@
2553
  "attributes": {}
2554
  }
2555
  },
2556
- "total_flos": 4.0655166024812544e+17,
2557
  "train_batch_size": 4,
2558
  "trial_name": null,
2559
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5289014701853711,
5
  "eval_steps": 500,
6
+ "global_step": 362,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
2534
  "learning_rate": 1.1061643835616441e-05,
2535
  "loss": 1.1788,
2536
  "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.5289014701853711,
2540
+ "grad_norm": 0.12005290389060974,
2541
+ "learning_rate": 1.1027397260273974e-05,
2542
+ "loss": 1.1608,
2543
+ "step": 362
2544
  }
2545
  ],
2546
  "logging_steps": 1,
 
2560
  "attributes": {}
2561
  }
2562
  },
2563
+ "total_flos": 4.077009720080179e+17,
2564
  "train_batch_size": 4,
2565
  "trial_name": null,
2566
  "trial_params": null