ramdhanfirdaus commited on
Commit
8f6456f
1 Parent(s): 021bcc3

Training in progress, step 3700, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d68bbb11be68bac250fdb245929bc5c33eb92572532a1c32e8786929240c64d
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506c9daa9a63f8a0359134f35e7222923af01f5861d09d9b702197ca38eff035
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9aade19b93275ace19302d959a9374b28d9a3d7a83c64fc202a6ecfd3051f30
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe1a670b9bd5b8db81a448d712a1caa862846faee9fbbfbb84cdc51054a1a9b
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:ef0cbe118e41f50f73b72dc69901b2174467b76d419ab6a1e3302e9eaafde12a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff244788f228d59f20add1a127912b5b144f70e4c321b25031a681809deb1ae0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2679202556610107,
3
- "best_model_checkpoint": "./outputs/checkpoint-3600",
4
- "epoch": 2.6229508196721314,
5
  "eval_steps": 100,
6
- "global_step": 3600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -511,13 +511,27 @@
511
  "eval_samples_per_second": 43.56,
512
  "eval_steps_per_second": 5.45,
513
  "step": 3600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
514
  }
515
  ],
516
  "logging_steps": 100,
517
  "max_steps": 4116,
518
  "num_train_epochs": 3,
519
  "save_steps": 100,
520
- "total_flos": 2.145691983734784e+17,
521
  "trial_name": null,
522
  "trial_params": null
523
  }
 
1
  {
2
+ "best_metric": 1.255784034729004,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3700",
4
+ "epoch": 2.6958105646630237,
5
  "eval_steps": 100,
6
+ "global_step": 3700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
511
  "eval_samples_per_second": 43.56,
512
  "eval_steps_per_second": 5.45,
513
  "step": 3600
514
+ },
515
+ {
516
+ "epoch": 2.7,
517
+ "learning_rate": 0.0002,
518
+ "loss": 1.2346,
519
+ "step": 3700
520
+ },
521
+ {
522
+ "epoch": 2.7,
523
+ "eval_loss": 1.255784034729004,
524
+ "eval_runtime": 144.0435,
525
+ "eval_samples_per_second": 43.556,
526
+ "eval_steps_per_second": 5.45,
527
+ "step": 3700
528
  }
529
  ],
530
  "logging_steps": 100,
531
  "max_steps": 4116,
532
  "num_train_epochs": 3,
533
  "save_steps": 100,
534
+ "total_flos": 2.2052180376706253e+17,
535
  "trial_name": null,
536
  "trial_params": null
537
  }