ramdhanfirdaus commited on
Commit
312c118
1 Parent(s): 4345548

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 sha256:5b47f7cb7f80077d04d264b8f37193d2acf6798c4a211d0ffff9d7ea8e53d8c0
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20fe6b6731c87461e5d236dbee3b5362f6ea24eb9eb26b7b0f64729a0eae81b
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f9ba58e13cbad9ee95bcbf4071bc0eed8ec6de53092d6b862bbe300f43bd3b3
3
  size 151032837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d24a097cd42c0f1ab5a4ee54c6c2b9f2fe8360152e6a8a7d7574b3d621e73ba
3
  size 151032837
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:baca4f1b68fe3db55c3f9c8ea267473af8c9b358050255190a124d44cbf1200b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63f840c83291fc5960ae39fd8fa5846eb4ff5d9e718f5f03667b39592197864
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": 1.1353813409805298,
3
- "best_model_checkpoint": "./outputs/checkpoint-3600",
4
- "epoch": 2.62367941712204,
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": 18.449,
512
  "eval_steps_per_second": 2.308,
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": 1.167321484023469e+18,
521
  "trial_name": null,
522
  "trial_params": null
523
  }
 
1
  {
2
+ "best_metric": 1.1255244016647339,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3700",
4
+ "epoch": 2.6965391621129324,
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": 18.449,
512
  "eval_steps_per_second": 2.308,
513
  "step": 3600
514
+ },
515
+ {
516
+ "epoch": 2.7,
517
+ "learning_rate": 0.0002,
518
+ "loss": 1.1106,
519
+ "step": 3700
520
+ },
521
+ {
522
+ "epoch": 2.7,
523
+ "eval_loss": 1.1255244016647339,
524
+ "eval_runtime": 341.3582,
525
+ "eval_samples_per_second": 18.38,
526
+ "eval_steps_per_second": 2.3,
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": 1.1997692622325402e+18,
535
  "trial_name": null,
536
  "trial_params": null
537
  }