ramdhanfirdaus commited on
Commit
3da09ee
1 Parent(s): 9bec5c4

Training in progress, step 3400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:324e95b7ddd0918ff8d9f8ecda2dd142c9e8889d31342e80c640b8efa6cdf99c
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f90a2da63f348434e3f45b718dce2b3f87a252225c3397aa8a051d7ece42cc6
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a96cd6c980e9348d7dc3e0b1b6e8178f2b0b44a80a7ee733fcce0b8671654e26
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c503eadb83102e83f532a9055aebab231aec2a0f1357cdec5c679711330825
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9806d4b87a560e81af9be766aec43076c5b1c0d6415e86c57d80b3f77acf5d6f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a46f0218404e0c30dbd1af232f5ed9fc7773078be75008ba1a070be2f38d151
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.147517442703247,
3
- "best_model_checkpoint": "./outputs/checkpoint-3300",
4
- "epoch": 2.4043715846994536,
5
  "eval_steps": 100,
6
- "global_step": 3300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -469,13 +469,27 @@
469
  "eval_samples_per_second": 14.768,
470
  "eval_steps_per_second": 1.848,
471
  "step": 3300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
472
  }
473
  ],
474
  "logging_steps": 100,
475
  "max_steps": 4116,
476
  "num_train_epochs": 3,
477
  "save_steps": 100,
478
- "total_flos": 1.0698532741881631e+18,
479
  "trial_name": null,
480
  "trial_params": null
481
  }
 
1
  {
2
+ "best_metric": 1.1388046741485596,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3400",
4
+ "epoch": 2.477231329690346,
5
  "eval_steps": 100,
6
+ "global_step": 3400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
469
  "eval_samples_per_second": 14.768,
470
  "eval_steps_per_second": 1.848,
471
  "step": 3300
472
+ },
473
+ {
474
+ "epoch": 2.48,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.1114,
477
+ "step": 3400
478
+ },
479
+ {
480
+ "epoch": 2.48,
481
+ "eval_loss": 1.1388046741485596,
482
+ "eval_runtime": 418.7042,
483
+ "eval_samples_per_second": 14.984,
484
+ "eval_steps_per_second": 1.875,
485
+ "step": 3400
486
  }
487
  ],
488
  "logging_steps": 100,
489
  "max_steps": 4116,
490
  "num_train_epochs": 3,
491
  "save_steps": 100,
492
+ "total_flos": 1.1022399703988951e+18,
493
  "trial_name": null,
494
  "trial_params": null
495
  }