rizkyjun commited on
Commit
7d1c7a0
1 Parent(s): 87b5928

Training in progress, step 4000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09af5650532bd8b482ed8a219ee62a8081101951ec735321e89017d31b176741
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2859ced70bd0cc114014626a2a07552ee2ddc904b30812c14b951d716f0b5d05
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09e364a0df2822ba617527aa0559e22bc3367696b395ef1b3e93fd9a7971bd2
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3394af7b82a5e4a624e525564734f797182105143f0ea5ad6468e0e0d9acd8
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4d4fec55083981c7a8b41d24f9a0c06691f34476dffbd5f9f0bb89a650c7032
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe072b43116ea6af1d9839ff9078df37c5fb13f3285b4cbe739c3c5d14228bdf
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9771522283554077,
3
- "best_model_checkpoint": "./outputs/checkpoint-3900",
4
- "epoch": 2.841530054644809,
5
  "eval_steps": 100,
6
- "global_step": 3900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -553,13 +553,27 @@
553
  "eval_samples_per_second": 29.023,
554
  "eval_steps_per_second": 3.631,
555
  "step": 3900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
556
  }
557
  ],
558
  "logging_steps": 100,
559
  "max_steps": 4116,
560
  "num_train_epochs": 3,
561
  "save_steps": 100,
562
- "total_flos": 1.1452801265934336e+17,
563
  "trial_name": null,
564
  "trial_params": null
565
  }
 
1
  {
2
+ "best_metric": 1.9712703227996826,
3
+ "best_model_checkpoint": "./outputs/checkpoint-4000",
4
+ "epoch": 2.9143897996357016,
5
  "eval_steps": 100,
6
+ "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
553
  "eval_samples_per_second": 29.023,
554
  "eval_steps_per_second": 3.631,
555
  "step": 3900
556
+ },
557
+ {
558
+ "epoch": 2.91,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.9399,
561
+ "step": 4000
562
+ },
563
+ {
564
+ "epoch": 2.91,
565
+ "eval_loss": 1.9712703227996826,
566
+ "eval_runtime": 210.5398,
567
+ "eval_samples_per_second": 29.8,
568
+ "eval_steps_per_second": 3.729,
569
+ "step": 4000
570
  }
571
  ],
572
  "logging_steps": 100,
573
  "max_steps": 4116,
574
  "num_train_epochs": 3,
575
  "save_steps": 100,
576
+ "total_flos": 1.1744177835220992e+17,
577
  "trial_name": null,
578
  "trial_params": null
579
  }