rizkyjun commited on
Commit
b2e787d
1 Parent(s): 3647bb0

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 sha256:8ea44eb2b44b63513c037fd61f3a455fde516b2fece30f948a241af8f61c02bc
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de543f42a8abb4cb8e9dd09d039525e203dedc7a7bd91c415eeadaae4f2776a
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:452385aa0dd9e5510e5632f2be488c98fc676ac604bd98f5603646439a696e10
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ba863b187e607ef384544a77872b58f6d7edb94ea8f2a6e193f23f3d167e78
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": 1.9740982055664062,
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": 30.42,
554
  "eval_steps_per_second": 3.806,
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": 1.969947099685669,
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": 30.42,
554
  "eval_steps_per_second": 3.806,
555
  "step": 3900
556
+ },
557
+ {
558
+ "epoch": 2.91,
559
+ "learning_rate": 0.0002,
560
+ "loss": 1.9383,
561
+ "step": 4000
562
+ },
563
+ {
564
+ "epoch": 2.91,
565
+ "eval_loss": 1.969947099685669,
566
+ "eval_runtime": 206.1194,
567
+ "eval_samples_per_second": 30.439,
568
+ "eval_steps_per_second": 3.808,
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
  }