ramdhanfirdaus commited on
Commit
9838038
1 Parent(s): 8ab1533

Training in progress, step 300, 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:f4bb27604a5c32bac6d3f65926248efd42781f541704419617efe82e083fb2ad
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2408fbc8c6fca425c1ecd7b70d7a83eac637e7fa36128746041ff1459a0f9c
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b21fd2092bc03311b3a1c23a1ec7b12aad53d46c8868b6ea69c386371e4ac65
3
- size 100692937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383a3db59bc21487f9fc5c5749cab26322fe065138915593c4c1f763012ee7f5
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:a8cca4050b412069a5a574ef82deadd3fd628d6acb7444705fb5ae44f31ae444
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0991493e3ac522258a52c5e5855e34a1077a108bf34c050d61cd9082a802fb6b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9196887016296387,
3
- "best_model_checkpoint": "./outputs/checkpoint-200",
4
- "epoch": 0.14571948998178508,
5
  "eval_steps": 100,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -35,13 +35,27 @@
35
  "eval_samples_per_second": 43.652,
36
  "eval_steps_per_second": 5.462,
37
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
39
  ],
40
  "logging_steps": 100,
41
  "max_steps": 4116,
42
  "num_train_epochs": 3,
43
  "save_steps": 100,
44
- "total_flos": 1.1917344486653952e+16,
45
  "trial_name": null,
46
  "trial_params": null
47
  }
 
1
  {
2
+ "best_metric": 1.8589884042739868,
3
+ "best_model_checkpoint": "./outputs/checkpoint-300",
4
+ "epoch": 0.2185792349726776,
5
  "eval_steps": 100,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
35
  "eval_samples_per_second": 43.652,
36
  "eval_steps_per_second": 5.462,
37
  "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.22,
41
+ "learning_rate": 0.0002,
42
+ "loss": 1.8881,
43
+ "step": 300
44
+ },
45
+ {
46
+ "epoch": 0.22,
47
+ "eval_loss": 1.8589884042739868,
48
+ "eval_runtime": 143.706,
49
+ "eval_samples_per_second": 43.659,
50
+ "eval_steps_per_second": 5.463,
51
+ "step": 300
52
  }
53
  ],
54
  "logging_steps": 100,
55
  "max_steps": 4116,
56
  "num_train_epochs": 3,
57
  "save_steps": 100,
58
+ "total_flos": 1.7888590056259584e+16,
59
  "trial_name": null,
60
  "trial_params": null
61
  }