rizkyjun commited on
Commit
aaa6615
1 Parent(s): 6d145d1

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ea459c83c13502fd674b5a2f6d6203d713aa859a868db2df4d809c9a07787c
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bdc7e55d253c9ec7e58c6e3b56d01846cb85d7fefc6288574577a6ffb61410
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9db8fb102b0f692c644e8a568353f7750b4b9d6ff56b3b7526a4d5d26e0ec4b8
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088c0eb021e697d0cd50e40820a7ef204f59f853290094635815cd05024c22ed
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:cce4b0727c93f2042ad25efd4c533206dde71a7b73dad840653daf205d264f6c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae75103ef104e9777a5ae5b55a7cb90c71c3a63aa7b14a23492610705b9c048
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.723731517791748,
3
- "best_model_checkpoint": "./outputs/checkpoint-100",
4
- "epoch": 0.07285974499089254,
5
  "eval_steps": 100,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -21,13 +21,27 @@
21
  "eval_samples_per_second": 30.097,
22
  "eval_steps_per_second": 3.766,
23
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 100,
27
  "max_steps": 4116,
28
  "num_train_epochs": 3,
29
  "save_steps": 100,
30
- "total_flos": 2847231117803520.0,
31
  "trial_name": null,
32
  "trial_params": null
33
  }
 
1
  {
2
+ "best_metric": 2.6728808879852295,
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,
 
21
  "eval_samples_per_second": 30.097,
22
  "eval_steps_per_second": 3.766,
23
  "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.15,
27
+ "learning_rate": 0.0002,
28
+ "loss": 2.6952,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.15,
33
+ "eval_loss": 2.6728808879852295,
34
+ "eval_runtime": 204.3784,
35
+ "eval_samples_per_second": 30.698,
36
+ "eval_steps_per_second": 3.841,
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": 5679101804544000.0,
45
  "trial_name": null,
46
  "trial_params": null
47
  }