rizkyjun commited on
Commit
f42a717
1 Parent(s): 5a38d71

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 sha256:59d777d2ee7103580893746a589b3d1e9c7ef5c56f8d9be87d7d8ed400ceede2
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d5717d5e121b4a9bba056713d9a4117b8354d97745c930f52701b07619bea85
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e35c8c44e73996db2eade8af211bbc06db0bb369e6d88cecf3e8d49d2c3f63
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c2cbab738e150703e3a6da3c3bae0fd4f50b4d91b9c9811ca2b77a15897403
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:bb3d217570474ed44ac994697c08a6231247f4bb9ecce7bb8af4dbe390e8d62a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26837cce4b9686e80c01fd503576bec322032548fab3bb432c6bb17f35ea1da
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": 2.591986656188965,
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": 30.577,
36
  "eval_steps_per_second": 3.826,
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": 5821275858370560.0,
45
  "trial_name": null,
46
  "trial_params": null
47
  }
 
1
  {
2
+ "best_metric": 2.5554449558258057,
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": 30.577,
36
  "eval_steps_per_second": 3.826,
37
  "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.22,
41
+ "learning_rate": 0.0002,
42
+ "loss": 2.5624,
43
+ "step": 300
44
+ },
45
+ {
46
+ "epoch": 0.22,
47
+ "eval_loss": 2.5554449558258057,
48
+ "eval_runtime": 204.8733,
49
+ "eval_samples_per_second": 30.624,
50
+ "eval_steps_per_second": 3.832,
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": 8750270976491520.0,
59
  "trial_name": null,
60
  "trial_params": null
61
  }