VERSIL91 commited on
Commit
7c157de
1 Parent(s): b21e730

Training in progress, step 4, 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:dd5938c54f44b94d480f2db736c0156ba0dac3e1886492fb503630e9a87164a1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a7c4985ae84e67304fc2d65ae7ea45cacffa774287686d3489a1f11f3031b1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0301e84aaaac7ed15e7dcee318588f354054fefb22e329055a45557f7360fdd
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659d8c85da31f50ad5afc327a2edcbf690f9f0dadc24c7014b666fa838bc8ff3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40f219058e6301bb2653ecd8c3eebd744bbf0a5bf23e0f8d9248d40cab6a39ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017583d2bd93fe9910a82ceabe249f8fabc7dfeef29c7c3f997a8f45e0fab04d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.00026577852343419073,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 28.724,
38
  "eval_steps_per_second": 14.362,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1479651398516736.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0005315570468683815,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 28.724,
38
  "eval_steps_per_second": 14.362,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0003986677851512861,
43
+ "grad_norm": 2.559051513671875,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.7985,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0005315570468683815,
50
+ "grad_norm": 2.5379083156585693,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.6094,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0005315570468683815,
57
+ "eval_loss": 2.7825121879577637,
58
+ "eval_runtime": 574.2258,
59
+ "eval_samples_per_second": 22.071,
60
+ "eval_steps_per_second": 11.036,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2959302797033472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null