VERSIL91 commited on
Commit
ee402e3
·
verified ·
1 Parent(s): 57e1cde

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 sha256:7463bca0e11d18caa1d02e4569e7b9074d4abdd785083aef3456bacc964084f4
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863b1dd58bc90de411911c57b4ad59a1b77fd96053cecf0210559d16dd37dfaf
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4823f07a39eb0c13953b19db4a7fa33ed38a92efdeb9132e76be13838758c5d9
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee7544771320d7d2cfec3267908d0b72d5dee081a59a25296617d3eef966d0ad
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:b274d200228065c5ad050511a1f7866a6edb57bdaa953138cf781ba60f5569eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
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": 0.010865874363327675,
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": 14.73,
38
  "eval_steps_per_second": 7.365,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1402135828758528.0,
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": 0.02173174872665535,
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": 14.73,
38
  "eval_steps_per_second": 7.365,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.01629881154499151,
43
+ "grad_norm": 67.22582244873047,
44
+ "learning_rate": 3e-05,
45
+ "loss": 50.0485,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.02173174872665535,
50
+ "grad_norm": 92.59852600097656,
51
+ "learning_rate": 4e-05,
52
+ "loss": 58.5185,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.02173174872665535,
57
+ "eval_loss": 3.3412952423095703,
58
+ "eval_runtime": 20.998,
59
+ "eval_samples_per_second": 14.763,
60
+ "eval_steps_per_second": 7.382,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2804271657517056.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null