VERSIL91 commited on
Commit
0a12590
·
verified ·
1 Parent(s): 282f5d4

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:c7a644296d5b4f206ba5bac36fcc8e61c6d33ee96d29e7f4bbd95d12bc816854
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea02a09897252b2e119ba29ce85ebad0b2e4f1c3b09c650619814d6954e08dd
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80bf8a9c7b2a6ba84c9ca89be23662a5f6b3459007e995c81fca491af17bed74
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17001beddf74de179c7c3052ec993a5472b3fc5b374798a97a0df9dea07f061
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f038db249d80ff27a0bc300d721fbbfd6aa33f22e42efc2048660f2d9f8c09f6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5059cf0c71c51f02ee969590c9c397dea8c41610c914bdf8477692d8344aa4
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": 0.012663237039968342,
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": 736.278,
38
  "eval_steps_per_second": 369.518,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 5976883200.0,
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": 0.025326474079936684,
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": 736.278,
38
  "eval_steps_per_second": 369.518,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.018994855559952513,
43
+ "grad_norm": 2.309274911880493,
44
+ "learning_rate": 3e-05,
45
+ "loss": 177.625,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.025326474079936684,
50
+ "grad_norm": 2.5874454975128174,
51
+ "learning_rate": 4e-05,
52
+ "loss": 177.4375,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.025326474079936684,
57
+ "eval_loss": 11.09831428527832,
58
+ "eval_runtime": 0.4363,
59
+ "eval_samples_per_second": 611.905,
60
+ "eval_steps_per_second": 307.099,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 11953766400.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null