VERSIL91 commited on
Commit
fa95b28
1 Parent(s): fe1f26b

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 sha256:062e9141bfb46fa4ab553c00c29f938945a24ebdd4cc2e42135e36a3c25c8d77
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74990d5c900d26b0ab035b62dda006bcb0a09cb9abd0bb0604d8630ec2add5c7
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce1dcedaec5703d916ab79d0e7f200d2958d5c84272058fee3f1e7227e85584e
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa8b8ec74bef651602031a344bce1dffac7e7be9d1907182c1be1ce56b62a23
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68ba991c155af792f54930c0284de016a912e165e6ce8b3a7f948c04650e6fcd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89fa8ac371a5d659948365d7c799bf69558c73b93c260685c8661740a2c99b2c
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": 0.00021404109589041095,
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": 12.276,
38
  "eval_steps_per_second": 6.138,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2605973017460736.0,
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": 0.0004280821917808219,
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": 12.276,
38
  "eval_steps_per_second": 6.138,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0003210616438356164,
43
+ "grad_norm": 4.463776111602783,
44
+ "learning_rate": 3e-05,
45
+ "loss": 19.9405,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0004280821917808219,
50
+ "grad_norm": 5.855804443359375,
51
+ "learning_rate": 4e-05,
52
+ "loss": 19.9278,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0004280821917808219,
57
+ "eval_loss": 1.1730619668960571,
58
+ "eval_runtime": 1499.2803,
59
+ "eval_samples_per_second": 10.497,
60
+ "eval_steps_per_second": 5.249,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5211946034921472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null