VERSIL91 commited on
Commit
9a393d5
·
verified ·
1 Parent(s): 2ac808d

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 sha256:086a36cd0c5f6c1691ee5868505f56bc2688267c78015d052f7fffdf5a9dd13c
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4111424ef9e5428123fb3b41fd02f823f51a2753c61ac9a404b75bcf01b8cd09
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f874314b2d59ec2c32ab26228db8679722490e7a1569273f4c715220429a524b
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be125ffc7e1c13669b81a0c8ed6124d92a86c469b151e6102188e0cc2397b068
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
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": 0.02448355011476664,
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": 229.091,
38
  "eval_steps_per_second": 114.545,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1240694784.0,
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": 0.04896710022953328,
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": 229.091,
38
  "eval_steps_per_second": 114.545,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.036725325172149964,
43
+ "grad_norm": 0.012828883714973927,
44
+ "learning_rate": 3e-05,
45
+ "loss": 11.9263,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.04896710022953328,
50
+ "grad_norm": 0.015544447116553783,
51
+ "learning_rate": 4e-05,
52
+ "loss": 11.9262,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.04896710022953328,
57
+ "eval_loss": 11.928632736206055,
58
+ "eval_runtime": 0.601,
59
+ "eval_samples_per_second": 229.62,
60
+ "eval_steps_per_second": 114.81,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2629091328.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null