VERSIL91 commited on
Commit
4e10a20
·
verified ·
1 Parent(s): cd1f1ce

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 sha256:2399d55a497259cf5900eaff44e211e2fa4dc4f4a7fbc2dcf6ae12eb4e0e4771
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7689f33151bd82adef3fbdd806f0a896151ad5ded514487710f21184e1a66f
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3de6098e8b9058ee1ab3255ed890ade5c93f73355661144cd153ee3365086e6c
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f2782ade138c5a2770b8fa3c20889fa7d2d170607dda48aaf8cf35717e1190
3
  size 55549892
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": 0.00010216983180291439,
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": 33.799,
38
  "eval_steps_per_second": 16.9,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1641914893860864.0,
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": 0.00020433966360582879,
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": 33.799,
38
  "eval_steps_per_second": 16.9,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00015325474770437158,
43
+ "grad_norm": 2.3463869094848633,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.4839,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00020433966360582879,
50
+ "grad_norm": 2.5627706050872803,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.2932,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00020433966360582879,
57
+ "eval_loss": 2.3392558097839355,
58
+ "eval_runtime": 976.0151,
59
+ "eval_samples_per_second": 33.779,
60
+ "eval_steps_per_second": 16.89,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3283829787721728.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null