VERSIL91 commited on
Commit
64b9b90
·
verified ·
1 Parent(s): 7516c15

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:e51ec39da4f163ea8cca843924532d180990f4139f1d0764f9328a535f3e09b3
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcfc68a0e43d4d028e46223ca7b91aa8d10958de847b42ee9b690c1e3f3ab96
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d9104fc59b23d619eedb40886706708bb6bbc669947113b4bb489e423f07b9b
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9496c301e6d38ed970a886a094c9409ba5beedee8d9d568a3b4bff5f2e28f782
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
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": 0.035437430786267994,
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": 3.881,
38
  "eval_steps_per_second": 1.961,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1744534574727168.0,
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": 0.07087486157253599,
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": 3.881,
38
  "eval_steps_per_second": 1.961,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.053156146179401995,
43
+ "grad_norm": 18.850143432617188,
44
+ "learning_rate": 3e-05,
45
+ "loss": 9.2496,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.07087486157253599,
50
+ "grad_norm": 18.118839263916016,
51
+ "learning_rate": 4e-05,
52
+ "loss": 8.4158,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.07087486157253599,
57
+ "eval_loss": 8.082810401916504,
58
+ "eval_runtime": 11.9435,
59
+ "eval_samples_per_second": 7.954,
60
+ "eval_steps_per_second": 4.019,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3489069149454336.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null