tuanna08go commited on
Commit
1af5225
·
verified ·
1 Parent(s): b6b6911

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56475e93ce7cff8292a5c72c111884812351786d4cf7a3b971cf8db967c087ac
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3cc115eb1ad4fd6b7168cf39a996072a7dc026ee5d972b7b20fda92df928fd
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e7a05122889604474c937383b90ee24bb0e7c5cc44e8e878cd9319e66dc6a93
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2b59980192090ff7529d2bf901733237a729b5a71fceed7fb53e56edc4aa28
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:320c97659e9ba82f4197bb31b458f13f660b2c6a35305b9930a3cd19dfefa4c0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc91beb7cc1d669cf71bea806ff3c7c78a86a84fd677616fb738c94788d95c31
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.23690205011389523,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 26.728,
46
  "eval_steps_per_second": 3.359,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 2.67546063273984e+16,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3553530751708428,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 26.728,
46
  "eval_steps_per_second": 3.359,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.2733485193621868,
51
+ "grad_norm": 2.113602876663208,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 1.0209,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.2733485193621868,
58
+ "eval_loss": 0.4289436638355255,
59
+ "eval_runtime": 27.4522,
60
+ "eval_samples_per_second": 26.956,
61
+ "eval_steps_per_second": 3.388,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 4.018055422987469e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null