tuanna08go commited on
Commit
d908914
·
verified ·
1 Parent(s): 19b4f00

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 sha256:10ec0d0b862d7b79ad817c14b37e10b57f37abe447b8df6d55dd87aa0f8b5948
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ff9c79f21e46e34c5f9fda9c1988c3aee9549bb6c9a8c6e4cd902aeed70245
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2e108bdc1d5930b01314a0432e0fc3fb3a841152f706dfba6cc6fe7d7444ec0
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e631b04193c0ed63fd5ae42d1c92a78c1f7bc2492813cb38622e61199a109
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8638d85cdde5c23462d969d214eecf01b525c427bc497c4ed563ee511772f854
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e561009e2ff39b4c9e252526ed009d5bad3c1086f161f5444dce1d8a1097b44c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0004607947823852333,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.7287,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4572708612341760.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00069119217357785,
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,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.7287,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005316862873675769,
72
+ "grad_norm": 1.5432759523391724,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6118,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005316862873675769,
79
+ "eval_loss": 0.5978233218193054,
80
+ "eval_runtime": 2010.9302,
81
+ "eval_samples_per_second": 11.814,
82
+ "eval_steps_per_second": 5.907,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006203006685955064,
87
+ "grad_norm": 1.030396819114685,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6266,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6920856278138880.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null