duyphu commited on
Commit
4ad228f
·
verified ·
1 Parent(s): f3c8f93

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 sha256:53a18b6a38ec222f9636a870239c5cc2a29f30cca83395996b011bb1da759a39
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f8dd5137ab509cf19c08ce56da3b8b2584d6e86d67419313826e30d8cf70ec
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2999444be69b4f71f2d964c200495fa8a5a6dfefbcb0ee76142f8492470c16c
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981b34d49485fb43b031402f8985bfc7bf4b354925c42fae14fe4f3c4fdec569
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea402b9b27c3cc250416823d1fd916c155c6766d61390bd38b5912be5e16fc65
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
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": 0.0948905109489051,
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": 0.6636,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1300253059842048.0,
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": 0.14233576642335766,
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": 0.6636,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.10948905109489052,
72
+ "grad_norm": 2.5473804473876953,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.3124,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.10948905109489052,
79
+ "eval_loss": 0.1789940446615219,
80
+ "eval_runtime": 6.3174,
81
+ "eval_samples_per_second": 18.362,
82
+ "eval_steps_per_second": 9.181,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.12773722627737227,
87
+ "grad_norm": 2.1772966384887695,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.1365,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1950379589763072.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null