tuanna08go commited on
Commit
4b331e1
·
verified ·
1 Parent(s): ac70660

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 sha256:7e2c5c7fc38ff48483c3e8ae71cc43bf8458577319c2431096a46a5d300a8196
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05f2b717b1c242ca9586e79af4580630c4b364b3eed9fbd8822aca84fa255ef
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7738c2b980f340928153451669be7ddb705efa975da96280e374065ba4e078fa
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f87b6d6e0524b53da6365ed0626aa484324722ce834fc4d60622d15609e1d7
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ffbd4452562de0339f271c2541dc8fd70a4481fe995ac95d472b46ffc41cc97
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a24991bea02210129036dcfcc79bc9b5f7668a5d0213c1ac7852e33cc700633
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": 0.07580174927113703,
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": 0.4891,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2533047580753920.0,
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": 0.11370262390670553,
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": 0.4891,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.08746355685131195,
72
+ "grad_norm": 0.5589450597763062,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4561,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.08746355685131195,
79
+ "eval_loss": 0.4273768961429596,
80
+ "eval_runtime": 16.5732,
81
+ "eval_samples_per_second": 8.749,
82
+ "eval_steps_per_second": 4.405,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.10204081632653061,
87
+ "grad_norm": 0.5327385663986206,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.3802,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3793452898713600.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null