tuanna08go commited on
Commit
561672c
1 Parent(s): f738db6

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 sha256:51581e48ee166ee26ee4f2ecca213c29ca9e5b2efde2af16556162219fe359a2
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890eb932ca4c160b30fa7984161d124eb5a7ddb10b54d4ee075bcef3ef9b5fbd
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56a5ed99eaa8960d202147b7983e4604d295b3693ec6fa2ff7be3e60c83ea551
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5780ab7c1c4bbc3e35107067c1eb51537ec052d82a39f26905bb89348fa4a4e
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea9b7c11e7b99a178580a46667e4e41b4aae3b906e765f175b969edf030ede0a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ceaf1922bf3db1a08d574607be64151b478ec76f9bee9cff4e31dc3ad2dff2
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": 0.006643669349686981,
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": 0.1541,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1154618474102784.0,
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": 0.009965504024530471,
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": 0.1541,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007665772326561901,
72
+ "grad_norm": 0.2781718969345093,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.1247,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007665772326561901,
79
+ "eval_loss": 0.13439211249351501,
80
+ "eval_runtime": 227.907,
81
+ "eval_samples_per_second": 7.231,
82
+ "eval_steps_per_second": 3.616,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008943401047655552,
87
+ "grad_norm": 0.28511881828308105,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0939,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1725914073268224.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null