tuanna08go commited on
Commit
8f9cb83
·
verified ·
1 Parent(s): cf7e3b1

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 sha256:1167b57fed182f15d4bbd85b0ce88a9c4ab0af27a20a49de9462aae19e27af67
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7993f88f7251226c437872b38bacf0801d0125b0634ca83caafa4f54c9bb919
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c3ed218ecb30f64eb865d4296abb5e7b76ff019ef92f640f08ea52859aff9d
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0331c090d5012246a3c1d051654f29d1c63adb1e659c8db8199d80c62ea81e7e
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be7005cc3fc15acfdf82dddf063b2d2565e65e391024dc8176c777dcd11198a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
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": 0.031746031746031744,
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": 11.933,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3072196608.0,
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": 0.047619047619047616,
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": 11.933,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03663003663003663,
72
+ "grad_norm": 0.017171213403344154,
73
+ "learning_rate": 5e-05,
74
+ "loss": 11.9326,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03663003663003663,
79
+ "eval_loss": 11.934120178222656,
80
+ "eval_runtime": 6.1064,
81
+ "eval_samples_per_second": 56.498,
82
+ "eval_steps_per_second": 28.331,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.042735042735042736,
87
+ "grad_norm": 0.009910144843161106,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 11.9316,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4608294912.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null