duyphu commited on
Commit
51790f2
·
verified ·
1 Parent(s): 8f64ecb

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 sha256:5484f6a37c929676dfab8471ce2f041a01185b89c93ccc9144bf19ef498f0a98
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d84f1c2f7ab55072f583ce9846ae3d8f8d70f3c34dca76b765afef4412f88b
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d38fbdf19c59bd27edc905800e4bf31666c81c597033baecdbd3dd3622e36829
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8a57106ed099a68fae39c320a8af1f56af4101aa27d88394fca7394b2f2502
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14cec7f4f18b52eb460be52233bf05963f4735806cd9aa709a7d48b79f32e846
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035fb21ad9439c20703c98781225d585364cea97e05e48374824cfdb1d700cc5
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": 0.0002788599988738346,
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": 1.5635,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1826272994918400.0,
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": 0.00041828999831075196,
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": 1.5635,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00032176153716211687,
72
+ "grad_norm": 4.269238471984863,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0313,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00032176153716211687,
79
+ "eval_loss": 1.0572291612625122,
80
+ "eval_runtime": 1676.2677,
81
+ "eval_samples_per_second": 23.42,
82
+ "eval_steps_per_second": 11.71,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0003753884600224697,
87
+ "grad_norm": 4.948161602020264,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8191,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2730712954306560.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null