chauhoang commited on
Commit
0a1c7f9
·
verified ·
1 Parent(s): 6c65e3b

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 sha256:536a2db40947885db5bf9939f158205f8c46a50508b2bdd36f1ed245f8262c50
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8db441a0c0d21810ce6d0706918c9201f1982719953abef7eab948e367d5ed6
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a82134c5cbbbc13a2981ee8253f5766698b00b94248832958a6460cd2a2703bb
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0f28a80d5b1b8e808bdcbd449cf3cd4ae69d71afbfcebc141ae310dca05284
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": 0.008638591245120026,
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": 0.8331,
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": 0.01295788686768004,
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": 0.8331,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0099676052828308,
72
+ "grad_norm": 0.9234360456466675,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7435,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0099676052828308,
79
+ "eval_loss": 0.7390913963317871,
80
+ "eval_runtime": 69.6251,
81
+ "eval_samples_per_second": 18.212,
82
+ "eval_steps_per_second": 9.106,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.011628872829969267,
87
+ "grad_norm": 0.9415158629417419,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7966,
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