kk-aivio commited on
Commit
d86383a
·
verified ·
1 Parent(s): f8edf22

Training in progress, step 50, 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:e5b682cee1c451a3bf60d2601fbfbc821373b1a710b8bce9fb575c73fc003f97
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c5831a467d1631b7b9ed08c6a92b2ca0e86a34828ddcea9e6273293ef36673
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b93a715b51800628ff90e70bc504b4de6888790dd31d21480cec72880dd4c9e
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413a4d5b8c4703c4b113459d0b5a154cf572e7f59160d495c2130753df52d161
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87f6818e20cc9e76942bb297832aa97a7e1564142c6665faa43595cea48f6db9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698ab5d20cd19cec2e5427c05f3f6a203a61371f5373dc7797e9372f4e4d15c7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.019809523809523808,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 20.425,
61
  "eval_steps_per_second": 10.225,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 8004335107571712.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.025396825396825397,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 20.425,
61
  "eval_steps_per_second": 10.225,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.020317460317460317,
66
+ "grad_norm": 0.08451275527477264,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.0119,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.025396825396825397,
73
+ "grad_norm": 0.3084169328212738,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.0131,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.02619680866304e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null