Best000 commited on
Commit
6cf653c
·
verified ·
1 Parent(s): fdb3b26

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:ccdb82ef1146f45ba8e9ced6192791388f4ca4602f1c3c73a994bd748687d7db
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8bd81f873b65ff28777e0da8a8d642a0056b37ed912cd506cfdba393ee6bdd
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19d59d47e07884e8eeebe11442889f5d0986c011d5f5267405db57d17643235d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf3cc942af63c9fd5f499626f33f2d797245f865c51c60577a551b30bba2193
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a24f5c78a7012dd23de4209f4d948d02b5774ea41a127640d01e22567f3f95
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09076676c8446571f934169ff1b1fe0aafa35283f609e8d595a025f9b64bdcc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
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": 0.005567849239774431,
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": 14.491,
61
  "eval_steps_per_second": 7.246,
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": 1.3627007585746944e+16,
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": 0.007138268256121065,
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": 14.491,
61
  "eval_steps_per_second": 7.246,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.005710614604896852,
66
+ "grad_norm": 3.236527681350708,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 2.1878,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.007138268256121065,
73
+ "grad_norm": 3.5043814182281494,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.2447,
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": 1.7482881114832896e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null