philip-hightech commited on
Commit
14e228d
·
verified ·
1 Parent(s): 9b98516

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 sha256:5f6ff963c388b99d21b79179824bde68834d098da93137bf799c01dfdbfc9aec
3
  size 247936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abbbced45747a7b3aa608bfc304dbcf32ec6e4395dd04da77ea100086bc9e398
3
  size 247936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0657cbf91bf5b946d44c1d9a6be489c842c96fa449ca508bae5727c7f3c20e5
3
  size 263024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b32172cf11fd24b9fa3c34931646cb341d682f88bf9898bd5b75ebe2e8e22c
3
  size 263024
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
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": 0.00497893527384144,
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": 498.353,
61
  "eval_steps_per_second": 249.328,
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": 40332165120.0,
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": 0.006383250351078769,
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": 498.353,
61
  "eval_steps_per_second": 249.328,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.005106600280863015,
66
+ "grad_norm": 0.9809399843215942,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 22.1118,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.006383250351078769,
73
+ "grad_norm": 1.0434082746505737,
74
+ "learning_rate": 0.0,
75
+ "loss": 22.0948,
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": 51707904000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null