shibajustfor commited on
Commit
3fa133a
·
verified ·
1 Parent(s): d049384

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:d5ca847cad4011cb1ca4916d8094691331875044484feee92a7eaedbcb25b406
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749cc22085ec0d46ba7958d51916a890d99c2304293853932329275178e535ba
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:833e79eeba36bdf93b1dbd6bfc041c9150fcfbbe9202f81f010bd5efddef630c
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375d65048c0636657644f53ecf2f9a66d5d0ea49537c74e2cdc6628ba72e1de4
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6772af577974c8afd4f01c292dee37aefb71155f4658c2cd442b9995c16c293
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f193d721d2c78b566d69bf5206148a72d855b794e4169c7dc96a973de157ed62
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": 0.0161976949434119,
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": 17.667,
61
  "eval_steps_per_second": 8.834,
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": 1.285301880225792e+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": 0.020766275568476794,
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": 17.667,
61
  "eval_steps_per_second": 8.834,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.016613020454781434,
66
+ "grad_norm": 0.26189422607421875,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.5679,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.020766275568476794,
73
+ "grad_norm": 0.269429087638855,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.5731,
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": 1.6478229233664e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null