havinash-ai commited on
Commit
4e53eef
·
verified ·
1 Parent(s): ee24b31

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:db4678d3ec36b226f7676de435ab5b814f5c5cd0bc604a1cde401a0c425d9d39
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c5429d6874773a34eed403bd94d15cbf2781047b24dc205abd2d2024607a2e
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2393bad26da4eff2fa5e6624070bc6b3303cf8500e86bea177e7d4de5c450e4
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d75b6b6d59377ad2c17e7e6fcf1b38fecb3b222698bebf6c2bfc14425ccacb
3
  size 132798
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": 0.0016453960552684317,
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": 495.201,
61
  "eval_steps_per_second": 247.6,
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": 18249154560.0,
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": 0.002109482122139015,
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": 495.201,
61
  "eval_steps_per_second": 247.6,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0016875856977112118,
66
+ "grad_norm": 1.9517555236816406,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 21.574,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.002109482122139015,
73
+ "grad_norm": 2.224480628967285,
74
+ "learning_rate": 0.0,
75
+ "loss": 21.5531,
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": 23396352000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null