shibajustfor commited on
Commit
a1ba798
·
verified ·
1 Parent(s): 83dad87

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 sha256:0586490fbc5484ba43050565017deddd8704367fc684c7a306ad6f14d93cdf2f
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b74b0fb782ddcf9a7a9c51342ed9400c963b736598001b38798752384898511
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ed578e7732f37ad703f496165158d88ee261835da675f8baf4b0a2da61999e
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b29623d9bb6e623df8a4ca698c15de87565ba8930f1ca3cc21b85f5c983d1ca
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:413c2acc7eea6176a73d0cbe494456450e343301052fed2289eb3a7b9b3d8b3f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a736b8495f78c5678865edcb6dc1d3367e2dfdc9ff024a518bbb29b87f23bfd1
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": 0.0007848622214619568,
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": 24.029,
61
  "eval_steps_per_second": 12.015,
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": 9029906941870080.0,
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": 0.001006233617258919,
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": 24.029,
61
  "eval_steps_per_second": 12.015,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0008049868938071352,
66
+ "grad_norm": 1.0334351062774658,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.3029,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.001006233617258919,
73
+ "grad_norm": 0.8946134448051453,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.3841,
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": 1.180098949545984e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null