adammandic87 commited on
Commit
5f82a36
·
verified ·
1 Parent(s): 50a21b7

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:ba5463159dfad1a43ff267afe32efb8d7299bde7a1c59ca716419936b073a35e
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522845da8138a215cdcd362977930b9ce3b36205a17cd0c433382dab7ef617e6
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:068a81d1f0a3d8d7d3bb874b66741956962a9eba5bad54301452a1daf10a6320
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f0a9fbfd34ef4860b457772d54ab463cab7bc3532c6aec01bfff0c8276a21c
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:a7bd3a2b2a125c6511b78d0dc07c1ed31cb5a5a60683f3a79a6f47417c703809
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1959a365c85a21fc6a5fdf21ef24263291b5c3acc088bea7043daa22260b8dd3
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": 0.0013657733691702927,
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": 19.768,
61
  "eval_steps_per_second": 9.884,
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": 1.140113195139072e+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": 0.0017509914989362726,
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": 19.768,
61
  "eval_steps_per_second": 9.884,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.001400793199149018,
66
+ "grad_norm": 8.291387557983398,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 12.1025,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0017509914989362726,
73
+ "grad_norm": 12.42542552947998,
74
+ "learning_rate": 0.0,
75
+ "loss": 12.1001,
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": 1.445500658122752e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null