daniel40 commited on
Commit
7413e86
·
verified ·
1 Parent(s): d0e4874

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 sha256:6a7c81c77420cfbd92d1f3022557f2b84e3dd9da6dbb6f379821f8471584e46a
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91ec364e240ac1cd5ee2e90d34420d7a75b90e163b6ef1df9632bc7718d8432
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4c1b410d2b144ed78205e054d30e89f12c15d94c54f841b9375141ec8296ab1
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8d3c07f90eb380f5f130d77d5b1da7db51eb0d69d918f9997977a8fda141db
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c3b386391a624b1bd584d01969e845897c710c297088eab7a1800fd97b3f3de
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d19bc63f2e461b259ea29712943b7f82b3b557c494d13d97c480a3eab868a91
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
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": 0.01628052598622417,
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": 56.759,
61
  "eval_steps_per_second": 28.408,
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": 365056471597056.0,
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": 0.02087246921310791,
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": 56.759,
61
  "eval_steps_per_second": 28.408,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.01669797537048633,
66
+ "grad_norm": 1.118395447731018,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 2.8748,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.02087246921310791,
73
+ "grad_norm": 1.456959843635559,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.8124,
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": 467450359971840.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null