philip-hightech commited on
Commit
478fd1d
·
verified ·
1 Parent(s): d537fe1

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 sha256:977f5515b24fd4773e963e5b00c435872a835229bacbdd6f31c8fe7eec3d37e6
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fef0ee79c14a6b7dabb523821659d5f660f33e7f2d3124ab150b06a3d9c0dcb
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a45793e133b232b79ce6df7b621210a1c8aa9a82feb2293bd3778c9edd413ae5
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bda637e0cc7c14d35ec2cfd4f26ce5fdaf9d43cfdbd4663583068307d980de5
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35cb217a47db1d6f9723ef9f93fc20fd98f2a90bb18bbc1bd2dc009ce7974ae9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e65517f2c0511f864fd875c55d2ba62383f8072dbd3fa7389b0f61668c68f3
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": 0.021294021294021293,
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": 10.553,
61
  "eval_steps_per_second": 5.276,
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": 1.255815663058944e+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": 0.0273000273000273,
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": 10.553,
61
  "eval_steps_per_second": 5.276,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.02184002184002184,
66
+ "grad_norm": 0.541061520576477,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.0321,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0273000273000273,
73
+ "grad_norm": 0.4552432894706726,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.0263,
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": 1.6100200808448e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null