baby-dev commited on
Commit
3aada91
·
verified ·
1 Parent(s): 0d38219

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7243e6d9f92f57ccc92a5e5a11449b180d0953cdfd694387bf9b423db4407d88
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361892f14c694a100c4aac6dad69c8ded813b87953862a3f6c736e224c125fbd
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaa02ae495268d33be2ba170ba7def7840b3b8fec78e9b5a576ee37a5d4540b0
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c117c2747202b9268eb661fa118bbc084616f23fef80f72f93fc2a89a734db2
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc38aba70c31a73a7fef153a0ca565ccbffcd60ca74b3f258e9cb2b75e2b81f5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:585dde8bd57899a42e658990a8ccd728e253e6befaed44d1cabfe387a9ca8070
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.004048582995951417,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 8.575,
74
  "eval_steps_per_second": 1.072,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.5312661952528384e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006072874493927126,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 8.575,
74
  "eval_steps_per_second": 1.072,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.004723346828609987,
79
+ "grad_norm": 2.649564266204834,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 3.1013,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.005398110661268556,
86
+ "grad_norm": 2.411900520324707,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 3.0944,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.006072874493927126,
93
+ "grad_norm": 2.7092297077178955,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 2.9518,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.006072874493927126,
100
+ "eval_loss": 0.7562000751495361,
101
+ "eval_runtime": 970.9794,
102
+ "eval_samples_per_second": 7.712,
103
+ "eval_steps_per_second": 0.964,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.796899292879258e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null