nathanialhunt commited on
Commit
451b799
·
verified ·
1 Parent(s): 4d4bdf5

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8da1cf43ee78482988af07513f41be8a0a8eab59a18e306ec2a6703f4a10f6c0
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33057875abb29ae5d3c11ddcf64947ff837922447bc070524bbac00979cb7f3
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c53c924155acd316b092ebe16f4a2d648f58295ce12dec7b7d87803fea54e1fe
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebed078aea5db4fb6605600851ab09c5cb01cf45fe95f2b026da8c9b3d124108
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.0021938614070245756,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 492.99,
46
  "eval_steps_per_second": 246.495,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 19424870400.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0032907921105368634,
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,
 
45
  "eval_samples_per_second": 492.99,
46
  "eval_steps_per_second": 246.495,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0025313785465668178,
51
+ "grad_norm": 3.7027828693389893,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 43.8833,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0032907921105368634,
58
+ "eval_loss": 10.918169021606445,
59
+ "eval_runtime": 10.1682,
60
+ "eval_samples_per_second": 490.744,
61
+ "eval_steps_per_second": 245.372,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 29137305600.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null