Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
260cbe8
·
verified ·
1 Parent(s): 10f9f5f

Training in progress, step 1730, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbde674517b939ef2df8342ec846b5dce1684cf9c0d2f85245a61a6bd0e2abb6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a6ad4f9c2aedea7ef0ce1277e8ee175d0714e52ecce8c78d6ef1ee7a6d920d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2449dcfb481a5381fbcd669fa9679935a88b5436a40569e9f0b77a16ecdb754
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed46718e9bc461b034c4ae6fc2f3b28ff26b6f03fec6979f1ea03d1a4dd46627
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1f64fac85f8a96a4b988ed0d818505c4aa3a89f1cdad1b179c915435773b54
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f69827a8531f011e3a7ae14ebe8eaf52e6656f83a6d95d4946c4798f4e1c5a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50beea14553facb781039ba99dd206ef3d17f4788ad7b84d15561314d737a621
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f025b7a35a2fa800fe18e0083eb1b988995df608e432283222f76c9cbfde0b07
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.36693333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1720,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1738,6 +1738,16 @@
1738
  "mean_token_accuracy": 0.7556669354438782,
1739
  "num_tokens": 7981235.0,
1740
  "step": 1720
 
 
 
 
 
 
 
 
 
 
1741
  }
1742
  ],
1743
  "logging_steps": 10,
@@ -1757,7 +1767,7 @@
1757
  "attributes": {}
1758
  }
1759
  },
1760
- "total_flos": 3.786099610394726e+16,
1761
  "train_batch_size": 4,
1762
  "trial_name": null,
1763
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.36906666666666665,
6
  "eval_steps": 500,
7
+ "global_step": 1730,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1738
  "mean_token_accuracy": 0.7556669354438782,
1739
  "num_tokens": 7981235.0,
1740
  "step": 1720
1741
+ },
1742
+ {
1743
+ "entropy": 0.9596796780824661,
1744
+ "epoch": 0.36906666666666665,
1745
+ "grad_norm": 0.24347490072250366,
1746
+ "learning_rate": 9.40070269837891e-05,
1747
+ "loss": 1.058722686767578,
1748
+ "mean_token_accuracy": 0.7606610782444477,
1749
+ "num_tokens": 8028778.0,
1750
+ "step": 1730
1751
  }
1752
  ],
1753
  "logging_steps": 10,
 
1767
  "attributes": {}
1768
  }
1769
  },
1770
+ "total_flos": 3.810022516971418e+16,
1771
  "train_batch_size": 4,
1772
  "trial_name": null,
1773
  "trial_params": null