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
2c120f4
·
verified ·
1 Parent(s): f98d905

Training in progress, step 1850, 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 sha256:8e6cd8094f1a9b275409b5e29dac6e5547d58a69f4c0e092f1df2f9b50f2114f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d14e4e81715785f502234a9e6406a4be9cd1fa5ca64756605fb0577dd9d05a6
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f024aacb386f38059a5d0449e8f47d95088bc37603ee6b9a9629e282bc9fce2b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9177642d339653b7b8829dd0da7791fbcd756a53d44d0cb9f53b61e73a259da
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:660d66769a25b90f8566fd916c316b9b0e244ffce7b25945b65ffcad1af3e768
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b395ed7d7a4710326416eb6e4392fdf90a56acd2ae5e2cf158847b83b2d399
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e44eaba2f1ebd92046727db70164f55edfc1880cb2e3a6c0bc0862f469502aa6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b30e37ce95972f97ae30ed4113e8141d4673871e5bbefc7061e0d0d9f62812
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": 0.39253333333333335,
6
  "eval_steps": 500,
7
- "global_step": 1840,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1858,6 +1858,16 @@
1858
  "mean_token_accuracy": 0.773698341846466,
1859
  "num_tokens": 8533216.0,
1860
  "step": 1840
 
 
 
 
 
 
 
 
 
 
1861
  }
1862
  ],
1863
  "logging_steps": 10,
@@ -1877,7 +1887,7 @@
1877
  "attributes": {}
1878
  }
1879
  },
1880
- "total_flos": 4.053352884170957e+16,
1881
  "train_batch_size": 4,
1882
  "trial_name": null,
1883
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.39466666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 1850,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1858
  "mean_token_accuracy": 0.773698341846466,
1859
  "num_tokens": 8533216.0,
1860
  "step": 1840
1861
+ },
1862
+ {
1863
+ "entropy": 0.9542841285467147,
1864
+ "epoch": 0.39466666666666667,
1865
+ "grad_norm": 0.3648325800895691,
1866
+ "learning_rate": 9.298344096080776e-05,
1867
+ "loss": 1.0262937545776367,
1868
+ "mean_token_accuracy": 0.7662550717592239,
1869
+ "num_tokens": 8579411.0,
1870
+ "step": 1850
1871
  }
1872
  ],
1873
  "logging_steps": 10,
 
1887
  "attributes": {}
1888
  }
1889
  },
1890
+ "total_flos": 4.074736246155878e+16,
1891
  "train_batch_size": 4,
1892
  "trial_name": null,
1893
  "trial_params": null