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
dcb655a
·
verified ·
1 Parent(s): 972223b

Training in progress, step 1860, 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 sha256:2d14e4e81715785f502234a9e6406a4be9cd1fa5ca64756605fb0577dd9d05a6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6425eeda19ba056ee2b342cda29d5c0bd62bb338add5362226aed1306b74a862
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9177642d339653b7b8829dd0da7791fbcd756a53d44d0cb9f53b61e73a259da
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622066bcb88b8bee80fb586cbff8d63c12b45207f4bd8a9555fd879998bc2c7a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89b395ed7d7a4710326416eb6e4392fdf90a56acd2ae5e2cf158847b83b2d399
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6900bdcd2a41c2c94e4c353bba1be97fd1f96ffaf529e7eb7f2b15dc3f32bb65
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0b30e37ce95972f97ae30ed4113e8141d4673871e5bbefc7061e0d0d9f62812
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3389e098396e0e90ec77ded90427ea77132ff66ec75ee7e8cc8afe1416926945
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": 0.39466666666666667,
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,
@@ -1868,6 +1868,16 @@
1868
  "mean_token_accuracy": 0.7662550717592239,
1869
  "num_tokens": 8579411.0,
1870
  "step": 1850
 
 
 
 
 
 
 
 
 
 
1871
  }
1872
  ],
1873
  "logging_steps": 10,
@@ -1887,7 +1897,7 @@
1887
  "attributes": {}
1888
  }
1889
  },
1890
- "total_flos": 4.074736246155878e+16,
1891
  "train_batch_size": 4,
1892
  "trial_name": null,
1893
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3968,
6
  "eval_steps": 500,
7
+ "global_step": 1860,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1868
  "mean_token_accuracy": 0.7662550717592239,
1869
  "num_tokens": 8579411.0,
1870
  "step": 1850
1871
+ },
1872
+ {
1873
+ "entropy": 0.820501434057951,
1874
+ "epoch": 0.3968,
1875
+ "grad_norm": 0.26821690797805786,
1876
+ "learning_rate": 9.289476978851976e-05,
1877
+ "loss": 0.8598980903625488,
1878
+ "mean_token_accuracy": 0.7888635769486427,
1879
+ "num_tokens": 8623046.0,
1880
+ "step": 1860
1881
  }
1882
  ],
1883
  "logging_steps": 10,
 
1897
  "attributes": {}
1898
  }
1899
  },
1900
+ "total_flos": 4.095164350061568e+16,
1901
  "train_batch_size": 4,
1902
  "trial_name": null,
1903
  "trial_params": null