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
befb9ab
·
verified ·
1 Parent(s): a5da5f7

Training in progress, step 1910, 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 sha256:1167122266955c58d336fcb3737918fa0cf2855602282a48b199fab96303200f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81f94115b4fbb58d7d4b85a773881137d29e95688723cc1fe5202c9ebda2842
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f45ebf44a3f5123453867e6e8568bc5d10af64ff07d0bbbf9e2808428710b5
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899980d7cfc2859cbf4f1c736d85bdfa7b0e2c4474c56b0cf4f51e29947a8bdf
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32a5528166168ffda74554ce3d9e46fbd51adb8f2e8a9328c3f66817bb311b54
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34328d093f4cca44bab210c4646c87c3492f38153ada8b43395eec4ccae09ec
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a50b6ada732039affb9dd5cc468ba0a686c56ff994976915da76196403c812f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f333dbe494d790dbcaa819d24bb8779c63089faf81bdccd0548679bf4a32c7
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": 0.4053333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1900,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1918,6 +1918,16 @@
1918
  "mean_token_accuracy": 0.7382492840290069,
1919
  "num_tokens": 8801703.0,
1920
  "step": 1900
 
 
 
 
 
 
 
 
 
 
1921
  }
1922
  ],
1923
  "logging_steps": 10,
@@ -1937,7 +1947,7 @@
1937
  "attributes": {}
1938
  }
1939
  },
1940
- "total_flos": 4.178739518938829e+16,
1941
  "train_batch_size": 4,
1942
  "trial_name": null,
1943
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.40746666666666664,
6
  "eval_steps": 500,
7
+ "global_step": 1910,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1918
  "mean_token_accuracy": 0.7382492840290069,
1919
  "num_tokens": 8801703.0,
1920
  "step": 1900
1921
+ },
1922
+ {
1923
+ "entropy": 0.8892258107662201,
1924
+ "epoch": 0.40746666666666664,
1925
+ "grad_norm": 0.2835586667060852,
1926
+ "learning_rate": 9.244372625047372e-05,
1927
+ "loss": 0.9624475479125977,
1928
+ "mean_token_accuracy": 0.7717373371124268,
1929
+ "num_tokens": 8848191.0,
1930
+ "step": 1910
1931
  }
1932
  ],
1933
  "logging_steps": 10,
 
1947
  "attributes": {}
1948
  }
1949
  },
1950
+ "total_flos": 4.200902407563878e+16,
1951
  "train_batch_size": 4,
1952
  "trial_name": null,
1953
  "trial_params": null