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
f81bcf6
·
verified ·
1 Parent(s): eb643f5

Training in progress, step 1920, 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:a81f94115b4fbb58d7d4b85a773881137d29e95688723cc1fe5202c9ebda2842
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351ef9c89739c3854aa4b522324985faaba838af2f3148ea3dfb0ba174fd2611
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:899980d7cfc2859cbf4f1c736d85bdfa7b0e2c4474c56b0cf4f51e29947a8bdf
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd99b8f7f37112533a36f1ff0eb5d240e2d8a8090f93856282a552682bf2d441
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:a34328d093f4cca44bab210c4646c87c3492f38153ada8b43395eec4ccae09ec
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36b03ac5c18a852f47b85eb361537889c7a52bee6f195ef044faaf9c24cb6c1
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45f333dbe494d790dbcaa819d24bb8779c63089faf81bdccd0548679bf4a32c7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9420597fe7100493a28305492d3dedf60c335e59ed12d963a7b8a1acd0370515
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": 0.40746666666666664,
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,
@@ -1928,6 +1928,16 @@
1928
  "mean_token_accuracy": 0.7717373371124268,
1929
  "num_tokens": 8848191.0,
1930
  "step": 1910
 
 
 
 
 
 
 
 
 
 
1931
  }
1932
  ],
1933
  "logging_steps": 10,
@@ -1947,7 +1957,7 @@
1947
  "attributes": {}
1948
  }
1949
  },
1950
- "total_flos": 4.200902407563878e+16,
1951
  "train_batch_size": 4,
1952
  "trial_name": null,
1953
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4096,
6
  "eval_steps": 500,
7
+ "global_step": 1920,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1928
  "mean_token_accuracy": 0.7717373371124268,
1929
  "num_tokens": 8848191.0,
1930
  "step": 1910
1931
+ },
1932
+ {
1933
+ "entropy": 0.9389666721224785,
1934
+ "epoch": 0.4096,
1935
+ "grad_norm": 0.2468794584274292,
1936
+ "learning_rate": 9.235198757339594e-05,
1937
+ "loss": 1.0801708221435546,
1938
+ "mean_token_accuracy": 0.7686146914958953,
1939
+ "num_tokens": 8895860.0,
1940
+ "step": 1920
1941
  }
1942
  ],
1943
  "logging_steps": 10,
 
1957
  "attributes": {}
1958
  }
1959
  },
1960
+ "total_flos": 4.221765784726426e+16,
1961
  "train_batch_size": 4,
1962
  "trial_name": null,
1963
  "trial_params": null