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
7d5a60c
·
verified ·
1 Parent(s): 3100417

Training in progress, step 930, 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:a00af1438a0f904c703b2a0a9b91360fc9cf02a1afd861f7ac653278d5f692e1
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9370d4a1660342890864d081521326d0b1c08ac4168b9f77ade49762884eb07d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:744d3d74d3e89764ef707a6d808aff55cdd0c082b466e82063591be566be397f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39da0c3376ec3eb8c5321c6755ce3072c7cca9c19b0d846ca2ba8a328ac49e27
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7793f67a5ffc7c73f9bd638ac902d3a52494a9eb54bc6a053bd4759db7dadd1b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e0325e7dd87e2b8bd5537684a71b38bfd6e57f99a1dce395bf92dfbd401dee
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60462611dbafa72b0e44e437a106336f8704064ce3123087a96fe9be72c4580f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250973f40cff87a41eed57b5ef4bc2ed58c8b9161ad299c9abd9b1dc8f84a6ee
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": 0.19626666666666667,
6
  "eval_steps": 500,
7
- "global_step": 920,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -938,6 +938,16 @@
938
  "mean_token_accuracy": 0.7639905765652657,
939
  "num_tokens": 4291788.0,
940
  "step": 920
 
 
 
 
 
 
 
 
 
 
941
  }
942
  ],
943
  "logging_steps": 10,
@@ -957,7 +967,7 @@
957
  "attributes": {}
958
  }
959
  },
960
- "total_flos": 2.036894999972659e+16,
961
  "train_batch_size": 4,
962
  "trial_name": null,
963
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1984,
6
  "eval_steps": 500,
7
+ "global_step": 930,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
938
  "mean_token_accuracy": 0.7639905765652657,
939
  "num_tokens": 4291788.0,
940
  "step": 920
941
+ },
942
+ {
943
+ "entropy": 0.8939604975283146,
944
+ "epoch": 0.1984,
945
+ "grad_norm": 0.2963460087776184,
946
+ "learning_rate": 9.881958207465158e-05,
947
+ "loss": 0.9668001174926758,
948
+ "mean_token_accuracy": 0.778343915939331,
949
+ "num_tokens": 4336567.0,
950
+ "step": 930
951
  }
952
  ],
953
  "logging_steps": 10,
 
967
  "attributes": {}
968
  }
969
  },
970
+ "total_flos": 2.0570698703686656e+16,
971
  "train_batch_size": 4,
972
  "trial_name": null,
973
  "trial_params": null