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
e1db3ef
·
verified ·
1 Parent(s): 396f4fb

Training in progress, step 3830, 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 sha256:0e8d3c64f27e5934306a440b80eaed49a4463262c226901c25bee30fc256892a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d69eacbb2f7117566a906f72be964ad8232e118d260c4d4f6dc65268da53b8
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4420e2117afcddadbea17196298170e4eb4c670916004727ffb5145c0682f26
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf16fcd679e2b6a523452aa551fa8ac67e2743efa5e80eee82568d9fa0b8782
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc8be5c2da0f9bfa384a3ddb4ea4604704f26d5d49706f2b90287cd26ed0bcb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6feb2759bca0e327b4d2bf4dac4280a1cdd2e253d40ea6c3d1d38efff607ab
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a08d6d83a98406c987328d0f90adfc90549eef5ad60ac4dff5af09d3535d3f1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492633a0e689414f8b596d271b8f83db32739ab33c218ebbb5fa0743993f69de
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": 0.8149333333333333,
6
  "eval_steps": 500,
7
- "global_step": 3820,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3838,6 +3838,16 @@
3838
  "mean_token_accuracy": 0.7579805940389633,
3839
  "num_tokens": 17796312.0,
3840
  "step": 3820
 
 
 
 
 
 
 
 
 
 
3841
  }
3842
  ],
3843
  "logging_steps": 10,
@@ -3857,7 +3867,7 @@
3857
  "attributes": {}
3858
  }
3859
  },
3860
- "total_flos": 8.427403028090573e+16,
3861
  "train_batch_size": 4,
3862
  "trial_name": null,
3863
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8170666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3830,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3838
  "mean_token_accuracy": 0.7579805940389633,
3839
  "num_tokens": 17796312.0,
3840
  "step": 3820
3841
+ },
3842
+ {
3843
+ "entropy": 1.0881080597639083,
3844
+ "epoch": 0.8170666666666667,
3845
+ "grad_norm": 0.2615782618522644,
3846
+ "learning_rate": 6.711004206939491e-05,
3847
+ "loss": 1.20444917678833,
3848
+ "mean_token_accuracy": 0.7393553704023361,
3849
+ "num_tokens": 17849058.0,
3850
+ "step": 3830
3851
  }
3852
  ],
3853
  "logging_steps": 10,
 
3867
  "attributes": {}
3868
  }
3869
  },
3870
+ "total_flos": 8.453106679916851e+16,
3871
  "train_batch_size": 4,
3872
  "trial_name": null,
3873
  "trial_params": null