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
14c7d46
·
verified ·
1 Parent(s): ea0ba10

Training in progress, step 3840, 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 sha256:47d69eacbb2f7117566a906f72be964ad8232e118d260c4d4f6dc65268da53b8
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c3555d272a933f68efe3eaba53d3e0df1624c54947e82fb2a150c8c3813e2d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cf16fcd679e2b6a523452aa551fa8ac67e2743efa5e80eee82568d9fa0b8782
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2926b6c208dc17ab7c10182d7305c3a23a95e4e128f05c39b4bc189f7651db9
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:cb6feb2759bca0e327b4d2bf4dac4280a1cdd2e253d40ea6c3d1d38efff607ab
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fea74e750e7c609ae9b74d03b5105eeb14b7cbb46fd360294f7a61b7f2a22fd
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:492633a0e689414f8b596d271b8f83db32739ab33c218ebbb5fa0743993f69de
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc3415032184dfc5f2abc53aef32b24c4d9a6120b3e02c5cbebf000e4f77d6e
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": 0.8170666666666667,
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,
@@ -3848,6 +3848,16 @@
3848
  "mean_token_accuracy": 0.7393553704023361,
3849
  "num_tokens": 17849058.0,
3850
  "step": 3830
 
 
 
 
 
 
 
 
 
 
3851
  }
3852
  ],
3853
  "logging_steps": 10,
@@ -3867,7 +3877,7 @@
3867
  "attributes": {}
3868
  }
3869
  },
3870
- "total_flos": 8.453106679916851e+16,
3871
  "train_batch_size": 4,
3872
  "trial_name": null,
3873
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8192,
6
  "eval_steps": 500,
7
+ "global_step": 3840,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3848
  "mean_token_accuracy": 0.7393553704023361,
3849
  "num_tokens": 17849058.0,
3850
  "step": 3830
3851
+ },
3852
+ {
3853
+ "entropy": 0.9971455112099648,
3854
+ "epoch": 0.8192,
3855
+ "grad_norm": 0.28769299387931824,
3856
+ "learning_rate": 6.694731732989593e-05,
3857
+ "loss": 1.186737632751465,
3858
+ "mean_token_accuracy": 0.7578480765223503,
3859
+ "num_tokens": 17897760.0,
3860
+ "step": 3840
3861
  }
3862
  ],
3863
  "logging_steps": 10,
 
3877
  "attributes": {}
3878
  }
3879
  },
3880
+ "total_flos": 8.475827403212698e+16,
3881
  "train_batch_size": 4,
3882
  "trial_name": null,
3883
  "trial_params": null