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
4d5770f
·
verified ·
1 Parent(s): 4b455b9

Training in progress, step 3930, 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 sha256:31bc93060aa1184b691124bc90c3e818b4bbd4ceef85e3743663db1a5501317d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d6628a0a9ebc5fb9e787f038279e83ed49aa583cda589cc7c63927dac130b2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ac11df89d5d5087ab54baed219bece04e40d4301762cc8cc572077525586373
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1890040fb958f00a1df37cb90a43f25a71e1e74f57666f4b1725e637e4fc0a03
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53766f1a435dd67babc209d7d3d785f039bc193286ba9f0d6820ca9248374731
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2481cdc139d16df566c9adcd5c6e4698e1ef15b2833bb88ed6b80eabe6cb5d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcbd0568a27645a5c5a0dce738eb2c9e393d0b3f97651ba1f9a6650098876f4f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa40628ff063e87b5889119abe99589f14832e66da2bb2f69a1347789bbddd85
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": 0.8362666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3920,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3938,6 +3938,16 @@
3938
  "mean_token_accuracy": 0.7563267104327679,
3939
  "num_tokens": 18270937.0,
3940
  "step": 3920
 
 
 
 
 
 
 
 
 
 
3941
  }
3942
  ],
3943
  "logging_steps": 10,
@@ -3957,7 +3967,7 @@
3957
  "attributes": {}
3958
  }
3959
  },
3960
- "total_flos": 8.650172816914944e+16,
3961
  "train_batch_size": 4,
3962
  "trial_name": null,
3963
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8384,
6
  "eval_steps": 500,
7
+ "global_step": 3930,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3938
  "mean_token_accuracy": 0.7563267104327679,
3939
  "num_tokens": 18270937.0,
3940
  "step": 3920
3941
+ },
3942
+ {
3943
+ "entropy": 0.9336299523711205,
3944
+ "epoch": 0.8384,
3945
+ "grad_norm": 0.25351837277412415,
3946
+ "learning_rate": 6.547389200362103e-05,
3947
+ "loss": 1.0218440055847169,
3948
+ "mean_token_accuracy": 0.767199169844389,
3949
+ "num_tokens": 18314733.0,
3950
+ "step": 3930
3951
  }
3952
  ],
3953
  "logging_steps": 10,
 
3967
  "attributes": {}
3968
  }
3969
  },
3970
+ "total_flos": 8.67109116647639e+16,
3971
  "train_batch_size": 4,
3972
  "trial_name": null,
3973
  "trial_params": null