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
c84232c
·
verified ·
1 Parent(s): 9d99d42

Training in progress, step 890, 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 sha256:2a89201e2981c3443e4690a2b08cdbb901b7cbf35b56a2251f389bdca44adfb9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aae7b0cce6aad56e5bde54756da6dd3d7d41fb4c6a8f7362f5a628cf74f9a05
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4fd8a0f4ce699737bf6a62e9fae62ede5d935346488525d3b70889f69e3be62
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbbfafc5d8111633e73757ab081578b308c2ef4cd87aafa81ee5243e893ce10e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95a5b399ec19b0ca4e18f925ddb3741df1a49a5fa34b3dca1198ca2d343e4cf0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be634b03f4d3c1157659edea58ce8ca3436a72ff55ac4eefcb0a21ec3a808d0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99c456df62378afb46dea59259d93eb8a7b5767c6590640903dc8ecd47bb7fb3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ece7eafbf9f3bfc99587ae73cdce5c8bbed9e3959157297dca0de38318de9e
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": 0.18773333333333334,
6
  "eval_steps": 500,
7
- "global_step": 880,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -898,6 +898,16 @@
898
  "mean_token_accuracy": 0.7438870698213578,
899
  "num_tokens": 4099181.0,
900
  "step": 880
 
 
 
 
 
 
 
 
 
 
901
  }
902
  ],
903
  "logging_steps": 10,
@@ -917,7 +927,7 @@
917
  "attributes": {}
918
  }
919
  },
920
- "total_flos": 1.9434887835611136e+16,
921
  "train_batch_size": 4,
922
  "trial_name": null,
923
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.18986666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 890,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
898
  "mean_token_accuracy": 0.7438870698213578,
899
  "num_tokens": 4099181.0,
900
  "step": 880
901
+ },
902
+ {
903
+ "entropy": 1.0237427443265914,
904
+ "epoch": 0.18986666666666666,
905
+ "grad_norm": 0.251798152923584,
906
+ "learning_rate": 9.896443702796573e-05,
907
+ "loss": 1.1016413688659668,
908
+ "mean_token_accuracy": 0.7469503089785576,
909
+ "num_tokens": 4143951.0,
910
+ "step": 890
911
  }
912
  ],
913
  "logging_steps": 10,
 
927
  "attributes": {}
928
  }
929
  },
930
+ "total_flos": 1.965345268651315e+16,
931
  "train_batch_size": 4,
932
  "trial_name": null,
933
  "trial_params": null