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
4ab37f3
·
verified ·
1 Parent(s): a421ac3

Training in progress, step 2000, 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 sha256:70b5bf36f0c548c52be06638dc047363b39d90bb2d799135929c7106abf638e9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e27c0323180173769ac19c24ccc858115ef66a00697f4ac2b8d6ba758cd3aa2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66aff3a74d3dd7edeecfff67963519461d81324c06715585eb9b06ca343d67bd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7baab09d9ca4ce2534ca0ac81f413e19364d0f53fa91defb0a43b3be4152c7
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:472e3772b9c33b9d08e9a6c07511578b569b63a6ae24bb15c89b125d2da2d5b8
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c31c7a9e073807f0bcbdd3865475a59db62e85533912972220623ae6274019b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8596289c22926ea852bd3cd9fab93f8e9788496fc55c0e309b96c555c42502a1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d973cb144de29338b3e08d2e2eced07863c8eda7f78a649e9a577059568d5b86
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": 0.4245333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1990,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2008,6 +2008,16 @@
2008
  "mean_token_accuracy": 0.7617688804864884,
2009
  "num_tokens": 9221289.0,
2010
  "step": 1990
 
 
 
 
 
 
 
 
 
 
2011
  }
2012
  ],
2013
  "logging_steps": 10,
@@ -2027,7 +2037,7 @@
2027
  "attributes": {}
2028
  }
2029
  },
2030
- "total_flos": 4.377669310378291e+16,
2031
  "train_batch_size": 4,
2032
  "trial_name": null,
2033
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4266666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 2000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2008
  "mean_token_accuracy": 0.7617688804864884,
2009
  "num_tokens": 9221289.0,
2010
  "step": 1990
2011
+ },
2012
+ {
2013
+ "entropy": 0.9027157455682755,
2014
+ "epoch": 0.4266666666666667,
2015
+ "grad_norm": 0.2674417495727539,
2016
+ "learning_rate": 9.159990394378303e-05,
2017
+ "loss": 0.980889892578125,
2018
+ "mean_token_accuracy": 0.7698795303702355,
2019
+ "num_tokens": 9268892.0,
2020
+ "step": 2000
2021
  }
2022
  ],
2023
  "logging_steps": 10,
 
2037
  "attributes": {}
2038
  }
2039
  },
2040
+ "total_flos": 4.400473844052787e+16,
2041
  "train_batch_size": 4,
2042
  "trial_name": null,
2043
  "trial_params": null