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
f567532
·
verified ·
1 Parent(s): 30687dd

Training in progress, step 1990, 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 sha256:32a17d54c73c50386a7ef2c6b84b22b0e73515dc2caa5da89ebe0822bde63784
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b5bf36f0c548c52be06638dc047363b39d90bb2d799135929c7106abf638e9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5f22d1d36fa98549e01a2085e25dc5b70e59fd6e42afc6b85e6f96322c32bf3
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66aff3a74d3dd7edeecfff67963519461d81324c06715585eb9b06ca343d67bd
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:e38fdf105eb0530e8f187df7fa9b2f9fb5ca585f11ab4ddc4ba194009ee6e145
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472e3772b9c33b9d08e9a6c07511578b569b63a6ae24bb15c89b125d2da2d5b8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a754c1e68bb45f21f63f5f86102687edeb189e2d8e644a7394ab0cb0d1f6668a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8596289c22926ea852bd3cd9fab93f8e9788496fc55c0e309b96c555c42502a1
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": 0.4224,
6
  "eval_steps": 500,
7
- "global_step": 1980,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1998,6 +1998,16 @@
1998
  "mean_token_accuracy": 0.7643323555588722,
1999
  "num_tokens": 9178671.0,
2000
  "step": 1980
 
 
 
 
 
 
 
 
 
 
2001
  }
2002
  ],
2003
  "logging_steps": 10,
@@ -2017,7 +2027,7 @@
2017
  "attributes": {}
2018
  }
2019
  },
2020
- "total_flos": 4.356944715993293e+16,
2021
  "train_batch_size": 4,
2022
  "trial_name": null,
2023
  "trial_params": null
 
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,
 
1998
  "mean_token_accuracy": 0.7643323555588722,
1999
  "num_tokens": 9178671.0,
2000
  "step": 1980
2001
+ },
2002
+ {
2003
+ "entropy": 0.9660324349999427,
2004
+ "epoch": 0.4245333333333333,
2005
+ "grad_norm": 0.35394829511642456,
2006
+ "learning_rate": 9.169567084993814e-05,
2007
+ "loss": 1.083635139465332,
2008
+ "mean_token_accuracy": 0.7617688804864884,
2009
+ "num_tokens": 9221289.0,
2010
+ "step": 1990
2011
  }
2012
  ],
2013
  "logging_steps": 10,
 
2027
  "attributes": {}
2028
  }
2029
  },
2030
+ "total_flos": 4.377669310378291e+16,
2031
  "train_batch_size": 4,
2032
  "trial_name": null,
2033
  "trial_params": null