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
bfb53e7
·
verified ·
1 Parent(s): 65ab7c9

Training in progress, step 1980, 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:dd804cdd81770152b3d7177dff6d991c1421b876c0e1dd1f85de893bc31b3815
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a17d54c73c50386a7ef2c6b84b22b0e73515dc2caa5da89ebe0822bde63784
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcbdfedc6733d5976b7dcfb074961ff1cf954506d4c206597b7fc67a84d75f2
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f22d1d36fa98549e01a2085e25dc5b70e59fd6e42afc6b85e6f96322c32bf3
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:cd865cb8212842e7dbc68c1c29d3d05cec68d0c1e280a37c46234002777acbe2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38fdf105eb0530e8f187df7fa9b2f9fb5ca585f11ab4ddc4ba194009ee6e145
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32bb471a796601b246ca30ed6a8dcc726b36b2b6891d11b7f34267b43df43a3c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a754c1e68bb45f21f63f5f86102687edeb189e2d8e644a7394ab0cb0d1f6668a
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": 0.4202666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1970,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1988,6 +1988,16 @@
1988
  "mean_token_accuracy": 0.7659218199551105,
1989
  "num_tokens": 9133717.0,
1990
  "step": 1970
 
 
 
 
 
 
 
 
 
 
1991
  }
1992
  ],
1993
  "logging_steps": 10,
@@ -2007,7 +2017,7 @@
2007
  "attributes": {}
2008
  }
2009
  },
2010
- "total_flos": 4.335691124917248e+16,
2011
  "train_batch_size": 4,
2012
  "trial_name": null,
2013
  "trial_params": null
 
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,
 
1988
  "mean_token_accuracy": 0.7659218199551105,
1989
  "num_tokens": 9133717.0,
1990
  "step": 1970
1991
+ },
1992
+ {
1993
+ "entropy": 0.9707967802882195,
1994
+ "epoch": 0.4224,
1995
+ "grad_norm": 0.2167668491601944,
1996
+ "learning_rate": 9.179093818039616e-05,
1997
+ "loss": 1.077283763885498,
1998
+ "mean_token_accuracy": 0.7643323555588722,
1999
+ "num_tokens": 9178671.0,
2000
+ "step": 1980
2001
  }
2002
  ],
2003
  "logging_steps": 10,
 
2017
  "attributes": {}
2018
  }
2019
  },
2020
+ "total_flos": 4.356944715993293e+16,
2021
  "train_batch_size": 4,
2022
  "trial_name": null,
2023
  "trial_params": null