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
4c20678
·
verified ·
1 Parent(s): 874450d

Training in progress, step 1970, 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:ebbae0f0867475b8a7f9335bb2f9f044d3aa5699f0d45c4f102be3f38251975d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd804cdd81770152b3d7177dff6d991c1421b876c0e1dd1f85de893bc31b3815
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6d3afcbf9f263042330c77d242154f5c3d73cc2e38e06131d797d8bad84fad0
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcbdfedc6733d5976b7dcfb074961ff1cf954506d4c206597b7fc67a84d75f2
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68d524ad371b2644db9c062ec3cdcd458f039156f9cddc00cfb9d4b3e22962fe
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd865cb8212842e7dbc68c1c29d3d05cec68d0c1e280a37c46234002777acbe2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef00cdc61ae10b88377c2844fd6923057cb361d7ff885b050e7e9f4d7086e26a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32bb471a796601b246ca30ed6a8dcc726b36b2b6891d11b7f34267b43df43a3c
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": 0.41813333333333336,
6
  "eval_steps": 500,
7
- "global_step": 1960,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1978,6 +1978,16 @@
1978
  "mean_token_accuracy": 0.7426734983921051,
1979
  "num_tokens": 9088894.0,
1980
  "step": 1960
 
 
 
 
 
 
 
 
 
 
1981
  }
1982
  ],
1983
  "logging_steps": 10,
@@ -1997,7 +2007,7 @@
1997
  "attributes": {}
1998
  }
1999
  },
2000
- "total_flos": 4.315311685102387e+16,
2001
  "train_batch_size": 4,
2002
  "trial_name": null,
2003
  "trial_params": null
 
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,
 
1978
  "mean_token_accuracy": 0.7426734983921051,
1979
  "num_tokens": 9088894.0,
1980
  "step": 1960
1981
+ },
1982
+ {
1983
+ "entropy": 0.9542628638446331,
1984
+ "epoch": 0.4202666666666667,
1985
+ "grad_norm": 0.2736513614654541,
1986
+ "learning_rate": 9.188570479371387e-05,
1987
+ "loss": 1.14229097366333,
1988
+ "mean_token_accuracy": 0.7659218199551105,
1989
+ "num_tokens": 9133717.0,
1990
+ "step": 1970
1991
  }
1992
  ],
1993
  "logging_steps": 10,
 
2007
  "attributes": {}
2008
  }
2009
  },
2010
+ "total_flos": 4.335691124917248e+16,
2011
  "train_batch_size": 4,
2012
  "trial_name": null,
2013
  "trial_params": null