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
cba9007
·
verified ·
1 Parent(s): f3a720d

Training in progress, step 3950, 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 sha256:67a71842616a4677b02d34458645aa12fb6137b2872cedd986360d51d4ad4e1d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7dd37205821e445b5a7d9e2489cc3194c006f75635a60f487a778d3b9383eed
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1af448ba076823eea24e332dcf9c9ce467a0e0fb62c0340c2000d748d2cda6
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c336382a56f6751ba11ea53a12c04fa71cf9bca3c3cbedcb2808039b558658
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45234e471588cc36ff7664898ecd1cc225bbd0b663638c6c91062c96426e5ef4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2242d0015c6567e39a1276bd53269a1edfecf37f1f9ab4ddcc03a50fb889eb
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:338ca2abead33bd1f1f2eb57903990248de5a037592d4dde0e4c004c95dd856c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61cfeac6c03c1de877322305f0fe5970af06ba8696c8712e459b3178cf37fa4
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": 0.8405333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3940,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3958,6 +3958,16 @@
3958
  "mean_token_accuracy": 0.764385013282299,
3959
  "num_tokens": 18367778.0,
3960
  "step": 3940
 
 
 
 
 
 
 
 
 
 
3961
  }
3962
  ],
3963
  "logging_steps": 10,
@@ -3977,7 +3987,7 @@
3977
  "attributes": {}
3978
  }
3979
  },
3980
- "total_flos": 8.695267306562765e+16,
3981
  "train_batch_size": 4,
3982
  "trial_name": null,
3983
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8426666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3950,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3958
  "mean_token_accuracy": 0.764385013282299,
3959
  "num_tokens": 18367778.0,
3960
  "step": 3940
3961
+ },
3962
+ {
3963
+ "entropy": 0.9153544351458549,
3964
+ "epoch": 0.8426666666666667,
3965
+ "grad_norm": 0.40482011437416077,
3966
+ "learning_rate": 6.5144374278673e-05,
3967
+ "loss": 0.990359878540039,
3968
+ "mean_token_accuracy": 0.7689836576581002,
3969
+ "num_tokens": 18413756.0,
3970
+ "step": 3950
3971
  }
3972
  ],
3973
  "logging_steps": 10,
 
3987
  "attributes": {}
3988
  }
3989
  },
3990
+ "total_flos": 8.718232251499622e+16,
3991
  "train_batch_size": 4,
3992
  "trial_name": null,
3993
  "trial_params": null