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
7a90de2
·
verified ·
1 Parent(s): 31e818a

Training in progress, step 3890, 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:e553d1155f3fcf8ec061c863d691cad5e307ae36ae809eb14bc86a02bf8fb8e9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766a2968831f87935845b94cf2be48203c26036529e1babc3789618d748fd532
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:466d4684921cda2c67be02c88819c357af36b61a442ac97b64fe7cf88b0573c4
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bb07a02ae53a5f8733a4bf0b9fd780e85485b72feccf16b45b90891fad5a72
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:055d91b1cdd4d0871f9a24a2c2804ca7344e0797f263ca83f2135d59d74815a7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85726ef5713cadd1df3ece9c9ff240c456cc7e697b4feb9e69941f0040445bc5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:201b71d5d61574d3ccab1355b8b55414d420e48e265766a3693614c44d3eff02
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5191c82830fae6addcc4e62aa736c747f395bbcb71d6b30fbda00baefa87f10b
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": 0.8277333333333333,
6
  "eval_steps": 500,
7
- "global_step": 3880,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3898,6 +3898,16 @@
3898
  "mean_token_accuracy": 0.7708318918943405,
3899
  "num_tokens": 18090208.0,
3900
  "step": 3880
 
 
 
 
 
 
 
 
 
 
3901
  }
3902
  ],
3903
  "logging_steps": 10,
@@ -3917,7 +3927,7 @@
3917
  "attributes": {}
3918
  }
3919
  },
3920
- "total_flos": 8.564077929556992e+16,
3921
  "train_batch_size": 4,
3922
  "trial_name": null,
3923
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8298666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 3890,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3898
  "mean_token_accuracy": 0.7708318918943405,
3899
  "num_tokens": 18090208.0,
3900
  "step": 3880
3901
+ },
3902
+ {
3903
+ "entropy": 0.8513198003172875,
3904
+ "epoch": 0.8298666666666666,
3905
+ "grad_norm": 0.2545130252838135,
3906
+ "learning_rate": 6.613068690246905e-05,
3907
+ "loss": 0.9449549674987793,
3908
+ "mean_token_accuracy": 0.7845224231481552,
3909
+ "num_tokens": 18135064.0,
3910
+ "step": 3890
3911
  }
3912
  ],
3913
  "logging_steps": 10,
 
3927
  "attributes": {}
3928
  }
3929
  },
3930
+ "total_flos": 8.583954507099955e+16,
3931
  "train_batch_size": 4,
3932
  "trial_name": null,
3933
  "trial_params": null