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
40f6dc4
·
verified ·
1 Parent(s): c5d28c8

Training in progress, step 1020, 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 sha256:7801abd00974aaa08bac2050addd05582358ba8d6fba1fdffd081f457f7cbbd0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668123144411634ca201e1e2c398f8b0dc431ed91b3b738160a2310edeb38f0f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80f976700ee39917a70e7455594093124179a6b8219d40c681b879f6c2f647e3
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252b7e9daf2fbcdac4289e793c05c866db218cf96123bf8e819aa6230d273648
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:ce9391dd9f8ca951b26f2722de8cb55b8ef3514b03d49ff246c82d67b2b3a704
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcec43d17a26608b8bfc06c04154fb7c3a2bd34c443f3de04f2fe54081c5f1d9
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c940e54a0db6643b85375ae76e99b254a9a6e56275e3458b83592cf6e135219
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b101d0a265445c70ecce8df0b28001fba354a395d578e7ea1671d59fbada1b1e
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": 0.21546666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1010,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1028,6 +1028,16 @@
1028
  "mean_token_accuracy": 0.77038114964962,
1029
  "num_tokens": 4713754.0,
1030
  "step": 1010
 
 
 
 
 
 
 
 
 
 
1031
  }
1032
  ],
1033
  "logging_steps": 10,
@@ -1047,7 +1057,7 @@
1047
  "attributes": {}
1048
  }
1049
  },
1050
- "total_flos": 2.229555234377011e+16,
1051
  "train_batch_size": 4,
1052
  "trial_name": null,
1053
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2176,
6
  "eval_steps": 500,
7
+ "global_step": 1020,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1028
  "mean_token_accuracy": 0.77038114964962,
1029
  "num_tokens": 4713754.0,
1030
  "step": 1010
1031
+ },
1032
+ {
1033
+ "entropy": 0.9357184395194054,
1034
+ "epoch": 0.2176,
1035
+ "grad_norm": 0.3024005889892578,
1036
+ "learning_rate": 9.845948570547187e-05,
1037
+ "loss": 1.001820945739746,
1038
+ "mean_token_accuracy": 0.7686716303229332,
1039
+ "num_tokens": 4754969.0,
1040
+ "step": 1020
1041
  }
1042
  ],
1043
  "logging_steps": 10,
 
1057
  "attributes": {}
1058
  }
1059
  },
1060
+ "total_flos": 2.248124189775667e+16,
1061
  "train_batch_size": 4,
1062
  "trial_name": null,
1063
  "trial_params": null