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
ea042a2
·
verified ·
1 Parent(s): 93636ad

Training in progress, step 2810, 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 sha256:4c8cbe71740290cc970ab8d5ec8ae6c73125df8936c67dea4142bc462d0245dd
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34322ebac780430a2d0f180530bb946169ada1e82457837e6ce8d367b0e6a5d6
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4f9779f1a5d91b00d4248a9b931a1d48046fd311d85a06132f6c4e82da1fee8
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b050f0f67ea3b048da51fe12d4be43883a0c4a32aa27ad9a4bd2a9973b682c86
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:b21e48f955adfb27cd16dd7ba96fbc344639dc4554ea36992618f83094fa5fd5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20a8d2718d6d7598cc26964f5cca4073cecbc57d6bcaef8758ee5cf2e3bd4ab
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64c213455cab2785998b959751e34bb8b907ebbb24ce24b1da1152b62522e147
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd6e15982ff81496b6f33aa5453d99d96b19411f1c911bb21595815ecca8608
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": 0.5973333333333334,
6
  "eval_steps": 500,
7
- "global_step": 2800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2818,6 +2818,16 @@
2818
  "mean_token_accuracy": 0.7694585740566253,
2819
  "num_tokens": 13015439.0,
2820
  "step": 2800
 
 
 
 
 
 
 
 
 
 
2821
  }
2822
  ],
2823
  "logging_steps": 10,
@@ -2837,7 +2847,7 @@
2837
  "attributes": {}
2838
  }
2839
  },
2840
- "total_flos": 6.168558319342694e+16,
2841
  "train_batch_size": 4,
2842
  "trial_name": null,
2843
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5994666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 2810,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2818
  "mean_token_accuracy": 0.7694585740566253,
2819
  "num_tokens": 13015439.0,
2820
  "step": 2800
2821
+ },
2822
+ {
2823
+ "entropy": 1.0109743446111679,
2824
+ "epoch": 0.5994666666666667,
2825
+ "grad_norm": 0.299020379781723,
2826
+ "learning_rate": 8.229966720757007e-05,
2827
+ "loss": 1.1124341011047363,
2828
+ "mean_token_accuracy": 0.7469129160046577,
2829
+ "num_tokens": 13064583.0,
2830
+ "step": 2810
2831
  }
2832
  ],
2833
  "logging_steps": 10,
 
2847
  "attributes": {}
2848
  }
2849
  },
2850
+ "total_flos": 6.191695390971187e+16,
2851
  "train_batch_size": 4,
2852
  "trial_name": null,
2853
  "trial_params": null