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
6f32961
·
verified ·
1 Parent(s): e20a327

Training in progress, step 2730, 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 sha256:506a613b0146512b986ba1981cdf2bbd94aeaffa8e987cd84342b92da5e79916
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3aa86c1d9c6dc81df7b665891a8b5abc5d6cc4bfb38913b4d0fcd506e660783
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9f1db54048384c15393cf611df07e5b8f554cf107ad4a691310de6e0b4a8216
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead78ad207974b1991e876201e73e2632e13450c7ff54d1f4ac815cd8ae7f884
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:d207612e3cba97c108af817135a46e7bc9cc05ec08c71123cba020f8561bdba4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac094950b3dd485ae517d4266f9e4f438aed07e153ad33663fb710e418504a49
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95b2601e1c630be4d03abe53e6c9f6eeb50259e09077bbed2f0773274a364431
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d0f986a44076d5360788ebc0677cc87f1c79c5ac763481086e0a7b1c471e6a
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": 0.5802666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2720,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2738,6 +2738,16 @@
2738
  "mean_token_accuracy": 0.7622367069125175,
2739
  "num_tokens": 12635296.0,
2740
  "step": 2720
 
 
 
 
 
 
 
 
 
 
2741
  }
2742
  ],
2743
  "logging_steps": 10,
@@ -2757,7 +2767,7 @@
2757
  "attributes": {}
2758
  }
2759
  },
2760
- "total_flos": 5.99009267928361e+16,
2761
  "train_batch_size": 4,
2762
  "trial_name": null,
2763
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5824,
6
  "eval_steps": 500,
7
+ "global_step": 2730,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2738
  "mean_token_accuracy": 0.7622367069125175,
2739
  "num_tokens": 12635296.0,
2740
  "step": 2720
2741
+ },
2742
+ {
2743
+ "entropy": 0.9387885488569736,
2744
+ "epoch": 0.5824,
2745
+ "grad_norm": 0.3290941119194031,
2746
+ "learning_rate": 8.334405198376958e-05,
2747
+ "loss": 1.0030738830566406,
2748
+ "mean_token_accuracy": 0.7586753875017166,
2749
+ "num_tokens": 12681486.0,
2750
+ "step": 2730
2751
  }
2752
  ],
2753
  "logging_steps": 10,
 
2767
  "attributes": {}
2768
  }
2769
  },
2770
+ "total_flos": 6.012579995180851e+16,
2771
  "train_batch_size": 4,
2772
  "trial_name": null,
2773
  "trial_params": null