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
46c34ec
·
verified ·
1 Parent(s): 508efd6

Training in progress, step 720, 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:a88e81d3f32ade194b58fb91379dff11bfd8e0f8fd0532bf90258df18eaf69e6
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9119bec5acae9119f096a54ede6c38ca2cca9877e9873535fbda8ec7b95d453
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d05cafba8450ed17db6307e500537d4b840670d7e35ac7624ddb7e24624c9ead
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a83f692e854cc298006bae6dfbbd41387cdfa68e38152eefdbf8a1891fe21db
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fa752c8460d17d6915d88e6ab1ffc029d0cecbe38986f782a07070e0b27186e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539050b22d56cf231108298e6d5c0f9344ec6541cc98d2380c80baee0419ef56
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aef5cf454641381822ccada9139aed26fd2ef08e6bf71fb1d478807e79577798
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a9af742a703a71e99f7a37f0ec4d8278e85a5d04634c205d2e956abe61db30
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": 0.15146666666666667,
6
  "eval_steps": 500,
7
- "global_step": 710,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -728,6 +728,16 @@
728
  "mean_token_accuracy": 0.7498437210917472,
729
  "num_tokens": 3287959.0,
730
  "step": 710
 
 
 
 
 
 
 
 
 
 
731
  }
732
  ],
733
  "logging_steps": 10,
@@ -747,7 +757,7 @@
747
  "attributes": {}
748
  }
749
  },
750
- "total_flos": 1.5570517442239488e+16,
751
  "train_batch_size": 4,
752
  "trial_name": null,
753
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1536,
6
  "eval_steps": 500,
7
+ "global_step": 720,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
728
  "mean_token_accuracy": 0.7498437210917472,
729
  "num_tokens": 3287959.0,
730
  "step": 710
731
+ },
732
+ {
733
+ "entropy": 1.027633222937584,
734
+ "epoch": 0.1536,
735
+ "grad_norm": 0.2338317185640335,
736
+ "learning_rate": 9.947505063281157e-05,
737
+ "loss": 1.0913351058959961,
738
+ "mean_token_accuracy": 0.750363714993,
739
+ "num_tokens": 3335092.0,
740
+ "step": 720
741
  }
742
  ],
743
  "logging_steps": 10,
 
757
  "attributes": {}
758
  }
759
  },
760
+ "total_flos": 1.5799896535547904e+16,
761
  "train_batch_size": 4,
762
  "trial_name": null,
763
  "trial_params": null