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
b52228d
·
verified ·
1 Parent(s): c9e6cb1

Training in progress, step 3570, 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:ebde3d7e559a48848dc709360ddf4d64cdda954d1cb3fe794d942bded79f95d8
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa49be33f5b9ddc9a70d3cf2e331246665fdcc6eaa1b6d35c88e278e335395d1
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c17c3bc26250a812166f29e379657082877dc2905caa7b3ca79bd0e054588564
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ce0c4b697fd154bf9c17d8a3ff46d3ba6b113761b3516973e5030159031046
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:d702f00a2f08d2b738793fd7a29f217448a5a6e44a611e821d40d99816cd86d9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd91a7367595c7c2ceb2f2618855abefa9c538ea9447f9bb1aa7919f131488a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd90a7b3ffd42e7d697a64c9b723494d4e821060ee3fea49f312e5184c1a7a0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba1c8310baa6581a06ef3da7d324d8ec2679b844a28c71f2f755bff61dd6cb5
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": 0.7594666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3560,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3578,6 +3578,16 @@
3578
  "mean_token_accuracy": 0.7682245895266533,
3579
  "num_tokens": 16586157.0,
3580
  "step": 3560
 
 
 
 
 
 
 
 
 
 
3581
  }
3582
  ],
3583
  "logging_steps": 10,
@@ -3597,7 +3607,7 @@
3597
  "attributes": {}
3598
  }
3599
  },
3600
- "total_flos": 7.860559192182374e+16,
3601
  "train_batch_size": 4,
3602
  "trial_name": null,
3603
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7616,
6
  "eval_steps": 500,
7
+ "global_step": 3570,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3578
  "mean_token_accuracy": 0.7682245895266533,
3579
  "num_tokens": 16586157.0,
3580
  "step": 3560
3581
+ },
3582
+ {
3583
+ "entropy": 0.8198081150650978,
3584
+ "epoch": 0.7616,
3585
+ "grad_norm": 0.3035356104373932,
3586
+ "learning_rate": 7.126327879619807e-05,
3587
+ "loss": 0.8880753517150879,
3588
+ "mean_token_accuracy": 0.7954168729484081,
3589
+ "num_tokens": 16623992.0,
3590
+ "step": 3570
3591
  }
3592
  ],
3593
  "logging_steps": 10,
 
3607
  "attributes": {}
3608
  }
3609
  },
3610
+ "total_flos": 7.879059657379123e+16,
3611
  "train_batch_size": 4,
3612
  "trial_name": null,
3613
  "trial_params": null