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
55050e7
·
verified ·
1 Parent(s): f4f9782

Training in progress, step 470, 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 sha256:5f6bba2fa766083a37b7fef14bdeb055d187dd40b46e5d093e6fb93edac39a7f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377450f9d5e72c2a3ac138957ba72da38269ec4e8ace8a689cfafdbdc8e9de67
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fda7aaf8c2feb0427797b8f314b5dabfb21db7a96dc8061c3b5c16544a8be75a
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2380a7f0a5febe1dc2cd09aa1d226529df0e940571ad9cb0358a30c713970ff
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:c338a65dcee0c9c43342d52e75b93791090fc469962c60e4c490681b73893c59
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4966ec76bc7bc8bb4cdbc928ada4e289b036911fee3cd860685c86f7168807
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0017a9ef1a6f6c77b373ad3374315b6d4aa6379414856ce1866607dc6e40ded
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d98f0d9d23105e8e46650fe3f487dd24428a36e6adf2ab34bc7f6b949f3ec6f
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": 0.09813333333333334,
6
  "eval_steps": 500,
7
- "global_step": 460,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -478,6 +478,16 @@
478
  "mean_token_accuracy": 0.7492104887962341,
479
  "num_tokens": 2119587.0,
480
  "step": 460
 
 
 
 
 
 
 
 
 
 
481
  }
482
  ],
483
  "logging_steps": 10,
@@ -497,7 +507,7 @@
497
  "attributes": {}
498
  }
499
  },
500
- "total_flos": 1.0067933514196992e+16,
501
  "train_batch_size": 4,
502
  "trial_name": null,
503
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.10026666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 470,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
478
  "mean_token_accuracy": 0.7492104887962341,
479
  "num_tokens": 2119587.0,
480
  "step": 460
481
+ },
482
+ {
483
+ "entropy": 1.082937440276146,
484
+ "epoch": 0.10026666666666667,
485
+ "grad_norm": 0.23417538404464722,
486
+ "learning_rate": 9.991447357127657e-05,
487
+ "loss": 1.2704851150512695,
488
+ "mean_token_accuracy": 0.7427436165511608,
489
+ "num_tokens": 2171365.0,
490
+ "step": 470
491
  }
492
  ],
493
  "logging_steps": 10,
 
507
  "attributes": {}
508
  }
509
  },
510
+ "total_flos": 1.0306892223903744e+16,
511
  "train_batch_size": 4,
512
  "trial_name": null,
513
  "trial_params": null