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
2c0eeac
·
verified ·
1 Parent(s): 2a79a2c

Training in progress, step 460, 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 sha256:750f0e7efdc8e37a14ecc5bc5ba319218d5854f6081236b6ae8ca6c13a591984
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6bba2fa766083a37b7fef14bdeb055d187dd40b46e5d093e6fb93edac39a7f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7f775348a1764a14d6f11b2a4a8a30e24aa7268352e03725d1b3af2aee6dc2b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda7aaf8c2feb0427797b8f314b5dabfb21db7a96dc8061c3b5c16544a8be75a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54172abd65c4b894245bc82a5e51893fc027b171b3b6cad3f63fcfe508d3884b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c338a65dcee0c9c43342d52e75b93791090fc469962c60e4c490681b73893c59
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23db730c265d17bb98bdc34a288220c0f5ef2c3115f88a855e50ac6ec0ecab2c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0017a9ef1a6f6c77b373ad3374315b6d4aa6379414856ce1866607dc6e40ded
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": 0.096,
6
  "eval_steps": 500,
7
- "global_step": 450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -468,6 +468,16 @@
468
  "mean_token_accuracy": 0.7607480764389039,
469
  "num_tokens": 2072441.0,
470
  "step": 450
 
 
 
 
 
 
 
 
 
 
471
  }
472
  ],
473
  "logging_steps": 10,
@@ -487,7 +497,7 @@
487
  "attributes": {}
488
  }
489
  },
490
- "total_flos": 9843312687547392.0,
491
  "train_batch_size": 4,
492
  "trial_name": null,
493
  "trial_params": null
 
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,
 
468
  "mean_token_accuracy": 0.7607480764389039,
469
  "num_tokens": 2072441.0,
470
  "step": 450
471
+ },
472
+ {
473
+ "entropy": 1.0221860893070698,
474
+ "epoch": 0.09813333333333334,
475
+ "grad_norm": 0.25882700085639954,
476
+ "learning_rate": 9.992429311088296e-05,
477
+ "loss": 1.0992252349853515,
478
+ "mean_token_accuracy": 0.7492104887962341,
479
+ "num_tokens": 2119587.0,
480
+ "step": 460
481
  }
482
  ],
483
  "logging_steps": 10,
 
497
  "attributes": {}
498
  }
499
  },
500
+ "total_flos": 1.0067933514196992e+16,
501
  "train_batch_size": 4,
502
  "trial_name": null,
503
  "trial_params": null