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
1b7722e
·
verified ·
1 Parent(s): a97de20

Training in progress, step 380, 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:e5304af3f27d3534d351511fca5e6a6863ebbafe222d93778ef73271a7fae5f2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad536876db10f3be2615947ae36289b2dbe30b514d60d20ea96412b6dd985b33
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ffd45f83268adebe065f312dfd395bd1507435cef0e4e4d1146fd0b39e3c2f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5598f896ac9528751710208d2a0d0e4a213fdf99ac27490e5d357f470c3d3f
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:c9221be7cf0b53d9897129a89b43f1ca268fdebcfb1504935f4e54c55403b602
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c59dadccd9b6d5640db255df66c9397363ec90cea60aab1c876bf4272241a3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b36df719885e8c29c64e277b702d22ef4d9ad1644bbb4180ff17df8ae4af2cc
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc47a82d6b62116d16571a1dde9113e9078d976e8eda42384330abeea15865e
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": 0.07893333333333333,
6
  "eval_steps": 500,
7
- "global_step": 370,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -388,6 +388,16 @@
388
  "mean_token_accuracy": 0.7424520552158356,
389
  "num_tokens": 1712075.0,
390
  "step": 370
 
 
 
 
 
 
 
 
 
 
391
  }
392
  ],
393
  "logging_steps": 10,
@@ -407,7 +417,7 @@
407
  "attributes": {}
408
  }
409
  },
410
- "total_flos": 8147477264587776.0,
411
  "train_batch_size": 4,
412
  "trial_name": null,
413
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.08106666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 380,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
388
  "mean_token_accuracy": 0.7424520552158356,
389
  "num_tokens": 1712075.0,
390
  "step": 370
391
+ },
392
+ {
393
+ "entropy": 1.0094588652253151,
394
+ "epoch": 0.08106666666666666,
395
+ "grad_norm": 0.1927226334810257,
396
+ "learning_rate": 9.998130704762335e-05,
397
+ "loss": 1.062878704071045,
398
+ "mean_token_accuracy": 0.7529133662581444,
399
+ "num_tokens": 1762001.0,
400
+ "step": 380
401
  }
402
  ],
403
  "logging_steps": 10,
 
417
  "attributes": {}
418
  }
419
  },
420
+ "total_flos": 8390211947268096.0,
421
  "train_batch_size": 4,
422
  "trial_name": null,
423
  "trial_params": null