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
29071e8
·
verified ·
1 Parent(s): 268bff4

Training in progress, step 420, 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:f4ed6a544f9d924a761db418c429862898e4ed7095da2fb2c963a476c8d15070
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a82e6668489974a397aeff7a7a6fde9bfc65030760cac5438c42869cd28458
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3958f1ad44d5ba182a73d90deda80200014c28bf3778bfcb4423f62766ecc52
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0f8014e3670591465e5f35750b881e9d139ba1b0d3bdee401f2a65695ee6bf
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:341acbb4c55ddb99a44518768b4df844b002cd93d82b7183b339754ddb4142ab
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bad05796bf22d2b9e7c0b69f863a9f28e9973eee050bf115148d79490fd722d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62455f2b1dbd96b08c8ebc6abeb255cec1cb2a2bf25cf908d290ca3a2151401a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985422dcfba385fa57091a242683ec1efb784f240b8b4674b2ce79107526aeb1
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": 0.08746666666666666,
6
  "eval_steps": 500,
7
- "global_step": 410,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -428,6 +428,16 @@
428
  "mean_token_accuracy": 0.7511946842074394,
429
  "num_tokens": 1891181.0,
430
  "step": 410
 
 
 
 
 
 
 
 
 
 
431
  }
432
  ],
433
  "logging_steps": 10,
@@ -447,7 +457,7 @@
447
  "attributes": {}
448
  }
449
  },
450
- "total_flos": 8984544686186496.0,
451
  "train_batch_size": 4,
452
  "trial_name": null,
453
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.0896,
6
  "eval_steps": 500,
7
+ "global_step": 420,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
428
  "mean_token_accuracy": 0.7511946842074394,
429
  "num_tokens": 1891181.0,
430
  "step": 410
431
+ },
432
+ {
433
+ "entropy": 0.9595077157020568,
434
+ "epoch": 0.0896,
435
+ "grad_norm": 0.31688833236694336,
436
+ "learning_rate": 9.995758853288805e-05,
437
+ "loss": 1.0745075225830079,
438
+ "mean_token_accuracy": 0.7604640245437622,
439
+ "num_tokens": 1934494.0,
440
+ "step": 420
441
  }
442
  ],
443
  "logging_steps": 10,
 
457
  "attributes": {}
458
  }
459
  },
460
+ "total_flos": 9192331342156800.0,
461
  "train_batch_size": 4,
462
  "trial_name": null,
463
  "trial_params": null