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
7f1f9ee
·
verified ·
1 Parent(s): b1e9c1f

Training in progress, step 430, 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 sha256:79a82e6668489974a397aeff7a7a6fde9bfc65030760cac5438c42869cd28458
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae250b808391f35fbdef96d5186b099cd7e2b4e3b56aa527d259bad9175184cd
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce0f8014e3670591465e5f35750b881e9d139ba1b0d3bdee401f2a65695ee6bf
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5983422f152e5254dc7d851895cf3dcbfc3884c6b6861a85daafd913bb66677d
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bad05796bf22d2b9e7c0b69f863a9f28e9973eee050bf115148d79490fd722d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec17cdbee57edc9c3932443e7e28d062ca51eba471aa77d55b6cea78da6bc812
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:985422dcfba385fa57091a242683ec1efb784f240b8b4674b2ce79107526aeb1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d37ddffce7cf94e2aa183379513439ac7bafddcb9ed7faca66cebb59aaaac58
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": 0.0896,
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,
@@ -438,6 +438,16 @@
438
  "mean_token_accuracy": 0.7604640245437622,
439
  "num_tokens": 1934494.0,
440
  "step": 420
 
 
 
 
 
 
 
 
 
 
441
  }
442
  ],
443
  "logging_steps": 10,
@@ -457,7 +467,7 @@
457
  "attributes": {}
458
  }
459
  },
460
- "total_flos": 9192331342156800.0,
461
  "train_batch_size": 4,
462
  "trial_name": null,
463
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.09173333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 430,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
438
  "mean_token_accuracy": 0.7604640245437622,
439
  "num_tokens": 1934494.0,
440
  "step": 420
441
+ },
442
+ {
443
+ "entropy": 0.963299511373043,
444
+ "epoch": 0.09173333333333333,
445
+ "grad_norm": 0.29464003443717957,
446
+ "learning_rate": 9.995016229448395e-05,
447
+ "loss": 1.0001104354858399,
448
+ "mean_token_accuracy": 0.763674932718277,
449
+ "num_tokens": 1976770.0,
450
+ "step": 430
451
  }
452
  ],
453
  "logging_steps": 10,
 
467
  "attributes": {}
468
  }
469
  },
470
+ "total_flos": 9384536477193216.0,
471
  "train_batch_size": 4,
472
  "trial_name": null,
473
  "trial_params": null