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
a4cc0fe
·
verified ·
1 Parent(s): ab47089

Training in progress, step 440, 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:ae250b808391f35fbdef96d5186b099cd7e2b4e3b56aa527d259bad9175184cd
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08b5c8d7c85c670fb281fe4b644b6295f19843e920cc077302bccc9f088568a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5983422f152e5254dc7d851895cf3dcbfc3884c6b6861a85daafd913bb66677d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31907e44baa8b4eab7884611939f5a3ebbf0f45c970fca44fd0c93a214c8322e
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:ec17cdbee57edc9c3932443e7e28d062ca51eba471aa77d55b6cea78da6bc812
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43eba60397466adac1442edb39b546391b90e1195ef90573e2cb80704a6826ad
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d37ddffce7cf94e2aa183379513439ac7bafddcb9ed7faca66cebb59aaaac58
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3732f56883ef738ff880dd47a651c3b358007655dc2c409a69ddba472e4f20b1
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": 0.09173333333333333,
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,
@@ -448,6 +448,16 @@
448
  "mean_token_accuracy": 0.763674932718277,
449
  "num_tokens": 1976770.0,
450
  "step": 430
 
 
 
 
 
 
 
 
 
 
451
  }
452
  ],
453
  "logging_steps": 10,
@@ -467,7 +477,7 @@
467
  "attributes": {}
468
  }
469
  },
470
- "total_flos": 9384536477193216.0,
471
  "train_batch_size": 4,
472
  "trial_name": null,
473
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.09386666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 440,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
448
  "mean_token_accuracy": 0.763674932718277,
449
  "num_tokens": 1976770.0,
450
  "step": 430
451
+ },
452
+ {
453
+ "entropy": 1.1388054117560387,
454
+ "epoch": 0.09386666666666667,
455
+ "grad_norm": 0.2581053078174591,
456
+ "learning_rate": 9.994213757938819e-05,
457
+ "loss": 1.2570265769958495,
458
+ "mean_token_accuracy": 0.726725485175848,
459
+ "num_tokens": 2028837.0,
460
+ "step": 440
461
  }
462
  ],
463
  "logging_steps": 10,
 
477
  "attributes": {}
478
  }
479
  },
480
+ "total_flos": 9640671808588800.0,
481
  "train_batch_size": 4,
482
  "trial_name": null,
483
  "trial_params": null