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
2171e4b
·
verified ·
1 Parent(s): c1a9787

Training in progress, step 560, 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:d1373aa907f406c2a9a059e9f7dd6d8ab313a44593760eb21bec5f66cfa79290
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3d54897077f51c13f1c3190fc3d6b83489f95531dd9f9a5172338f273c4f76
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e87965615be6532f700b360379291c73709ed2b89bdb73d3a0e9e4d2436a88cd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3382c6c15b5088798e584118f4d6b50a5f926f9212fc14a6f6ab2138fedb7a43
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d46faea8b6ef817b5f8a4954749e3f9a7577ad87f750461ef35ca0eef05e24
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d200a24c76e64bc1662c52278c2910b26a289160b10fc430a343bd27357df0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3175a1c494fdb1ecab89a31951e6cddf6494463267320da3674109b13ee3461d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73aade3a3b23c3d74be43fc20e89a4415c962a244d7bc4816e416a3bd9ad6c08
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": 0.11733333333333333,
6
  "eval_steps": 500,
7
- "global_step": 550,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -568,6 +568,16 @@
568
  "mean_token_accuracy": 0.786571592092514,
569
  "num_tokens": 2537415.0,
570
  "step": 550
 
 
 
 
 
 
 
 
 
 
571
  }
572
  ],
573
  "logging_steps": 10,
@@ -587,7 +597,7 @@
587
  "attributes": {}
588
  }
589
  },
590
- "total_flos": 1.2078760782849024e+16,
591
  "train_batch_size": 4,
592
  "trial_name": null,
593
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.11946666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 560,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
568
  "mean_token_accuracy": 0.786571592092514,
569
  "num_tokens": 2537415.0,
570
  "step": 550
571
+ },
572
+ {
573
+ "entropy": 0.9333060696721077,
574
+ "epoch": 0.11946666666666667,
575
+ "grad_norm": 0.23799379169940948,
576
+ "learning_rate": 9.979920198805464e-05,
577
+ "loss": 1.0223896980285645,
578
+ "mean_token_accuracy": 0.7608667835593224,
579
+ "num_tokens": 2582645.0,
580
+ "step": 560
581
  }
582
  ],
583
  "logging_steps": 10,
 
597
  "attributes": {}
598
  }
599
  },
600
+ "total_flos": 1.2304679318587392e+16,
601
  "train_batch_size": 4,
602
  "trial_name": null,
603
  "trial_params": null