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
e37dff3
·
verified ·
1 Parent(s): a2a0743

Training in progress, step 570, 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 sha256:3d3d54897077f51c13f1c3190fc3d6b83489f95531dd9f9a5172338f273c4f76
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e44eec5f56d52e43b2610cc3e84e2e1626372132ec6a5f85692a6d5bc9aa031
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3382c6c15b5088798e584118f4d6b50a5f926f9212fc14a6f6ab2138fedb7a43
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdab28c9af2d554e14c73561057d8ad73d6629b600ee89f4cb722b52f664e38
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80d200a24c76e64bc1662c52278c2910b26a289160b10fc430a343bd27357df0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02de5fb9bfccc0170908c4cdcef68c10f4f63b9b7bb070992c40bea295c55430
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aade3a3b23c3d74be43fc20e89a4415c962a244d7bc4816e416a3bd9ad6c08
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec925dca036ab43778a9e060e6b0537f2fba29a5a21c06f32f84af971ca0981
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": 0.11946666666666667,
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,
@@ -578,6 +578,16 @@
578
  "mean_token_accuracy": 0.7608667835593224,
579
  "num_tokens": 2582645.0,
580
  "step": 560
 
 
 
 
 
 
 
 
 
 
581
  }
582
  ],
583
  "logging_steps": 10,
@@ -597,7 +607,7 @@
597
  "attributes": {}
598
  }
599
  },
600
- "total_flos": 1.2304679318587392e+16,
601
  "train_batch_size": 4,
602
  "trial_name": null,
603
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1216,
6
  "eval_steps": 500,
7
+ "global_step": 570,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
578
  "mean_token_accuracy": 0.7608667835593224,
579
  "num_tokens": 2582645.0,
580
  "step": 560
581
+ },
582
+ {
583
+ "entropy": 1.0654601491987705,
584
+ "epoch": 0.1216,
585
+ "grad_norm": 0.26716434955596924,
586
+ "learning_rate": 9.97834084337101e-05,
587
+ "loss": 1.1589471817016601,
588
+ "mean_token_accuracy": 0.7418766617774963,
589
+ "num_tokens": 2633308.0,
590
+ "step": 570
591
  }
592
  ],
593
  "logging_steps": 10,
 
607
  "attributes": {}
608
  }
609
  },
610
+ "total_flos": 1.2541583322236928e+16,
611
  "train_batch_size": 4,
612
  "trial_name": null,
613
  "trial_params": null