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
85172a3
·
verified ·
1 Parent(s): 63a52ed

Training in progress, step 620, 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 sha256:1980e9d513046749104f51d129c38cf0c83397055629e08ef9bf07eaab0951f3
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ebf63bb41e862c08b625fbff2a46abfb7785763a1b5678ff0fd3879fab1922
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dea179640ae26abb1f6b655e9477a7f8d2041cb5ccddd0777813faddfc772078
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53fc74bd261ac48d2d5b9d1c6449156c10126c16978ee2ad52c011c5598079f
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:c68443901778d0fcd7a67d39423203107772649973a82bb59d560e31f3a6fd7e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0844d9e7253175439b16df209e4e624bce3a9c2d35f7599a5c2620cb697a435d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3123c3a3cbd19b5762f539402f90431bc51bf235aea93b08293175f902d0c081
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8307ec5f73e8cd7c4ea10c1ad3f02f5df1c4edc5b8ef25d02ba7784cde94dd8e
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": 0.13013333333333332,
6
  "eval_steps": 500,
7
- "global_step": 610,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -628,6 +628,16 @@
628
  "mean_token_accuracy": 0.7568746477365493,
629
  "num_tokens": 2827832.0,
630
  "step": 610
 
 
 
 
 
 
 
 
 
 
631
  }
632
  ],
633
  "logging_steps": 10,
@@ -647,7 +657,7 @@
647
  "attributes": {}
648
  }
649
  },
650
- "total_flos": 1.345012387427328e+16,
651
  "train_batch_size": 4,
652
  "trial_name": null,
653
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.13226666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 620,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
628
  "mean_token_accuracy": 0.7568746477365493,
629
  "num_tokens": 2827832.0,
630
  "step": 610
631
+ },
632
+ {
633
+ "entropy": 0.9435897715389728,
634
+ "epoch": 0.13226666666666667,
635
+ "grad_norm": 0.25219106674194336,
636
+ "learning_rate": 9.969549751566075e-05,
637
+ "loss": 1.016776180267334,
638
+ "mean_token_accuracy": 0.76652851998806,
639
+ "num_tokens": 2873516.0,
640
+ "step": 620
641
  }
642
  ],
643
  "logging_steps": 10,
 
657
  "attributes": {}
658
  }
659
  },
660
+ "total_flos": 1.3646294231525376e+16,
661
  "train_batch_size": 4,
662
  "trial_name": null,
663
  "trial_params": null