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
bd70d87
·
verified ·
1 Parent(s): 070d994

Training in progress, step 630, 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:e9ebf63bb41e862c08b625fbff2a46abfb7785763a1b5678ff0fd3879fab1922
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62792dd6d7369257c8ee45ddc8c3e61dd5512b359ebe039b307cbfa54a7b628c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b53fc74bd261ac48d2d5b9d1c6449156c10126c16978ee2ad52c011c5598079f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4723d88bcbbb490940420fb23c0ce176e4998f75e9096bca0e5d7db41a485e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0844d9e7253175439b16df209e4e624bce3a9c2d35f7599a5c2620cb697a435d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183eb7f0e9a043d0ae9a8b852649f7318c6fc687c52d4ffd1e9ea423323886d0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8307ec5f73e8cd7c4ea10c1ad3f02f5df1c4edc5b8ef25d02ba7784cde94dd8e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192936caada80d5efac5f67e7ef090d85c1689ed04ed501ec75bb0a18fd6c436
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": 0.13226666666666667,
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,
@@ -638,6 +638,16 @@
638
  "mean_token_accuracy": 0.76652851998806,
639
  "num_tokens": 2873516.0,
640
  "step": 620
 
 
 
 
 
 
 
 
 
 
641
  }
642
  ],
643
  "logging_steps": 10,
@@ -657,7 +667,7 @@
657
  "attributes": {}
658
  }
659
  },
660
- "total_flos": 1.3646294231525376e+16,
661
  "train_batch_size": 4,
662
  "trial_name": null,
663
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1344,
6
  "eval_steps": 500,
7
+ "global_step": 630,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
638
  "mean_token_accuracy": 0.76652851998806,
639
  "num_tokens": 2873516.0,
640
  "step": 620
641
+ },
642
+ {
643
+ "entropy": 0.9641087010502816,
644
+ "epoch": 0.1344,
645
+ "grad_norm": 0.2497103363275528,
646
+ "learning_rate": 9.967612817741272e-05,
647
+ "loss": 1.0406078338623046,
648
+ "mean_token_accuracy": 0.7586069479584694,
649
+ "num_tokens": 2913600.0,
650
+ "step": 630
651
  }
652
  ],
653
  "logging_steps": 10,
 
667
  "attributes": {}
668
  }
669
  },
670
+ "total_flos": 1.3828703465315328e+16,
671
  "train_batch_size": 4,
672
  "trial_name": null,
673
  "trial_params": null