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
8e45b9b
·
verified ·
1 Parent(s): dca3191

Training in progress, step 660, 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 sha256:5ba2c9e34e30db5c998ce0a4de749a0bdd1a6b5f90b27534ad36835dbf6d582d
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61d1ce6eee4db4f03b66ed79bd4af7559b73446813d7f61aded2136c3f4638c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:641d66196316619b3710a969d55a4d82f4fb3b572c3c294b8b6409d90761e312
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd6baca095808d02e92c43f96fc1a66a23524029cb0e1a8f1c9f1ae7822ef7dc
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:a4114553082ca1845f3fc7e69c4e6e7243ca221ebcfd740c1a75560d0bd716ac
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5f88a93444460d1014be9a7f9defe4780737900c6e285a029cebddf392adf3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026b5c74cc8e086c9916a04299b290480732d771d50ea5509c5a30a72dbfe481
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b59c5d619e8d9fe2fb09b701937a06cf585e9d9564fe1d0bf53187d4d0146c7
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": 0.13866666666666666,
6
  "eval_steps": 500,
7
- "global_step": 650,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -668,6 +668,16 @@
668
  "mean_token_accuracy": 0.7496687114238739,
669
  "num_tokens": 3006113.0,
670
  "step": 650
 
 
 
 
 
 
 
 
 
 
671
  }
672
  ],
673
  "logging_steps": 10,
@@ -687,7 +697,7 @@
687
  "attributes": {}
688
  }
689
  },
690
- "total_flos": 1.4248061762098176e+16,
691
  "train_batch_size": 4,
692
  "trial_name": null,
693
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1408,
6
  "eval_steps": 500,
7
+ "global_step": 660,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
668
  "mean_token_accuracy": 0.7496687114238739,
669
  "num_tokens": 3006113.0,
670
  "step": 650
671
+ },
672
+ {
673
+ "entropy": 0.9443116314709187,
674
+ "epoch": 0.1408,
675
+ "grad_norm": 0.26775607466697693,
676
+ "learning_rate": 9.961444996646532e-05,
677
+ "loss": 1.020461654663086,
678
+ "mean_token_accuracy": 0.7648672193288804,
679
+ "num_tokens": 3052837.0,
680
+ "step": 660
681
  }
682
  ],
683
  "logging_steps": 10,
 
697
  "attributes": {}
698
  }
699
  },
700
+ "total_flos": 1.44496302286848e+16,
701
  "train_batch_size": 4,
702
  "trial_name": null,
703
  "trial_params": null