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
78c6f02
·
verified ·
1 Parent(s): 31f15ee

Training in progress, step 1640, 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:dbc0b9535e0cd7bbd40c325e1df1d620f5e0634732be36e06c6531f780634a51
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a789cc82fc55c5d1977b11b095e485df1d770d045fa5bcd10e1d6d6896cd202
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:201984ae8edf6b6a133b6515a8fcbc3eab2566e3f1873ee0a97aa9fd9218db8b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e758a621f68658f478f9af1488bcbd512cb1884c61c4d03eec6469a82be5158
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ecd86e07e61f77465e226ceb43a96afc3eb7e6952e61209c9020ac360d89a4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6a58b813668536860ea2f8905ed991304e0c6708601983c17a7d0c9ae1cfb2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9d4ee00fbfe2a02df4f98c5ce73c96144020d97c62d625c71fc70631e2a4ce1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5b1ba2dd1208014572958a84bd2231054da43cd48315ebd0b09b5bb9db420c
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": 0.34773333333333334,
6
  "eval_steps": 500,
7
- "global_step": 1630,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1648,6 +1648,16 @@
1648
  "mean_token_accuracy": 0.7502199374139309,
1649
  "num_tokens": 7573700.0,
1650
  "step": 1630
 
 
 
 
 
 
 
 
 
 
1651
  }
1652
  ],
1653
  "logging_steps": 10,
@@ -1667,7 +1677,7 @@
1667
  "attributes": {}
1668
  }
1669
  },
1670
- "total_flos": 3.5912134444283904e+16,
1671
  "train_batch_size": 4,
1672
  "trial_name": null,
1673
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.34986666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 1640,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1648
  "mean_token_accuracy": 0.7502199374139309,
1649
  "num_tokens": 7573700.0,
1650
  "step": 1630
1651
+ },
1652
+ {
1653
+ "entropy": 0.9277701899409294,
1654
+ "epoch": 0.34986666666666666,
1655
+ "grad_norm": 0.25027042627334595,
1656
+ "learning_rate": 9.472498834887671e-05,
1657
+ "loss": 0.9662016868591309,
1658
+ "mean_token_accuracy": 0.769710011780262,
1659
+ "num_tokens": 7619772.0,
1660
+ "step": 1640
1661
  }
1662
  ],
1663
  "logging_steps": 10,
 
1677
  "attributes": {}
1678
  }
1679
  },
1680
+ "total_flos": 3.614708287243162e+16,
1681
  "train_batch_size": 4,
1682
  "trial_name": null,
1683
  "trial_params": null