codet5p-220m-v30 / README.md
chathuranga-jayanath's picture
End of training
4e6b28f verified
|
raw
history blame
1.61 kB
metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-220m
tags:
  - generated_from_trainer
model-index:
  - name: codet5p-220m-v30
    results: []

codet5p-220m-v30

This model is a fine-tuned version of Salesforce/codet5p-220m on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0641
  • Bleu Score: 0.0007
  • Gen Len: 14.5204

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 12
  • eval_batch_size: 12
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Score Gen Len
0.1254 1.0 8517 0.0991 0.0007 14.4791
0.0632 2.0 17034 0.0714 0.0007 14.51
0.0462 3.0 25551 0.0641 0.0007 14.5204

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.2