Patcas's picture
End of training
3c2b5e7 verified
metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
  - generated_from_trainer
model-index:
  - name: codet5-with-doc-neww-v3
    results: []

codet5-with-doc-neww-v3

This model is a fine-tuned version of Salesforce/codet5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1008

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 230 1.6652
No log 2.0 460 1.4116
2.0142 3.0 690 1.2981
2.0142 4.0 920 1.2329
1.1448 5.0 1150 1.1712
1.1448 6.0 1380 1.1466
0.814 7.0 1610 1.1150
0.814 8.0 1840 1.1093
0.7008 9.0 2070 1.1018
0.7008 10.0 2300 1.1008

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1