codet5-small-v11

This model is a fine-tuned version of Salesforce/codet5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1410
• Bleu Score: 0.0004
• Gen Len: 13.1271

Model description

Trained:

• on: chathuranga-jayanath/formatted-selfapr-train-data
  • prompt: selfapr train data format -> [BUG]...[CONTEXT]...[CLASS]...[ERROR]

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: 30
• eval_batch_size: 30
• 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
0.2246	1.0	10656	0.1778	0.0004	13.1185
0.1915	2.0	21312	0.1489	0.0004	13.1311
0.1623	3.0	31968	0.1410	0.0004	13.1271

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1