PopularPenguin/CodeT5L-1

codet5-large-2024-11-27_20-00

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

• Loss: 0.2856
• Gen Len: 18.9997
• Bertscorer-p: 0.6071
• Bertscorer-r: 0.2214
• Bertscorer-f1: 0.4073
• Sacrebleu-score: 13.1915
• Sacrebleu-precisions: [91.2377160786171, 81.28148602080365, 74.45810305941498, 69.5812750161697]
• Bleu-bp: 0.1676

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Gen Len	Bertscorer-p	Bertscorer-r	Bertscorer-f1	Sacrebleu-score	Sacrebleu-precisions	Bleu-bp
0.3327	1.0	2386	0.2856	18.9997	0.6071	0.2214	0.4073	13.1915	[91.2377160786171, 81.28148602080365, 74.45810305941498, 69.5812750161697]	0.1676

Framework versions

• PEFT 0.13.2
• Transformers 4.40.1
• Pytorch 1.13.1+cu117
• Datasets 3.1.0
• Tokenizers 0.19.1