codet5-large-finetuned-py2cpp

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

• Loss: 0.5811
• Bleu: 1.7782
• Gen Len: 19.0

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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	Bleu	Gen Len
No log	0.98	41	1.4340	1.1636	18.6571
No log	1.99	83	0.8793	1.6009	19.0
No log	2.99	125	0.7255	1.6991	19.0
No log	4.0	167	0.6623	1.7248	19.0
No log	4.98	208	0.6263	1.6321	19.0
No log	5.99	250	0.6073	1.6506	19.0
No log	6.99	292	0.5934	1.7734	19.0
No log	8.0	334	0.5852	1.7891	19.0
No log	8.98	375	0.5824	1.7787	19.0
No log	9.82	410	0.5811	1.7782	19.0

Framework versions

• Transformers 4.33.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.13.3