codet5-small-java-v1-text-to-code

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

• Loss: 0.7705
• Rouge1: 57.1969
• Rouge2: 40.0098
• Rougel: 55.326
• Rougelsum: 56.119
• Gen Len: 16.8335

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: 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.7434	1.0	6250	0.8148	55.9045	38.592	54.0278	54.7633	16.796
0.6708	2.0	12500	0.7868	56.3354	38.9843	54.5278	55.2197	16.751
0.6309	3.0	18750	0.7741	56.9883	39.8626	55.1321	55.9173	16.8495
0.6262	4.0	25000	0.7705	57.1969	40.0098	55.326	56.119	16.8335

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0