codet5-small-ft-v7-iter-f

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: 0.3579
• Rouge1: 65.1905
• Rouge2: 58.0093
• Rougel: 64.6754
• Rougelsum: 64.9444
• Gen Len: 12.7593

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
No log	1.0	20	1.2614	53.6789	41.4991	53.6127	53.6281	11.9259
No log	2.0	40	0.5435	53.3609	42.8943	50.5216	50.638	16.1852
No log	3.0	60	0.3948	57.8859	48.6662	57.8364	57.7638	11.4815
No log	4.0	80	0.3579	65.1905	58.0093	64.6754	64.9444	12.7593

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0