codet5-small-ft-v8-cpatd-ft-v8-cpat_dv5

This model is a fine-tuned version of ayeshgk/codet5-small-ft-v8-cpatd on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1715
• Rouge1: 86.4622
• Rouge2: 76.541
• Rougel: 85.4053
• Rougelsum: 85.4218
• Gen Len: 13.7143

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	0.3355	82.9142	68.2812	81.8458	81.8291	13.3857
No log	2.0	40	0.2333	84.3779	72.1358	83.5562	83.5825	13.3571
No log	3.0	60	0.1830	86.0988	75.5643	85.1853	85.2291	13.6143
No log	4.0	80	0.1715	86.4622	76.541	85.4053	85.4218	13.7143

Framework versions

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