T5_new

This model is a fine-tuned version of Salesforce/codet5p-220m-py on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.3757
• Train Accuracy: 0.7073
• Validation Loss: 0.7734
• Validation Accuracy: 0.6682
• Epoch: 9

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.8179	0.4747	1.3962	0.5364	0
1.3319	0.5404	1.1654	0.5717	1
1.0794	0.5798	1.0278	0.5973	2
0.9032	0.6099	0.9476	0.6147	3
0.7547	0.6362	0.8761	0.6324	4
0.6419	0.6570	0.8206	0.6456	5
0.5576	0.6727	0.7988	0.6529	6
0.4906	0.6852	0.7782	0.6596	7
0.4357	0.6956	0.7575	0.6646	8
0.3757	0.7073	0.7734	0.6682	9

Framework versions

• Transformers 4.47.0
• TensorFlow 2.17.1
• Datasets 3.3.1
• Tokenizers 0.21.0