conservation_gc_codon_t5_small

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3890
• Accuracy: 0.8465

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: 8
• eval_batch_size: 8
• seed: 0
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: polynomial
• num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6949	1.0	1344	0.6931	0.4458
0.624	2.0	2688	0.4578	0.8307
0.5455	3.0	4032	0.3847	0.8624
0.5393	4.0	5376	0.3912	0.8648
0.5208	5.0	6720	0.3811	0.8624
0.5277	6.0	8064	0.4022	0.8648
0.5241	7.0	9408	0.3903	0.8575
0.5191	8.0	10752	0.3941	0.8465
0.5031	9.0	12096	0.3941	0.8538
0.5046	10.0	13440	0.3892	0.8441
0.5183	11.0	14784	0.3800	0.8465
0.5088	12.0	16128	0.3783	0.8551
0.5247	13.0	17472	0.3861	0.8502
0.5162	14.0	18816	0.3775	0.8514
0.5125	15.0	20160	0.3819	0.8538
0.4959	16.0	21504	0.3851	0.8502
0.5047	17.0	22848	0.3876	0.8477
0.5014	18.0	24192	0.3890	0.8465

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0