typhoon-t5-finetuned3

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

• Loss: 0.4705

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	12	1.7729
No log	2.0	24	0.8577
No log	3.0	36	0.6314
No log	4.0	48	0.5748
No log	5.0	60	0.5426
No log	6.0	72	0.5223
No log	7.0	84	0.5081
No log	8.0	96	0.4975
No log	9.0	108	0.4893
No log	10.0	120	0.4828
No log	11.0	132	0.4783
No log	12.0	144	0.4747
No log	13.0	156	0.4725
No log	14.0	168	0.4709
No log	15.0	180	0.4705

Framework versions

• Transformers 4.56.0
• Pytorch 2.8.0+cu129
• Datasets 4.4.2
• Tokenizers 0.22.0