typhoon-t5-finetuned

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: 0.3899

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	35	0.7777
No log	2.0	70	0.5711
No log	3.0	105	0.5039
No log	4.0	140	0.4666
No log	5.0	175	0.4435
No log	6.0	210	0.4294
No log	7.0	245	0.4184
No log	8.0	280	0.4104
No log	9.0	315	0.4042
No log	10.0	350	0.3996
No log	11.0	385	0.3959
No log	12.0	420	0.3932
No log	13.0	455	0.3913
No log	14.0	490	0.3903
0.6133	15.0	525	0.3899

Framework versions

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