typhoon-t5-finetuned-rag2

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: 0.3809

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	25	1.2873
No log	2.0	50	0.6654
No log	3.0	75	0.5487
No log	4.0	100	0.4922
No log	5.0	125	0.4609
No log	6.0	150	0.4376
No log	7.0	175	0.4210
No log	8.0	200	0.4087
No log	9.0	225	0.3997
No log	10.0	250	0.3932
No log	11.0	275	0.3886
No log	12.0	300	0.3851
No log	13.0	325	0.3827
No log	14.0	350	0.3813
No log	15.0	375	0.3809

Framework versions

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