output_augmented

This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2795

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.3758	0.32	100	1.3474
1.3576	0.64	200	1.3313
1.3505	0.96	300	1.3184
1.2681	1.2784	400	1.3041
1.26	1.5984	500	1.2963
1.235	1.9184	600	1.2880
1.1949	2.2368	700	1.2813
1.1916	2.5568	800	1.2819
1.1803	2.8768	900	1.2795

Framework versions

• Transformers 4.57.3
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.22.1