BaViT_Base_Finetune_v0

This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4516
• Sacrebleu: 7.9929

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: 100
• eval_batch_size: 100
• seed: 42
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu
0.6988	1.0	468	0.6266	2.2994
0.6014	2.0	936	0.5592	4.0780
0.5548	3.0	1404	0.5231	4.9356
0.5239	4.0	1872	0.5022	5.6738
0.5063	5.0	2340	0.4875	6.2733
0.4849	6.0	2808	0.4769	6.7126
0.4701	7.0	3276	0.4705	6.9856
0.4555	8.0	3744	0.4651	7.2721
0.4524	9.0	4212	0.4601	7.5539
0.4388	10.0	4680	0.4571	7.6076
0.4341	11.0	5148	0.4549	7.7267
0.4231	12.0	5616	0.4536	7.9165
0.4174	13.0	6084	0.4519	7.9585
0.4209	14.0	6552	0.4515	7.9864
0.4167	15.0	7020	0.4516	7.9929

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0