bartpho-word-base-finetuned-ee

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

• Loss: 0.0116
• Rouge1: 88.7018
• Rouge2: 79.3922
• Rougel: 88.6978
• Rougelsum: 88.7065
• Gen Len: 9.733

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0184	1.0	1492	0.0143	87.5521	76.9727	87.5302	87.5409	9.779
0.0124	2.0	2984	0.0125	87.4254	76.7809	87.4381	87.4401	9.9261
0.0093	3.0	4476	0.0116	88.7018	79.3922	88.6978	88.7065	9.733

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1