gpt2-small-vietnamese-students-feedback

This model is a fine-tuned version of NlpHUST/gpt2-vietnamese on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5515

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: 7e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss
2.9154	3.5714	50	2.7091
2.5882	7.1429	100	2.6147
2.4831	10.7143	150	2.5797
2.4193	14.2857	200	2.5626
2.3697	17.8571	250	2.5549
2.3309	21.4286	300	2.5518
2.3073	25.0	350	2.5516
2.2897	28.5714	400	2.5515

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.0.1
• Tokenizers 0.21.1