antphb/DS-Chatbox-gpt2-vietnamese-V3-FT

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

DS-Chatbox-gpt2-vietnamese-V3-FT

This model is a fine-tuned version of NlpHUST/gpt2-vietnamese on the None dataset. It achieves the following results on the evaluation set:

• —eval_loss: 3.4374
• —eval_runtime: 45.4992
• —evalsamplesper_second: 382.6
• —evalstepsper_second: 47.825
• —epoch: 0.27
• —step: 7100

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: 1.5e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 200
• —num_epochs: 5

Framework versions

• —Transformers 4.30.2
• —Pytorch 2.0.1+cu118
• —Datasets 2.13.0
• —Tokenizers 0.13.3