Mikivis/gpt2-large-imdb3

gpt2-large-imdb3 This model is a fine-tuned version of output_models/gpt2-large-news2 on the customized dataset.

Model description More information needed

Intended uses & limitations More information needed

Training procedure Training hyperparameters The following hyperparameters were used during training:

learningrate: 0.0003 trainbatchsize: 1 evalbatchsize: 8 seed: 42 distributedtype: multi-GPU numdevices: 6 totaltrainbatchsize: 6 totalevalbatchsize: 48 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lrschedulertype: linear numepochs: 3.0 Training results Framework versions Transformers 4.32.1 Pytorch 2.0.1+cu117 Datasets 2.10.1 Tokenizers 0.13.3