finetuned-ytu

This model is a fine-tuned version of ytu-ce-cosmos/turkish-gpt2-large on an ucekmez/openorca-tr translated dataset. This is just a checkpoint for training almost 12hrs! Check the TensorBoard.

Model description

More information needed

Intended uses & limitations

This is just a checkpoint. Needs to be trained further.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 4e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2