anwgpt2-355m

My second attempt at a LLM.

Model Details

• Model Type: GPT-2
• Model Size: 354,823,168 parameters
• Base Model: gpt2-medium
• Dataset: Elriggs/openwebtext-100k
• Training Framework: Hugging Face Transformers

Intended Use

This model is intended for text generation tasks.

Training

The model was fine-tuned on the Elriggs/openwebtext-100k dataset.

Evaluation

Evaluation was not recorded.

Limitations

May perform repetitions, but very not likely.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Framework versions

• Transformers 4.56.0
• Pytorch 2.8.0+cu126
• Datasets 2.14.6
• Tokenizers 0.22.0