simplewiki_upsampled_tom

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

• Loss: 3.1560

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.0268	0.5387	20	3.4559
3.3888	1.0774	40	3.2204
3.2608	1.6162	60	3.1798
3.0763	2.1549	80	3.1624
3.0912	2.6936	100	3.1531

Framework versions

• Transformers 4.44.1
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.19.1