testdatasetpretraining

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

• Loss: 3.3016

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: 0.0006
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 320
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• training_steps: 1250
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.7934	2.4777	250	4.3840
3.6869	4.9554	500	3.6285
3.0053	7.4331	750	3.3747
2.6172	9.9108	1000	3.2880
2.3081	12.3885	1250	3.3016

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1