finetuningtest

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

• Loss: 3.7542

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: 0.0005
• train_batch_size: 15
• eval_batch_size: 15
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 120
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	180	5.4889
No log	2.0	360	4.6958
No log	3.0	540	4.2670
No log	4.0	720	4.0355
No log	5.0	900	3.9067
No log	6.0	1080	3.8282
No log	7.0	1260	3.7552
No log	8.0	1440	3.7185
No log	9.0	1620	3.7286
No log	10.0	1800	3.7542

Framework versions

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