gpt2-cnn-dailymail-seed42

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

• Loss: nan
• Rouge1: 0.0603
• Rouge2: 0.0591
• Rougel: 0.0603
• Rougelsum: 0.0603

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.9192	0.1115	1000	nan	0.0607	0.0595	0.0607	0.0607
0.8063	0.2229	2000	nan	0.0603	0.0591	0.0603	0.0603
0.7731	0.3344	3000	nan	0.0602	0.0590	0.0602	0.0602
0.7575	0.4458	4000	nan	0.0603	0.0591	0.0603	0.0603

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1