t5-base-finetuned-arxiver

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4141
• Rouge1: 88.4527
• Rouge2: 85.9716
• Rougel: 88.2515
• Rougelsum: 88.2522

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_restarts
• num_epochs: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.3076	1.0	1584	0.4287	88.3592	85.8872	88.1554	88.1659
0.2896	2.0	3168	0.4141	88.4527	85.9716	88.2515	88.2522
0.5806	3.0	4752	0.4071	88.4403	85.9628	88.2306	88.2359
0.5059	4.0	6336	0.3993	88.4437	85.9587	88.2291	88.2381

Framework versions

• Transformers 4.49.0
• Pytorch 2.7.0+cu126
• Datasets 3.5.1
• Tokenizers 0.21.1