Long_attention_Longformer

This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8677
• Bleu: 20.8728
• Meteor: 0.4023
• Comet: 0.4747

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Meteor	Comet
2.2865	0.9994	786	2.1788	13.5745	0.2981	0.3646
2.0517	2.0	1573	1.8939	19.3520	0.3838	0.4486
1.9429	2.9981	2358	1.8313	20.8728	0.4023	0.4747

Framework versions

• Transformers 4.41.2
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.19.1