longt5_xl_gov_bp_20

This model is a fine-tuned version of learn3r/longt5_xl_gov_bp_15 on the learn3r/gov_report_bp dataset. It achieves the following results on the evaluation set:

• Loss: 1.3539

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6879	1.0	34	1.3539
0.4865	1.99	68	1.3666
0.436	2.99	102	1.5058
0.3893	3.99	136	1.4800
0.3517	4.98	170	1.5911

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3