LongT5-XLarge-NSPCC

This model is a fine-tuned version of google/long-t5-tglobal-xl on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6843
• Rouge1: 0.5138
• Rouge2: 0.2297
• Rougel: 0.2999
• Rougelsum: 0.2995
• Gen Len: 337.6809

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: 0.0003
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.6911	0.9960	188	0.7292	0.4665	0.1826	0.2611	0.2611	360.7021
0.8701	1.9974	377	0.6967	0.4886	0.2073	0.2805	0.2799	365.3298
0.7849	2.9987	566	0.6808	0.5116	0.2302	0.2995	0.2997	332.3191
0.7769	3.9841	752	0.6843	0.5138	0.2297	0.2999	0.2995	337.6809

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1