flan-t5-base-v3-edos_labelled_aggregated

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

• Loss: 0.0663
• Rouge1: 95.8792
• Rouge2: 71.25
• Rougel: 95.875
• Rougelsum: 95.8792
• Gen Len: 4.7903

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0822	1.0	1750	0.0688	95.8375	71.9	95.8417	95.8333	4.805
0.0663	2.0	3500	0.0663	95.8792	71.25	95.875	95.8792	4.7903
0.0536	3.0	5250	0.0764	95.65	69.3	95.65	95.6667	4.758
0.0486	4.0	7000	0.0849	95.8333	69.925	95.8167	95.8333	4.7657
0.0467	5.0	8750	0.0946	95.825	69.8	95.8083	95.825	4.7635

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3