flan-t5-large-finetuned-xsum

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

• Loss: nan
• Rouge1: 14.0152
• Rouge2: 6.2802
• Rougel: 13.7963
• Rougelsum: 13.9306
• Gen Len: 6.8696

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	13	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	2.0	26	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	3.0	39	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	4.0	52	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	5.0	65	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	6.0	78	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	7.0	91	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	8.0	104	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	9.0	117	nan	14.0152	6.2802	13.7963	13.9306	6.8696
No log	10.0	130	nan	14.0152	6.2802	13.7963	13.9306	6.8696

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3