flan-t5-base-finetuned-openai-summarize_from_feedback

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

• Loss: 1.8833
• Rouge1: 29.3494
• Rouge2: 10.9406
• Rougel: 23.9907
• Rougelsum: 25.461
• Gen Len: 18.9265

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: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.7678	1.0	5804	1.8833	29.3494	10.9406	23.9907	25.461	18.9265
1.5839	2.0	11608	1.8992	29.6239	11.1795	24.2927	25.7183	18.9358
1.4812	3.0	17412	1.8929	29.8899	11.2855	24.4193	25.9219	18.9189
1.4198	4.0	23216	1.8939	29.8897	11.2606	24.3262	25.8642	18.9309
1.3612	5.0	29020	1.9105	29.8469	11.2112	24.2483	25.7884	18.9396
1.3279	6.0	34824	1.9170	30.038	11.3426	24.4385	25.9675	18.9328

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2