t5-small-finetuned-dialogsum

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

• Loss: 1.3427
• Rouge1: 34.5499
• Rouge2: 12.3125
• Rougel: 29.2213
• Rougelsum: 31.2176
• Gen Len: 18.912

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.7379	1.0	779	1.4326	33.3809	10.7783	27.8592	29.9459	18.852
1.5112	2.0	1558	1.3788	33.9764	11.4064	28.4124	30.5554	18.868
1.4827	3.0	2337	1.3585	34.5398	12.0974	29.2394	31.1362	18.842
1.4516	4.0	3116	1.3477	34.4064	12.0904	29.1304	31.0513	18.908
1.4482	5.0	3895	1.3427	34.5499	12.3125	29.2213	31.2176	18.912

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0