t5-small-finetuned-dialogsum-v2

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

• Loss: 1.3041
• Rouge1: 35.9525
• Rouge2: 13.1826
• Rougel: 30.3535
• Rougelsum: 32.2144
• Gen Len: 18.902

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: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.7356	1.0	779	1.4283	33.2097	10.6868	27.8451	29.9371	18.854
1.5042	2.0	1558	1.3706	34.3543	11.7561	28.8686	31.0041	18.842
1.4725	3.0	2337	1.3471	34.5334	11.9629	29.1625	31.1241	18.88
1.4329	4.0	3116	1.3299	35.31	12.6214	29.7381	31.7618	18.918
1.424	5.0	3895	1.3153	35.5141	13.2169	30.3033	32.0904	18.928
1.4044	6.0	4674	1.3090	35.7821	12.9692	30.3978	32.1945	18.912
1.3984	7.0	5453	1.3050	35.9485	13.3086	30.3416	32.2398	18.906
1.3908	8.0	6232	1.3041	35.9525	13.1826	30.3535	32.2144	18.902

Framework versions

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