veronica-girolimetti/one-shot-colab-originalflant5

test-dialogue-summarization

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

• Loss: 2.3647
• Rouge1: 43.7125
• Rouge2: 20.8696
• Rougel: 20.4726
• Rougelsum: 20.4726
• Gen Len: 15.005

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: 7
• eval_batch_size: 7
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.9658	1.0	186	2.6549	47.8375	19.6224	19.3309	19.3309	15.65
2.8292	2.0	372	2.5659	46.3424	19.6335	20.017	20.017	14.965
2.7598	3.0	558	2.5190	45.6451	19.7504	20.0363	20.0363	15.07
2.6531	4.0	744	2.4796	45.0646	19.649	19.6929	19.6929	14.9
2.5946	5.0	930	2.4526	44.0678	19.4902	20.0463	20.0463	15.01
2.5868	6.0	1116	2.4340	44.7027	19.7504	20.0391	20.0391	14.765
2.5896	7.0	1302	2.4179	44.5941	19.8653	20.0073	20.0073	14.745
2.5626	8.0	1488	2.3981	44.6259	19.9902	20.3022	20.3022	15.1
2.4633	9.0	1674	2.3921	44.6047	20.4376	20.3104	20.3104	14.97
2.5217	10.0	1860	2.3826	44.2188	19.9486	20.3353	20.3353	14.995
2.48	11.0	2046	2.3766	44.4635	20.6357	20.3618	20.3618	14.99
2.4502	12.0	2232	2.3723	44.0093	20.7614	20.3647	20.3647	14.995
2.4946	13.0	2418	2.3677	43.8165	20.947	20.4526	20.4526	15.035
2.4372	14.0	2604	2.3651	44.0221	20.9248	20.5763	20.5763	14.92
2.4606	15.0	2790	2.3647	43.7125	20.8696	20.4726	20.4726	15.005

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0