sum_model_3r1e_3_20_with_extract

Extract all the texts at first. number of sentence in train data = 12 number of sentence in validation data = 12 words in train data: 350 words in summury: 32 after modification: 247 words in validation data: 344 words in summury: 32 after modification 247

This model is a fine-tuned version of weny22/sum_model_t5_saved on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3194
• Rouge1: 0.2073
• Rouge2: 0.0779
• Rougel: 0.1693
• Rougelsum: 0.1693
• Gen Len: 18.976

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: 0.003
• train_batch_size: 60
• eval_batch_size: 60
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	357	2.4971	0.1672	0.0411	0.1318	0.1319	18.9973
3.3592	2.0	714	2.1618	0.1794	0.0535	0.1425	0.1427	18.9927
2.3157	3.0	1071	2.0832	0.1978	0.0659	0.1587	0.1587	18.9887
2.3157	4.0	1428	2.0403	0.1964	0.0681	0.1568	0.157	18.994
2.0573	5.0	1785	2.0229	0.2041	0.073	0.165	0.1651	18.936
1.8803	6.0	2142	2.0163	0.1978	0.0708	0.1605	0.1605	18.9707
1.8803	7.0	2499	2.0227	0.2007	0.0721	0.1617	0.162	18.968
1.7658	8.0	2856	2.0233	0.2071	0.0756	0.1669	0.1669	18.9887
1.6171	9.0	3213	2.0440	0.2064	0.0754	0.1683	0.1682	18.986
1.5285	10.0	3570	2.0572	0.2066	0.0757	0.1672	0.1671	18.9873
1.5285	11.0	3927	2.0608	0.2055	0.076	0.1672	0.1672	18.9633
1.4229	12.0	4284	2.0915	0.2091	0.0801	0.1702	0.1703	18.9827
1.3307	13.0	4641	2.1216	0.2069	0.0764	0.167	0.1672	18.98
1.3307	14.0	4998	2.1477	0.2078	0.0768	0.1687	0.1688	18.9753
1.2601	15.0	5355	2.1685	0.2089	0.0784	0.1697	0.1697	18.9747
1.1685	16.0	5712	2.2118	0.2069	0.0784	0.1693	0.1694	18.9653
1.1162	17.0	6069	2.2417	0.2097	0.0797	0.1706	0.1707	18.9733
1.1162	18.0	6426	2.2659	0.2086	0.0781	0.1704	0.1705	18.9707
1.0569	19.0	6783	2.2943	0.2089	0.0795	0.1703	0.1705	18.976
1.014	20.0	7140	2.3194	0.2073	0.0779	0.1693	0.1693	18.976

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2