Text_Summarization

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

• Loss: 1.4199
• Rouge1: 0.2439
• Rouge2: 0.2006
• Rougel: 0.2365
• Rougelsum: 0.2366
• Gen Len: 18.9994

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: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.9264	1.0	1580	1.6705	0.2329	0.1842	0.223	0.223	18.9994
1.8184	2.0	3160	1.5849	0.2376	0.1894	0.2287	0.2288	18.9988
1.7427	3.0	4740	1.5382	0.2379	0.1914	0.2296	0.2297	18.9994
1.7067	4.0	6320	1.5073	0.2397	0.1943	0.2318	0.2318	19.0
1.6783	5.0	7900	1.4873	0.2406	0.1957	0.2329	0.2329	19.0
1.6585	6.0	9480	1.4716	0.242	0.1976	0.2343	0.2343	19.0
1.6457	7.0	11060	1.4572	0.2427	0.1988	0.2351	0.2351	19.0
1.6129	8.0	12640	1.4488	0.2433	0.1995	0.2357	0.2358	19.0
1.6014	9.0	14220	1.4405	0.2435	0.1999	0.236	0.236	19.0
1.5851	10.0	15800	1.4337	0.2439	0.2002	0.2364	0.2365	18.9994
1.5859	11.0	17380	1.4281	0.2436	0.2	0.2362	0.2362	19.0
1.573	12.0	18960	1.4247	0.244	0.2005	0.2365	0.2366	18.9994
1.5826	13.0	20540	1.4220	0.244	0.2007	0.2365	0.2365	18.9994
1.5674	14.0	22120	1.4205	0.2439	0.2006	0.2365	0.2365	18.9994
1.572	15.0	23700	1.4199	0.2439	0.2006	0.2365	0.2366	18.9994

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0