results

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

• Loss: 0.3877
• Rouge1: 0.1916
• Rouge2: 0.0900
• Rougel: 0.1578
• Rougelsum: 0.1799

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: 8e-05
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	17	6.3841	0.0258	0.0043	0.0256	0.0255
No log	2.0	34	3.6116	0.0214	0.0020	0.0193	0.0203
No log	3.0	51	1.7410	0.0075	0.0016	0.0070	0.0071
No log	4.0	68	0.8219	0.0037	0.0013	0.0025	0.0025
No log	5.0	85	0.6052	0.0095	0.0050	0.0067	0.0074
No log	6.0	102	0.4904	0.1239	0.0566	0.0988	0.1164
No log	7.0	119	0.4477	0.1669	0.0745	0.1366	0.1570
No log	8.0	136	0.4218	0.1765	0.0781	0.1464	0.1665
No log	9.0	153	0.4044	0.1923	0.0955	0.1604	0.1845
No log	10.0	170	0.3937	0.1909	0.0967	0.1636	0.1794
No log	11.0	187	0.3887	0.1919	0.0893	0.1594	0.1795
No log	11.76	200	0.3877	0.1916	0.0900	0.1578	0.1799

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3