results_t5base

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

• Loss: 0.3660
• Rouge1: 0.904
• Rouge2: 0.8349
• Rougel: 0.8863
• Gen Len: 237.7528

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
0.6675	0.8969	200	0.5012	0.8797	0.7929	0.8578	236.6854
0.5426	1.7937	400	0.4133	0.8937	0.8192	0.8751	237.7101
0.2768	2.6906	600	0.3971	0.8984	0.8262	0.8797	237.7551
0.4136	3.5874	800	0.3864	0.9001	0.8295	0.8824	237.7483
0.3067	4.4843	1000	0.3815	0.9011	0.8307	0.8833	237.7506
0.4425	5.3812	1200	0.3735	0.9015	0.8319	0.884	237.7528
0.4285	6.2780	1400	0.3720	0.9026	0.8334	0.885	237.7528
0.3025	7.1749	1600	0.3687	0.9039	0.8345	0.8859	237.7528
0.2699	8.0717	1800	0.3681	0.9034	0.8341	0.8857	237.7528
0.4072	8.9686	2000	0.3657	0.9039	0.8349	0.8862	237.7528
0.4555	9.8655	2200	0.3660	0.904	0.8349	0.8863	237.7528

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.2
• Datasets 2.19.1
• Tokenizers 0.19.1