t5-base-Clakmann-thesis-epoch10

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5727
• Rouge1: 0.2268
• Rouge2: 0.0853
• Rougel: 0.215
• Rougelsum: 0.2157
• Gen Len: 14.2621

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8844	1.0	5029	1.6766	0.2148	0.0756	0.2044	0.2045	13.7397
1.7073	2.0	10058	1.6168	0.2196	0.0792	0.2099	0.2102	13.8238
1.6487	3.0	15087	1.5948	0.2199	0.0794	0.209	0.2091	14.3399
1.5773	4.0	20116	1.5800	0.2252	0.0816	0.2157	0.2164	13.9383
1.5114	5.0	25145	1.5770	0.2229	0.0798	0.212	0.2126	14.2567
1.4688	6.0	30174	1.5703	0.2255	0.0848	0.2158	0.2164	13.9973
1.4283	7.0	35203	1.5673	0.2237	0.0834	0.2125	0.2129	14.0966
1.4166	8.0	40232	1.5702	0.2276	0.0866	0.2153	0.2159	14.3453
1.3978	9.0	45261	1.5706	0.2274	0.0864	0.216	0.2166	14.2272
1.3688	10.0	50290	1.5727	0.2268	0.0853	0.215	0.2157	14.2621

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3