t5-small-finetuned-vehidefecttwo

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

• Loss: 1.2260
• Rouge1: 0.3205
• Rouge2: 0.0694
• Rougel: 0.2564
• Rougelsum: 0.2564
• Gen Len: 0.3167

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: 20
• eval_batch_size: 20
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	21	3.7438	48.9925	32.0494	45.5108	45.2375	15.0417
No log	2.0	42	1.7784	19.2369	11.715	17.4777	17.7156	7.2583
No log	3.0	63	1.3420	7.208	4.3119	6.7668	6.9177	3.5083
No log	4.0	84	1.2382	2.1269	0.8562	1.8271	1.8788	1.575
No log	5.0	105	1.2285	0.5256	0.119	0.4615	0.4615	0.6333
No log	6.0	126	1.2277	0.3647	0.0694	0.2564	0.3006	0.475
No log	7.0	147	1.2260	0.3205	0.0694	0.2564	0.2564	0.3167
No log	8.0	168	1.2260	0.3205	0.0694	0.2564	0.2564	0.3167

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3