tidy-tab-model-t5-small

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: 0.9997
• Rouge1: 0.7404
• Rouge2: 0.6249
• Rougel: 0.7403
• Rougelsum: 0.7413
• Gen Len: 6.9017

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 32

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.3461	3.7879	500	1.0711	0.7407	0.6192	0.736	0.7374	7.188
1.0075	7.5758	1000	0.9645	0.7313	0.6071	0.7304	0.7303	6.9274
0.7921	11.3636	1500	0.9563	0.7306	0.6079	0.7323	0.7325	6.7863
0.6587	15.1515	2000	0.9697	0.7382	0.6142	0.739	0.7397	6.8675
0.5579	18.9394	2500	0.9905	0.7388	0.6203	0.7378	0.7395	6.8718
0.4984	22.7273	3000	0.9997	0.7404	0.6249	0.7403	0.7413	6.9017

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1