t5-samsum

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

• Loss: 1.7097
• Rouge1: 43.1274
• Rouge2: 19.364
• Rougel: 35.6435
• Rougelsum: 39.6113
• Gen Len: 16.8840

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.01	1.0	1842	1.7905	40.9077	17.5516	33.9527	37.531	16.6960
1.8931	2.0	3684	1.7445	42.0004	18.4562	34.676	38.4273	16.8816
1.8391	3.0	5526	1.7248	42.6688	18.9855	35.2402	39.0387	16.7326
1.8104	4.0	7368	1.7121	42.9504	19.3162	35.6305	39.543	16.9829
1.7834	5.0	9210	1.7097	43.1274	19.364	35.6435	39.6113	16.8840

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2