t5-small-finetuned-policy

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

• Loss: 2.6990
• Rouge1: 18.4909
• Rouge2: 10.2538
• Rougel: 15.7923
• Rougelsum: 17.7389
• Gen Len: 19.0

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: 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	9	3.8135	17.7379	9.4809	15.1302	17.2319	19.0
No log	2.0	18	3.1032	18.6526	10.4901	15.8718	17.8287	19.0
No log	3.0	27	2.7841	18.4909	10.2538	15.7923	17.7389	19.0
No log	4.0	36	2.6990	18.4909	10.2538	15.7923	17.7389	19.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1