flan-t5-small-asap_t5_f0_prompt_adherence

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

• Loss: 0.0638
• Rouge1: 79.3921
• Rouge2: 73.8671
• Rougel: 79.4314
• Rougelsum: 79.397
• Gen Len: 12.0319

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
No log	1.0	271	0.0983	76.0693	68.9433	76.0621	76.077	12.0
0.4745	2.0	542	0.0715	76.9123	70.6854	76.9889	76.9047	12.0083
0.4745	3.0	813	0.0652	78.4337	72.7285	78.4968	78.4136	12.0180
0.0868	4.0	1084	0.0645	79.1916	73.6922	79.2211	79.1421	12.0277
0.0868	5.0	1355	0.0638	79.3921	73.8671	79.4314	79.397	12.0319

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2