flan-t5-small-asap_t5_f3_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: 0.0674
• Rouge1: 79.2211
• Rouge2: 73.7497
• Rougel: 79.2024
• Rougelsum: 79.199
• Gen Len: 12.0360

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	0.1073	74.7884	68.0509	74.791	74.7345	12.0097
0.4704	2.0	542	0.0746	77.5977	71.7478	77.6371	77.6192	12.0332
0.4704	3.0	813	0.0710	78.5683	73.0397	78.5601	78.5631	12.0180
0.0852	4.0	1084	0.0671	78.7386	73.1012	78.7286	78.7115	12.0277
0.0852	5.0	1355	0.0674	79.2211	73.7497	79.2024	79.199	12.0360

Framework versions

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