FLANT5_base

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

• Loss: 0.0809
• Bleu Score: 25.4116
• Precision: 6.3321
• Recall: 6.3321
• Gen Len: 18.8124
• Err: 6.3321

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: 0.0002
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu Score	Precision	Recall	Gen Len	Err
0.2003	1.0	838	0.1201	24.1793	5.0179	5.0179	18.8017	5.0179
0.11	2.0	1676	0.0926	24.8581	5.7348	5.7348	18.81	5.7348
0.0832	3.0	2514	0.0833	25.3868	6.0932	6.0932	18.8136	6.0932
0.0674	4.0	3352	0.0809	25.4116	6.3321	6.3321	18.8124	6.3321

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0