trainer_wheel_model

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

• Loss: 2.8911
• Refined F1: 6.5281
• Meteor: 14.3360
• Bert Score F1: 80.5293
• Rouge1: 11.9272
• Rouge2: 1.9063
• Rougel: 8.2440

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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	Refined F1	Meteor	Bert Score F1	Rouge1	Rouge2	Rougel
3.1114	1.0	3535	2.9473	6.3827	14.0121	80.5994	12.0441	1.9421	8.4024
3.021	2.0	7070	2.9119	6.4954	14.0416	80.4270	11.8023	1.9007	8.2623
2.9904	3.0	10605	2.8950	6.5251	14.2535	80.5717	12.0747	1.9382	8.3584
2.9729	4.0	14140	2.8911	6.5281	14.3360	80.5293	11.9272	1.9063	8.2440

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1