hw-intent-atis

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

• Loss: 13.3164

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.0266	1.6	500	11.9988
0.0444	3.21	1000	11.4742
0.0314	4.81	1500	12.1216
0.0163	6.41	2000	12.8759
0.0104	8.01	2500	13.1008
0.0052	9.62	3000	13.2233
0.0046	11.22	3500	13.2846
0.0022	12.82	4000	13.3164

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2