sv3.4-bigbird-roberta-large

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

• Loss: 0.5284
• Mse: 0.3063
• Mae: 0.5284
• Rmse: 0.5534

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	Rmse
0.2148	0.1548	50	0.6346	0.4310	0.6346	0.6565
0.2317	0.3096	100	0.4964	0.2705	0.4964	0.5201
0.22	0.4644	150	0.5909	0.3752	0.5909	0.6125
0.1846	0.6192	200	0.5494	0.3274	0.5494	0.5722
0.1858	0.7740	250	0.5280	0.3046	0.5280	0.5520
0.1886	0.9288	300	0.5284	0.3063	0.5284	0.5534

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0