bea-rubric-match-2way-full

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

• Loss: 0.6745
• N Samples: 1654.0
• Accuracy: 0.8343
• Precision Macro: 0.8344
• Recall Macro: 0.8343
• F1 Macro: 0.8343
• Qwk: 0.6687

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: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	N Samples	Accuracy	Precision Macro	Recall Macro	F1 Macro	Qwk
0.4742	1.0	1768	0.4886	1654.0	0.7811	0.7813	0.7811	0.7811	0.5623
0.3412	2.0	3536	0.5374	1654.0	0.8204	0.8207	0.8204	0.8204	0.6409
0.2641	3.0	5304	0.6745	1654.0	0.8343	0.8344	0.8343	0.8343	0.6687

Framework versions

• Transformers 5.1.0
• Pytorch 2.10.0+cu128
• Datasets 4.6.1
• Tokenizers 0.22.2