phrase_bank_v1

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

• Loss: 0.2072
• Accuracy: 0.9685
• Precision: 0.9570
• Recall: 0.9458
• F1: 0.9479

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: 64
• eval_batch_size: 64
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	18	0.6233	0.7402	0.4449	0.5471	0.4866
No log	2.0	36	0.6032	0.7795	0.7077	0.6534	0.6198
No log	3.0	54	0.4921	0.7874	0.8024	0.6014	0.5935
No log	4.0	72	0.2028	0.9370	0.9361	0.9046	0.9182
No log	5.0	90	0.1545	0.9606	0.9573	0.9335	0.9430
No log	6.0	108	0.1373	0.9606	0.9514	0.9335	0.9396
No log	7.0	126	0.1093	0.9685	0.9570	0.9458	0.9479
No log	8.0	144	0.1646	0.9606	0.9514	0.9335	0.9396
No log	9.0	162	0.2421	0.9606	0.9514	0.9335	0.9396
No log	10.0	180	0.2072	0.9685	0.9570	0.9458	0.9479

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.1