finetuning-sentiment-model

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

• Loss: 0.3181
• Accuracy: 0.8709
• F1: 0.8709

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: 32
• 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3675	0.2286	5000	0.3607	0.8434	0.8431
0.3524	0.4571	10000	0.3422	0.8527	0.8525
0.3419	0.6857	15000	0.3338	0.8563	0.8561
0.3294	0.9143	20000	0.3247	0.8627	0.8627
0.2989	1.1429	25000	0.3325	0.8662	0.8661
0.2981	1.3714	30000	0.3182	0.8677	0.8676
0.2789	1.6	35000	0.3225	0.8694	0.8694
0.2836	1.8286	40000	0.3181	0.8709	0.8709

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1