This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base on the None dataset.
It achieves the following results on the evaluation set:
eval_loss: 0.3651
eval_label_0_f1: 0.7305
eval_label_0_accuracy: 0.9498
eval_label_1_f1: 0.8458
eval_label_1_accuracy: 0.8573
eval_label_2_f1: 0.7816
eval_label_2_accuracy: 0.9576
eval_label_3_f1: 0.7638
eval_label_3_accuracy: 0.9097
eval_label_4_f1: 0.6438
eval_label_4_accuracy: 0.9420
eval_label_5_f1: 0.6857
eval_label_5_accuracy: 0.9755
eval_runtime: 5.7337
eval_samples_per_second: 156.444
eval_steps_per_second: 5.058
epoch: 5.0
step: 795
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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
