Instructions to use tweettemposhift/hate-hate_balance_temporal-roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/hate-hate_balance_temporal-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tweettemposhift/hate-hate_balance_temporal-roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/hate-hate_balance_temporal-roberta-base") model = AutoModelForSequenceClassification.from_pretrained("tweettemposhift/hate-hate_balance_temporal-roberta-base") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.8775679469108582, "test/eval_f1": 0.35406698564593303, "test/eval_accuracy": 0.8169491525423729, "test/eval_runtime": 2.1953, "test/eval_samples_per_second": 671.882, "test/eval_steps_per_second": 84.27, "test_1/eval_loss": 0.9689406752586365, "test_1/eval_f1": 0.33027522935779813, "test_1/eval_accuracy": 0.8016304347826086, "test_1/eval_runtime": 0.5588, "test_1/eval_samples_per_second": 658.529, "test_1/eval_steps_per_second": 82.316, "test_2/eval_loss": 0.7785986065864563, "test_2/eval_f1": 0.38775510204081637, "test_2/eval_accuracy": 0.8369565217391305, "test_2/eval_runtime": 0.563, "test_2/eval_samples_per_second": 653.599, "test_2/eval_steps_per_second": 81.7, "test_3/eval_loss": 0.7462887763977051, "test_3/eval_f1": 0.40816326530612246, "test_3/eval_accuracy": 0.842391304347826, "test_3/eval_runtime": 0.5611, "test_3/eval_samples_per_second": 655.856, "test_3/eval_steps_per_second": 81.982, "test_4/eval_loss": 1.0153206586837769, "test_4/eval_f1": 0.3008849557522124, "test_4/eval_accuracy": 0.7870619946091644, "test_4/eval_runtime": 0.5662, "test_4/eval_samples_per_second": 655.267, "test_4/eval_steps_per_second": 83.012} |