Instructions to use tweettemposhift/topic-topic_temporal-roberta-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/topic-topic_temporal-roberta-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tweettemposhift/topic-topic_temporal-roberta-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/topic-topic_temporal-roberta-large") model = AutoModelForSequenceClassification.from_pretrained("tweettemposhift/topic-topic_temporal-roberta-large") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.11689302325248718, "test/eval_f1": 0.7325870646766169, "test/eval_f1_macro": 0.5426379824269185, "test/eval_accuracy": 0.5104228707564026, "test/eval_runtime": 14.0424, "test/eval_samples_per_second": 119.567, "test/eval_steps_per_second": 14.955, "test_1/eval_loss": 0.11518736183643341, "test_1/eval_f1": 0.7275832621690863, "test_1/eval_f1_macro": 0.5211520550900638, "test_1/eval_accuracy": 0.5346062052505967, "test_1/eval_runtime": 3.6097, "test_1/eval_samples_per_second": 116.077, "test_1/eval_steps_per_second": 14.683, "test_2/eval_loss": 0.11647367477416992, "test_2/eval_f1": 0.73421926910299, "test_2/eval_f1_macro": 0.5584097513593045, "test_2/eval_accuracy": 0.4916467780429594, "test_2/eval_runtime": 3.766, "test_2/eval_samples_per_second": 111.26, "test_2/eval_steps_per_second": 14.073, "test_3/eval_loss": 0.11921310424804688, "test_3/eval_f1": 0.7346938775510203, "test_3/eval_f1_macro": 0.48597234868794, "test_3/eval_accuracy": 0.5155131264916468, "test_3/eval_runtime": 3.8181, "test_3/eval_samples_per_second": 109.739, "test_3/eval_steps_per_second": 13.881, "test_4/eval_loss": 0.11669933795928955, "test_4/eval_f1": 0.7336601307189542, "test_4/eval_f1_macro": 0.5379013138721028, "test_4/eval_accuracy": 0.5, "test_4/eval_runtime": 3.5703, "test_4/eval_samples_per_second": 118.199, "test_4/eval_steps_per_second": 14.845} |