Instructions to use ChrisZeng/twitter-roberta-base-efl-hateval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ChrisZeng/twitter-roberta-base-efl-hateval with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ChrisZeng/twitter-roberta-base-efl-hateval")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ChrisZeng/twitter-roberta-base-efl-hateval") model = AutoModelForSequenceClassification.from_pretrained("ChrisZeng/twitter-roberta-base-efl-hateval") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.6998718119161117, | |
| "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-211", | |
| "epoch": 1.0, | |
| "global_step": 211, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.666666666666666e-07, | |
| "loss": 0.5392, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7, | |
| "eval_f1": 0.6998718119161117, | |
| "eval_loss": 0.4048246741294861, | |
| "eval_runtime": 5.0256, | |
| "eval_samples_per_second": 596.939, | |
| "eval_steps_per_second": 74.617, | |
| "step": 211 | |
| } | |
| ], | |
| "max_steps": 6330, | |
| "num_train_epochs": 30, | |
| "total_flos": 1430448984655488.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |