Question Answering
Transformers
PyTorch
TensorBoard
Habana
roberta
Generated from Trainer
Eval Results (legacy)
Instructions to use nbroad/rob-base-superqa2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nbroad/rob-base-superqa2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="nbroad/rob-base-superqa2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("nbroad/rob-base-superqa2") model = AutoModelForQuestionAnswering.from_pretrained("nbroad/rob-base-superqa2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from nbroad/rob-base-superqa2: direct link, hf CLI and curl.
- Browser
- Download file 695 Bytes
-
https://huggingface.co/nbroad/rob-base-superqa2/resolve/main/all_results.json
- Command line
-
hf download hf://nbroad/rob-base-superqa2/all_results.json
-
curl -L -o all_results.json https://huggingface.co/nbroad/rob-base-superqa2/resolve/main/all_results.json
695 Bytes
| { | |
| "epoch": 2.0, | |
| "eval_HasAns_exact": 69.19611355371003, | |
| "eval_HasAns_f1": 75.75383941256567, | |
| "eval_HasAns_total": 18423, | |
| "eval_NoAns_exact": 77.6109552879063, | |
| "eval_NoAns_f1": 77.6109552879063, | |
| "eval_NoAns_total": 6061, | |
| "eval_best_exact": 71.27920274464957, | |
| "eval_best_exact_thresh": 0.0, | |
| "eval_best_f1": 76.21356737043324, | |
| "eval_best_f1_thresh": 0.0, | |
| "eval_exact": 71.27920274464957, | |
| "eval_f1": 76.21356737043327, | |
| "eval_samples": 44895, | |
| "eval_total": 24484, | |
| "train_loss": 1.0762882447665056, | |
| "train_runtime": 1067.9056, | |
| "train_samples": 317774, | |
| "train_samples_per_second": 616.543, | |
| "train_steps_per_second": 2.41 | |
| } |