Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use JeremiahZ/bert-base-uncased-mrpc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JeremiahZ/bert-base-uncased-mrpc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="JeremiahZ/bert-base-uncased-mrpc")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("JeremiahZ/bert-base-uncased-mrpc") model = AutoModelForSequenceClassification.from_pretrained("JeremiahZ/bert-base-uncased-mrpc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from JeremiahZ/bert-base-uncased-mrpc: direct link, hf CLI and curl.
- Browser
- Download file 309 Bytes
-
https://huggingface.co/JeremiahZ/bert-base-uncased-mrpc/resolve/main/eval_results.json
- Command line
-
hf download hf://JeremiahZ/bert-base-uncased-mrpc/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/JeremiahZ/bert-base-uncased-mrpc/resolve/main/eval_results.json
309 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8578431372549019, | |
| "eval_combined_score": 0.8801000198059021, | |
| "eval_f1": 0.9023569023569024, | |
| "eval_loss": 0.557181179523468, | |
| "eval_runtime": 1.1896, | |
| "eval_samples": 408, | |
| "eval_samples_per_second": 342.971, | |
| "eval_steps_per_second": 42.871 | |
| } |