Text Classification
Transformers
PyTorch
English
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use Cheng98/bert-large-mnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cheng98/bert-large-mnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Cheng98/bert-large-mnli")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Cheng98/bert-large-mnli") model = AutoModelForSequenceClassification.from_pretrained("Cheng98/bert-large-mnli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from Cheng98/bert-large-mnli: direct link, hf CLI and curl.
- Browser
- Download file 659 Bytes
-
https://huggingface.co/Cheng98/bert-large-mnli/resolve/main/all_results.json
- Command line
-
hf download hf://Cheng98/bert-large-mnli/all_results.json
-
curl -L -o all_results.json https://huggingface.co/Cheng98/bert-large-mnli/resolve/main/all_results.json
659 Bytes
| { | |
| "epoch": 5.0, | |
| "epoch_mm": 5.0, | |
| "eval_accuracy": 0.8589913397860418, | |
| "eval_accuracy_mm": 0.8613710333604556, | |
| "eval_loss": 0.9180570840835571, | |
| "eval_loss_mm": 0.9132344126701355, | |
| "eval_runtime": 25.7835, | |
| "eval_runtime_mm": 25.7904, | |
| "eval_samples": 9815, | |
| "eval_samples_mm": 9832, | |
| "eval_samples_per_second": 380.669, | |
| "eval_samples_per_second_mm": 381.227, | |
| "eval_steps_per_second": 47.588, | |
| "eval_steps_per_second_mm": 47.653, | |
| "train_loss": 0.23671778235317364, | |
| "train_runtime": 11417.9442, | |
| "train_samples": 392702, | |
| "train_samples_per_second": 171.967, | |
| "train_steps_per_second": 10.748 | |
| } |