Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use Hartunka/tiny_bert_rand_10_v1_mrpc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hartunka/tiny_bert_rand_10_v1_mrpc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_rand_10_v1_mrpc")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Hartunka/tiny_bert_rand_10_v1_mrpc") model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_rand_10_v1_mrpc") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6936274509803921, | |
| "eval_combined_score": 0.7490046488078799, | |
| "eval_f1": 0.8043818466353677, | |
| "eval_loss": 0.5896283388137817, | |
| "eval_runtime": 0.14, | |
| "eval_samples": 408, | |
| "eval_samples_per_second": 2914.512, | |
| "eval_steps_per_second": 14.287, | |
| "total_flos": 673316591603712.0, | |
| "train_loss": 0.47859985941932315, | |
| "train_runtime": 20.3015, | |
| "train_samples": 3668, | |
| "train_samples_per_second": 9033.83, | |
| "train_steps_per_second": 36.943 | |
| } |