Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use Hartunka/tiny_bert_rand_50_v2_rte with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hartunka/tiny_bert_rand_50_v2_rte with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_rand_50_v2_rte")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Hartunka/tiny_bert_rand_50_v2_rte") model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_rand_50_v2_rte") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5776173285198556, | |
| "eval_loss": 0.6836854219436646, | |
| "eval_runtime": 0.1244, | |
| "eval_samples": 277, | |
| "eval_samples_per_second": 2227.399, | |
| "eval_steps_per_second": 16.082, | |
| "total_flos": 522373675991040.0, | |
| "train_loss": 0.5587728291749954, | |
| "train_runtime": 18.0236, | |
| "train_samples": 2490, | |
| "train_samples_per_second": 6907.6, | |
| "train_steps_per_second": 27.741 | |
| } |