ML Intern API IMDb DistilBERT Example
This model was produced by a public ML Intern API example run.
- Base model:
distilbert-base-uncased - Dataset:
imdb - Train subset: 1,000 examples
- Eval subset: 200 examples
- Training: 60 Trainer steps, batch size 16, learning rate 5e-5
- Eval metrics:
{"epoch": 0.9523809523809523, "eval_accuracy": 0.815, "eval_loss": 0.4811082184314728, "eval_runtime": 24.2035, "eval_samples_per_second": 8.263, "eval_steps_per_second": 0.289}
Generated by ML Intern
This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.
- Try ML Intern: https://smolagents-ml-intern.hf.space
- Source code: https://github.com/huggingface/ml-intern
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = 'abidlabs/ml-intern-api-imdb-distilbert-20260613-020123'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.