cardiffnlp/tweet_eval
Viewer • Updated • 201k • 37.2k • 144
How to use TransferGraph/ncduy_roberta-imdb-sentiment-analysis-finetuned-lora-tweet_eval_irony with PEFT:
from peft import PeftModel
from transformers import AutoModelForSequenceClassification
base_model = AutoModelForSequenceClassification.from_pretrained("ncduy/roberta-imdb-sentiment-analysis")
model = PeftModel.from_pretrained(base_model, "TransferGraph/ncduy_roberta-imdb-sentiment-analysis-finetuned-lora-tweet_eval_irony")This model is a fine-tuned version of ncduy/roberta-imdb-sentiment-analysis on the tweet_eval dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| accuracy | train_loss | epoch |
|---|---|---|
| 0.5131 | None | 0 |
| 0.5885 | 0.7327 | 0 |
| 0.6147 | 0.6602 | 1 |
| 0.6890 | 0.5931 | 2 |
| 0.7183 | 0.5550 | 3 |
| 0.7267 | 0.5275 | 4 |
| 0.7058 | 0.5040 | 5 |
| 0.7330 | 0.4999 | 6 |
| 0.7351 | 0.4875 | 7 |
Base model
ncduy/roberta-imdb-sentiment-analysis