clinc/clinc_oos
Viewer โข Updated โข 59.3k โข 22.4k โข 23
How to use wangsherpa/distilbert-base-uncased-distilled-clinc with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="wangsherpa/distilbert-base-uncased-distilled-clinc") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("wangsherpa/distilbert-base-uncased-distilled-clinc")
model = AutoModelForSequenceClassification.from_pretrained("wangsherpa/distilbert-base-uncased-distilled-clinc", device_map="auto")This model is a fine-tuned version of distilbert-base-uncased on the clinc_oos 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:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 318 | 1.6639 | 0.7397 |
| 2.0085 | 2.0 | 636 | 0.8483 | 0.8616 |
| 2.0085 | 3.0 | 954 | 0.4984 | 0.9155 |
| 0.7685 | 4.0 | 1272 | 0.3698 | 0.9326 |
| 0.3717 | 5.0 | 1590 | 0.3223 | 0.9442 |
| 0.3717 | 6.0 | 1908 | 0.3012 | 0.9477 |
| 0.269 | 7.0 | 2226 | 0.2905 | 0.9484 |
| 0.236 | 8.0 | 2544 | 0.2864 | 0.9494 |
| 0.236 | 9.0 | 2862 | 0.2848 | 0.9494 |