# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("dusersad12/BestCheckpoint-Demo")
model = AutoModelForSequenceClassification.from_pretrained("dusersad12/BestCheckpoint-Demo", device_map="auto")Quick Links
BestCheckpoint Demo
This model checkpoint was selected from a hyperparameter sweep as the best-performing run.
Evaluation Metrics
| Metric | Value |
|---|---|
| Validation Accuracy | 0.861 |
| Validation Loss | 0.412 |
| Validation F1 | 0.855 |
Training Configuration
The best run used the following hyperparameters:
| Hyperparameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| Weight Decay | 0.1 |
| Epochs | 10 |
| Batch Size | 32 |
How to Use
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained("BestCheckpoint-Demo")
tokenizer = AutoTokenizer.from_pretrained("BestCheckpoint-Demo")
License
This model is released under the Apache 2.0 license.
- Downloads last month
- 17
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dusersad12/BestCheckpoint-Demo")