Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("dv347/deberta-v3-base_smcalflow_balanced-classifier")
model = AutoModelForSequenceClassification.from_pretrained("dv347/deberta-v3-base_smcalflow_balanced-classifier")Quick Links
deberta-v3-base_smcalflow_balanced-classifier
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0390
- F1 Micro: 0.8614
- F1 Macro: 0.1143
- Exact Match: 0.125
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Exact Match |
|---|---|---|---|---|---|---|
| 0.0858 | 1.0 | 656 | 0.0804 | 0.6547 | 0.0284 | 0.0 |
| 0.0637 | 2.0 | 1312 | 0.0592 | 0.7628 | 0.0588 | 0.0056 |
| 0.0480 | 3.0 | 1968 | 0.0460 | 0.8277 | 0.0931 | 0.0458 |
| 0.0426 | 4.0 | 2624 | 0.0408 | 0.8548 | 0.1109 | 0.125 |
| 0.0405 | 5.0 | 3280 | 0.0390 | 0.8614 | 0.1143 | 0.125 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- -
Model tree for dv347/deberta-v3-base_smcalflow_balanced-classifier
Base model
microsoft/deberta-v3-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dv347/deberta-v3-base_smcalflow_balanced-classifier")