# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("EshAhm/Paper-Matcher-scibert")
model = AutoModelForSequenceClassification.from_pretrained("EshAhm/Paper-Matcher-scibert", device_map="auto")Quick Links
Paper-Matcher-scibert
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6140
- Accuracy: 0.865
- Macro F1: 0.865
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: 16
- eval_batch_size: 32
- 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: 75
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|---|---|---|---|---|---|
| 0.3351 | 1.0 | 125 | 0.3319 | 0.885 | 0.8848 |
| 0.2588 | 2.0 | 250 | 0.3041 | 0.89 | 0.8899 |
| 0.2228 | 3.0 | 375 | 0.6524 | 0.8 | 0.7971 |
| 0.1493 | 4.0 | 500 | 0.5196 | 0.87 | 0.8699 |
| 0.0623 | 5.0 | 625 | 0.6140 | 0.865 | 0.865 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.2
- Downloads last month
- 51
Model tree for EshAhm/Paper-Matcher-scibert
Base model
allenai/scibert_scivocab_uncased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="EshAhm/Paper-Matcher-scibert")