metadata
library_name: transformers
license: apache-2.0
base_model: MoritzLaurer/ModernBERT-large-zeroshot-v2.0
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: ModernBERT-hf-posts-classifier
results: []
ModernBERT-hf-posts-classifier
This model is a fine-tuned version of MoritzLaurer/ModernBERT-large-zeroshot-v2.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1848
- F1: 0.2079
- Accuracy: 0.1569
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| No log | 1.0 | 15 | 0.2568 | 0.0560 | 0.0196 |
| No log | 2.0 | 30 | 0.2353 | 0.0665 | 0.0784 |
| No log | 3.0 | 45 | 0.2007 | 0.1981 | 0.0980 |
| No log | 4.0 | 60 | 0.1878 | 0.2129 | 0.0980 |
| No log | 4.7018 | 70 | 0.1848 | 0.2079 | 0.1569 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0