metadata
library_name: transformers
license: cc-by-4.0
base_model: allegro/herbert-large-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: herbert-large-cased-topic_classification
results: []
herbert-large-cased-topic_classification
This model is a fine-tuned version of allegro/herbert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5731
- Precision: 0.9195
- Recall: 0.9014
- F1: 0.9082
- Accuracy: 0.9167
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 44 | 0.3576 | 0.9119 | 0.8684 | 0.8815 | 0.9020 |
| No log | 2.0 | 88 | 0.3342 | 0.9085 | 0.9027 | 0.8973 | 0.9069 |
| No log | 3.0 | 132 | 0.4985 | 0.9121 | 0.8826 | 0.8916 | 0.9020 |
| No log | 4.0 | 176 | 0.6182 | 0.8998 | 0.8858 | 0.8911 | 0.9020 |
| No log | 5.0 | 220 | 0.5089 | 0.9056 | 0.8880 | 0.8944 | 0.9020 |
| No log | 6.0 | 264 | 0.6806 | 0.9061 | 0.8593 | 0.8766 | 0.8922 |
| No log | 7.0 | 308 | 0.5604 | 0.9127 | 0.8866 | 0.8969 | 0.9069 |
| No log | 8.0 | 352 | 0.5780 | 0.9157 | 0.9036 | 0.9077 | 0.9167 |
| No log | 9.0 | 396 | 0.5733 | 0.9195 | 0.9014 | 0.9082 | 0.9167 |
| No log | 10.0 | 440 | 0.5731 | 0.9195 | 0.9014 | 0.9082 | 0.9167 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1