metadata
license: apache-2.0
base_model: HooshvareLab/roberta-fa-zwnj-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
model-index:
- name: roberta-fa-zwnj-base_v2
results: []
roberta-fa-zwnj-base_v2
This model is a fine-tuned version of HooshvareLab/roberta-fa-zwnj-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3459
- Accuracy: 0.6322
- F1: 0.6314
- Precision: 0.6344
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| No log | 1.0 | 221 | 1.1727 | 0.5051 | 0.4774 | 0.5339 |
| No log | 2.0 | 442 | 0.9745 | 0.5993 | 0.5974 | 0.6020 |
| 1.0847 | 3.0 | 663 | 0.9534 | 0.6390 | 0.6364 | 0.6376 |
| 1.0847 | 4.0 | 884 | 0.9851 | 0.6504 | 0.6494 | 0.6559 |
| 0.6653 | 5.0 | 1105 | 1.0650 | 0.6300 | 0.6302 | 0.6337 |
| 0.6653 | 6.0 | 1326 | 1.1519 | 0.6413 | 0.6401 | 0.6450 |
| 0.4049 | 7.0 | 1547 | 1.2131 | 0.6356 | 0.6358 | 0.6362 |
| 0.4049 | 8.0 | 1768 | 1.2801 | 0.6356 | 0.6355 | 0.6360 |
| 0.4049 | 9.0 | 1989 | 1.3335 | 0.6322 | 0.6306 | 0.6320 |
| 0.2507 | 10.0 | 2210 | 1.3459 | 0.6322 | 0.6314 | 0.6344 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2