metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
model-index:
- name: distil_final
results: []
language:
- ar
distil_final
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5805
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: 0.0002
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.0926 | 0.32 | 10 | 3.9348 |
| 3.9237 | 0.64 | 20 | 4.0141 |
| 3.8084 | 0.96 | 30 | 3.8194 |
| 3.6561 | 1.28 | 40 | 3.6860 |
| 3.4836 | 1.6 | 50 | 3.6023 |
| 3.5731 | 1.92 | 60 | 3.5904 |
| 3.497 | 2.24 | 70 | 3.6435 |
| 3.34 | 2.56 | 80 | 3.5359 |
| 3.2943 | 2.88 | 90 | 3.6003 |
| 3.0902 | 3.2 | 100 | 3.6634 |
| 3.1061 | 3.52 | 110 | 3.6059 |
| 3.1395 | 3.84 | 120 | 3.5805 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1