metadata
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: arabic-nano-gpt
results: []
arabic-nano-gpt
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.9452
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.1376 | 100 | 7.6593 |
| No log | 2.2752 | 200 | 7.3363 |
| No log | 3.4127 | 300 | 7.0512 |
| No log | 4.5503 | 400 | 6.9452 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.0
- Datasets 3.0.1
- Tokenizers 0.20.1