Meta_Llama3_LORA_Persian_MCQ_16_32_v1
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0125
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: 4
- eval_batch_size: 4
- seed: 100
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2293 | 1.0 | 375 | 1.1947 |
| 0.9835 | 2.0 | 750 | 1.0519 |
| 0.8834 | 3.0 | 1125 | 1.0125 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.44.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 214
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Kamyar-zeinalipour/PMCQ-Llama3.1-8b
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct