llama3.1-3b-coding-gpt4o-100k2
This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6301
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: 0.002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0031 | 1.0 | 68 | 1.5510 |
| 0.9546 | 2.0 | 136 | 1.5149 |
| 0.936 | 3.0 | 204 | 1.5085 |
| 0.9186 | 4.0 | 272 | 1.5175 |
| 0.8948 | 5.0 | 340 | 1.5302 |
| 0.8742 | 6.0 | 408 | 1.5502 |
| 0.8556 | 7.0 | 476 | 1.5617 |
| 0.8428 | 8.0 | 544 | 1.5965 |
| 0.8168 | 9.0 | 612 | 1.6217 |
| 0.8191 | 9.8593 | 670 | 1.6301 |
Framework versions
- PEFT 0.15.1
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for llama-duo/llama3-3b-coding-gpt4o-100k2
Base model
meta-llama/Llama-3.2-3B