llama3.1-1b-coding-gpt4o-100k2
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6745
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: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 512
- total_eval_batch_size: 256
- 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 |
|---|---|---|---|
| 1.2024 | 1.0 | 34 | 1.7381 |
| 1.0846 | 2.0 | 68 | 1.6923 |
| 1.0447 | 3.0 | 102 | 1.6731 |
| 1.0207 | 4.0 | 136 | 1.6660 |
| 1.0039 | 5.0 | 170 | 1.6681 |
| 0.9957 | 6.0 | 204 | 1.6620 |
| 0.9793 | 7.0 | 238 | 1.6656 |
| 0.9761 | 8.0 | 272 | 1.6707 |
| 0.9678 | 9.0 | 306 | 1.6741 |
| 0.9709 | 10.0 | 340 | 1.6745 |
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
- 14
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/llama3-1b-coding-gpt4o-100k2
Base model
meta-llama/Llama-3.2-1B