big
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the big_data_new_train dataset. It achieves the following results on the evaluation set:
- Loss: 1.2365
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
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 4 | 2.6428 |
| No log | 2.0 | 8 | 2.5757 |
| 2.623 | 3.0 | 12 | 2.2870 |
| 2.623 | 4.0 | 16 | 1.6938 |
| 1.9392 | 5.0 | 20 | 1.4979 |
| 1.9392 | 6.0 | 24 | 1.3804 |
| 1.9392 | 7.0 | 28 | 1.3060 |
| 1.3428 | 8.0 | 32 | 1.2553 |
| 1.3428 | 9.0 | 36 | 1.2050 |
| 1.1313 | 10.0 | 40 | 1.1795 |
| 1.1313 | 11.0 | 44 | 1.1784 |
| 1.1313 | 12.0 | 48 | 1.1800 |
| 0.9106 | 13.0 | 52 | 1.1952 |
| 0.9106 | 14.0 | 56 | 1.2365 |
Framework versions
- PEFT 0.15.1
- Transformers 4.51.1
- Pytorch 2.7.1+cu126
- Datasets 3.5.0
- Tokenizers 0.21.0
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Gnomy19/llama3__newbig
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct