llama-256-12L
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6964
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: 0.0018
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 6.9829 |
| 2.3602 | 0.0500 | 2014 | 2.3738 |
| 2.1514 | 0.1000 | 4028 | 2.1621 |
| 2.0689 | 0.1500 | 6042 | 2.0853 |
| 2.0211 | 0.2000 | 8056 | 2.0399 |
| 1.9966 | 0.2500 | 10070 | 2.0125 |
| 1.9684 | 0.3000 | 12084 | 1.9834 |
| 1.9348 | 0.3500 | 14098 | 1.9624 |
| 1.9139 | 0.4000 | 16112 | 1.9438 |
| 1.9061 | 0.4500 | 18126 | 1.9172 |
| 1.8702 | 0.5000 | 20140 | 1.8941 |
| 1.8539 | 0.5500 | 22154 | 1.8710 |
| 1.8164 | 0.6000 | 24168 | 1.8455 |
| 1.8036 | 0.6500 | 26182 | 1.8194 |
| 1.7791 | 0.7000 | 28196 | 1.7929 |
| 1.7427 | 0.7500 | 30210 | 1.7650 |
| 1.7179 | 0.8000 | 32224 | 1.7419 |
| 1.7015 | 0.8500 | 34238 | 1.7202 |
| 1.6827 | 0.9000 | 36252 | 1.7059 |
| 1.6726 | 0.9500 | 38266 | 1.6981 |
| 1.6695 | 1.0 | 40278 | 1.6964 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2