c1295bec-325e-4569-91f9-0db4c9762ee4
This model is a fine-tuned version of scb10x/llama-3-typhoon-v1.5-8b-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1583
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: 0.000217
- train_batch_size: 4
- eval_batch_size: 4
- seed: 170
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 3.0859 |
| 2.047 | 0.0028 | 50 | 2.6733 |
| 2.1434 | 0.0057 | 100 | 2.5131 |
| 2.0379 | 0.0085 | 150 | 2.5083 |
| 2.0508 | 0.0113 | 200 | 2.3921 |
| 1.9863 | 0.0141 | 250 | 2.3390 |
| 1.9769 | 0.0170 | 300 | 2.2515 |
| 1.9077 | 0.0198 | 350 | 2.2212 |
| 1.927 | 0.0226 | 400 | 2.1766 |
| 1.9741 | 0.0255 | 450 | 2.1585 |
| 1.9373 | 0.0283 | 500 | 2.1583 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 13
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso17/c1295bec-325e-4569-91f9-0db4c9762ee4
Base model
scb10x/llama-3-typhoon-v1.5-8b-instruct