metadata
library_name: peft
license: llama3.2
base_model: NousResearch/Llama-3.2-1B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: a0779866-1f51-4925-860d-00cf019236b0
results: []
a0779866-1f51-4925-860d-00cf019236b0
This model is a fine-tuned version of NousResearch/Llama-3.2-1B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7908
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: 0.000204
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- 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 | 0.0002 | 1 | 1.3080 |
| 0.9993 | 0.0121 | 50 | 1.0143 |
| 0.9247 | 0.0242 | 100 | 1.0134 |
| 0.8933 | 0.0363 | 150 | 0.9623 |
| 0.9655 | 0.0484 | 200 | 0.9523 |
| 0.8654 | 0.0605 | 250 | 0.8886 |
| 0.8406 | 0.0726 | 300 | 0.8539 |
| 0.8368 | 0.0847 | 350 | 0.8226 |
| 0.785 | 0.0968 | 400 | 0.8037 |
| 0.6706 | 0.1089 | 450 | 0.7931 |
| 0.7728 | 0.1210 | 500 | 0.7908 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1