metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: model_output_luh2
results: []
model_output_luh2
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9295
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5118 | 0.2385 | 5000 | 1.9295 |
| 0.9663 | 0.4769 | 10000 | 2.1287 |
| 0.5362 | 0.7154 | 15000 | 2.4146 |
| 0.2763 | 0.9539 | 20000 | 2.8170 |
| 0.1798 | 1.1923 | 25000 | 3.0370 |
| 0.1565 | 1.4308 | 30000 | 3.1830 |
| 0.143 | 1.6693 | 35000 | 3.2466 |
| 0.1259 | 1.9078 | 40000 | 3.3591 |
| 0.1062 | 2.1462 | 45000 | 3.5343 |
| 0.0987 | 2.3847 | 50000 | 3.7228 |
| 0.0934 | 2.6232 | 55000 | 3.8807 |
| 0.0901 | 2.8616 | 60000 | 3.9691 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.0
- Datasets 2.16.1
- Tokenizers 0.20.3