metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: rationale_model_e10_save5000
results: []
rationale_model_e10_save5000
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: 2.6975
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: 8
- eval_batch_size: 8
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3986 | 0.9538 | 5000 | 2.6975 |
| 0.1468 | 1.9077 | 10000 | 3.2221 |
| 0.1156 | 2.8615 | 15000 | 3.4922 |
| 0.0981 | 3.8153 | 20000 | 3.6490 |
| 0.0847 | 4.7692 | 25000 | 3.8345 |
| 0.0704 | 5.7230 | 30000 | 3.9968 |
| 0.0551 | 6.6768 | 35000 | 4.2504 |
| 0.0433 | 7.6307 | 40000 | 4.5271 |
| 0.0354 | 8.5845 | 45000 | 4.7534 |
| 0.0317 | 9.5383 | 50000 | 4.9696 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.0
- Datasets 2.14.4
- Tokenizers 0.20.3