|
--- |
|
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_e3_save5000_rp |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# rationale_model_e3_save5000_rp |
|
|
|
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2603 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 1.966 | 0.1908 | 1000 | 2.2603 | |
|
| 1.3866 | 0.3815 | 2000 | 2.4390 | |
|
| 0.8202 | 0.5723 | 3000 | 2.6035 | |
|
| 0.497 | 0.7631 | 4000 | 2.8871 | |
|
| 0.3141 | 0.9538 | 5000 | 3.1623 | |
|
| 0.2115 | 1.1446 | 6000 | 3.3478 | |
|
| 0.1859 | 1.3354 | 7000 | 3.4553 | |
|
| 0.159 | 1.5261 | 8000 | 3.5514 | |
|
| 0.1431 | 1.7169 | 9000 | 3.6509 | |
|
| 0.127 | 1.9077 | 10000 | 3.7211 | |
|
| 0.094 | 2.0984 | 11000 | 3.8280 | |
|
| 0.0899 | 2.2892 | 12000 | 3.8603 | |
|
| 0.0883 | 2.4800 | 13000 | 3.9257 | |
|
| 0.0813 | 2.6707 | 14000 | 3.9864 | |
|
| 0.0784 | 2.8615 | 15000 | 4.0649 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.20.3 |
|
|
