|
--- |
|
base_model: models/smolm-autoreg-bpe-seed_555/config.json |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smolm-autoreg-bpe-seed_555 |
|
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. --> |
|
|
|
# smolm-autoreg-bpe-seed_555 |
|
|
|
This model is a fine-tuned version of [models/smolm-autoreg-bpe-seed_555/config.json](https://huggingface.co/models/smolm-autoreg-bpe-seed_555/config.json) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.5572 |
|
- Accuracy: 0.4865 |
|
|
|
## 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: 0.003 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 512 |
|
- seed: 555 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 24000 |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 6.0722 | 1.0 | 732 | 3.5448 | 0.3932 | |
|
| 3.4869 | 2.0 | 1464 | 3.1229 | 0.4320 | |
|
| 2.9405 | 3.0 | 2196 | 2.9153 | 0.4493 | |
|
| 2.8073 | 4.0 | 2928 | 2.7839 | 0.4623 | |
|
| 2.6116 | 5.0 | 3660 | 2.6959 | 0.4708 | |
|
| 2.5433 | 6.0 | 4392 | 2.6370 | 0.4772 | |
|
| 2.4481 | 7.0 | 5124 | 2.6047 | 0.4806 | |
|
| 2.4044 | 8.0 | 5856 | 2.5815 | 0.4826 | |
|
| 2.3619 | 9.0 | 6588 | 2.5696 | 0.4854 | |
|
| 2.322 | 10.0 | 7320 | 2.5572 | 0.4865 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
