|
--- |
|
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: 2.2878 |
|
- Accuracy: 0.5417 |
|
|
|
## 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: 42 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 5.8796 | 1.0 | 826 | 3.1083 | 0.4611 | |
|
| 2.802 | 2.0 | 1652 | 2.7455 | 0.4965 | |
|
| 2.6268 | 3.0 | 2478 | 2.5734 | 0.5116 | |
|
| 2.4165 | 4.0 | 3304 | 2.4667 | 0.5211 | |
|
| 2.2892 | 5.0 | 4130 | 2.3949 | 0.5288 | |
|
| 2.2315 | 6.0 | 4956 | 2.3446 | 0.5338 | |
|
| 2.1587 | 7.0 | 5782 | 2.3208 | 0.5374 | |
|
| 2.1253 | 8.0 | 6608 | 2.3044 | 0.5394 | |
|
| 2.0858 | 9.0 | 7434 | 2.2940 | 0.5404 | |
|
| 2.0556 | 10.0 | 8260 | 2.2878 | 0.5417 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
