metadata
base_model: models/smolm-autoreg-bpe-seed_888/config.json
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-seed_888
results: []
smolm-autoreg-bpe-seed_888
This model is a fine-tuned version of models/smolm-autoreg-bpe-seed_888/config.json on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5572
- Accuracy: 0.4861
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: 888
- 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 |
|---|---|---|---|---|
| 6.1167 | 1.0 | 732 | 3.5358 | 0.3947 |
| 3.4801 | 2.0 | 1464 | 3.1202 | 0.4320 |
| 2.9429 | 3.0 | 2196 | 2.9158 | 0.4498 |
| 2.8071 | 4.0 | 2928 | 2.7906 | 0.4605 |
| 2.6197 | 5.0 | 3660 | 2.6998 | 0.4701 |
| 2.5459 | 6.0 | 4392 | 2.6419 | 0.4760 |
| 2.4492 | 7.0 | 5124 | 2.6036 | 0.4802 |
| 2.4065 | 8.0 | 5856 | 2.5770 | 0.4824 |
| 2.3626 | 9.0 | 6588 | 2.5622 | 0.4863 |
| 2.3276 | 10.0 | 7320 | 2.5572 | 0.4861 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3