metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-seed_111
results: []
smolm-autoreg-bpe-seed_111
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4759
- Accuracy: 0.5000
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: 16
- eval_batch_size: 128
- seed: 111
- 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 |
|---|---|---|---|---|
| 3.0508 | 1.0 | 2928 | 3.0180 | 0.4367 |
| 2.7062 | 2.0 | 5856 | 2.7857 | 0.4600 |
| 2.5923 | 3.0 | 8784 | 2.6900 | 0.4700 |
| 2.5183 | 4.0 | 11712 | 2.6405 | 0.4760 |
| 2.4632 | 5.0 | 14640 | 2.6110 | 0.4799 |
| 2.4241 | 6.0 | 17568 | 2.5840 | 0.4835 |
| 2.3815 | 7.0 | 20496 | 2.5728 | 0.4851 |
| 2.3595 | 8.0 | 23424 | 2.5581 | 0.4867 |
| 2.2838 | 9.0 | 26352 | 2.5014 | 0.4949 |
| 2.1364 | 10.0 | 29280 | 2.4759 | 0.5000 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1