metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-seed_888
results: []
smolm-autoreg-bpe-seed_888
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4712
- 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: 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 |
|---|---|---|---|---|
| 3.0458 | 1.0 | 2928 | 3.0245 | 0.4357 |
| 2.71 | 2.0 | 5856 | 2.7881 | 0.4585 |
| 2.5918 | 3.0 | 8784 | 2.6924 | 0.4682 |
| 2.5122 | 4.0 | 11712 | 2.6471 | 0.4759 |
| 2.4623 | 5.0 | 14640 | 2.6053 | 0.4803 |
| 2.4246 | 6.0 | 17568 | 2.5798 | 0.4824 |
| 2.3871 | 7.0 | 20496 | 2.5647 | 0.4858 |
| 2.3644 | 8.0 | 23424 | 2.5571 | 0.4853 |
| 2.2824 | 9.0 | 26352 | 2.5034 | 0.4934 |
| 2.1369 | 10.0 | 29280 | 2.4712 | 0.5000 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1