metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: smolm-autoreg-bpe-seed_1102
results: []
smolm-autoreg-bpe-seed_1102
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4764
- Accuracy: 0.4996
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: 1102
- 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 |
|---|---|---|---|---|
| 3.0413 | 1.0 | 2928 | 3.0106 | 0.4380 |
| 2.706 | 2.0 | 5856 | 2.7757 | 0.4615 |
| 2.5796 | 3.0 | 8784 | 2.6893 | 0.4708 |
| 2.5174 | 4.0 | 11712 | 2.6343 | 0.4766 |
| 2.4609 | 5.0 | 14640 | 2.6072 | 0.4795 |
| 2.4299 | 6.0 | 17568 | 2.5857 | 0.4826 |
| 2.3999 | 7.0 | 20496 | 2.5639 | 0.4859 |
| 2.3645 | 8.0 | 23424 | 2.5553 | 0.4874 |
| 2.2938 | 9.0 | 26352 | 2.5049 | 0.4939 |
| 2.151 | 10.0 | 29280 | 2.4764 | 0.4996 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1