myBit-Llama2-jp-127M-test-15
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.5958
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: 0.00024
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
9.1453 | 0.07 | 200 | 8.0071 |
7.103 | 0.14 | 400 | 6.5019 |
5.9901 | 0.22 | 600 | 5.8962 |
5.3919 | 0.29 | 800 | 5.3668 |
5.285 | 0.36 | 1000 | 5.1433 |
5.0055 | 0.43 | 1200 | 5.0014 |
4.8818 | 0.51 | 1400 | 4.8863 |
4.7867 | 0.58 | 1600 | 4.8011 |
4.7076 | 0.65 | 1800 | 4.7424 |
4.6476 | 0.72 | 2000 | 4.6900 |
4.6026 | 0.8 | 2200 | 4.6517 |
4.5725 | 0.87 | 2400 | 4.6187 |
4.5339 | 0.94 | 2600 | 4.5958 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 17
Inference API (serverless) does not yet support model repos that contain custom code.