myBit-Llama2-jp-127M-test-25
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.5789
- eval_runtime: 321.4234
- eval_samples_per_second: 665.935
- eval_steps_per_second: 6.938
- epoch: 0.29
- step: 12000
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: 0.0024
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.675700 | 0.05 | 2000 | 3.745954 |
3.607800 | 0.1 | 4000 | 3.538378 |
3.580200 | 0.15 | 6000 | 3.586447 |
3.523000 | 0.2 | 8000 | 3.467970 |
3.453600 | 0.25 | 10000 | 3.596693 |
3.543700 | 0.29 | 12000 | 3.578868 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.5.4
- Downloads last month
- 14
Inference API (serverless) does not yet support model repos that contain custom code.