myBit-Llama2-jp-127M-test-28
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5376
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 |
---|---|---|---|
5.015 | 0.05 | 2000 | 4.0397 |
3.9362 | 0.1 | 4000 | 3.8746 |
3.9138 | 0.15 | 6000 | 4.0041 |
3.9033 | 0.2 | 8000 | 3.8676 |
3.8408 | 0.25 | 10000 | 3.8122 |
3.8043 | 0.29 | 12000 | 3.8096 |
3.7816 | 0.34 | 14000 | 3.7726 |
3.7578 | 0.39 | 16000 | 3.7465 |
3.7396 | 0.44 | 18000 | 3.7269 |
3.7254 | 0.49 | 20000 | 3.7242 |
3.712 | 0.54 | 22000 | 3.7005 |
3.7014 | 0.59 | 24000 | 3.7055 |
3.6999 | 0.64 | 26000 | 3.6937 |
3.6877 | 0.69 | 28000 | 3.6774 |
3.6725 | 0.74 | 30000 | 3.6593 |
3.6556 | 0.79 | 32000 | 3.6526 |
3.6409 | 0.83 | 34000 | 3.6319 |
3.6206 | 0.88 | 36000 | 3.6091 |
3.5953 | 0.93 | 38000 | 3.5774 |
3.5597 | 0.98 | 40000 | 3.5376 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.5.7
- Downloads last month
- 5
Inference API (serverless) does not yet support model repos that contain custom code.