metadata
tags:
- generated_from_trainer
model-index:
- name: myBit-Llama2-jp-127M-test-26
results: []
myBit-Llama2-jp-127M-test-26
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.1801
- eval_runtime: 317.4695
- eval_samples_per_second: 674.229
- eval_steps_per_second: 7.024
- 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 |
|---|---|---|---|
| 4.704100 | 0.05 | 2000 | 3.699232 |
| 3.558400 | 0.1 | 4000 | 3.473247 |
| 3.416400 | 0.15 | 6000 | 3.345342 |
| 3.299700 | 0.2 | 8000 | 3.261319 |
| 3.239000 | 0.25 | 10000 | 3.214480 |
| 3.196300 | 0.29 | 12000 | 3.180121 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- mybitnet 0.5.5