|
--- |
|
license: apache-2.0 |
|
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: myBit-Llama2-jp-127M-test-1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# myBit-Llama2-jp-127M-test-1 |
|
|
|
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 10.6136 |
|
|
|
## 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: 48 |
|
- eval_batch_size: 48 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 7.3834 | 0.04 | 200 | 6.5397 | |
|
| 6.8679 | 0.07 | 400 | 9.8549 | |
|
| 10.2542 | 0.11 | 600 | 10.3642 | |
|
| 10.3959 | 0.14 | 800 | 10.4168 | |
|
| 10.4303 | 0.18 | 1000 | 10.4429 | |
|
| 10.4527 | 0.22 | 1200 | 10.4638 | |
|
| 10.4744 | 0.25 | 1400 | 10.4837 | |
|
| 10.4907 | 0.29 | 1600 | 10.4981 | |
|
| 10.5032 | 0.32 | 1800 | 10.5069 | |
|
| 10.5134 | 0.36 | 2000 | 10.5165 | |
|
| 10.5208 | 0.4 | 2200 | 10.5264 | |
|
| 10.5284 | 0.43 | 2400 | 10.5324 | |
|
| 10.535 | 0.47 | 2600 | 10.5372 | |
|
| 10.541 | 0.51 | 2800 | 10.5445 | |
|
| 10.5472 | 0.54 | 3000 | 10.5498 | |
|
| 10.5532 | 0.58 | 3200 | 10.5561 | |
|
| 10.5588 | 0.61 | 3400 | 10.5614 | |
|
| 10.5647 | 0.65 | 3600 | 10.5672 | |
|
| 10.5698 | 0.69 | 3800 | 10.5727 | |
|
| 10.5753 | 0.72 | 4000 | 10.5760 | |
|
| 10.5809 | 0.76 | 4200 | 10.5834 | |
|
| 10.5864 | 0.79 | 4400 | 10.5892 | |
|
| 10.5919 | 0.83 | 4600 | 10.5946 | |
|
| 10.5971 | 0.87 | 4800 | 10.5995 | |
|
| 10.6027 | 0.9 | 5000 | 10.6047 | |
|
| 10.6076 | 0.94 | 5200 | 10.6105 | |
|
| 10.6126 | 0.97 | 5400 | 10.6136 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
