|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: myBit-Llama2-jp-127M-test-23 |
|
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-23 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- eval_loss: 3.7610 |
|
- eval_runtime: 323.9734 |
|
- eval_samples_per_second: 660.693 |
|
- eval_steps_per_second: 6.883 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 4.8240 | 0.05 | 2000 | 4.082750 | |
|
| 3.8518 | 0.1 | 4000 | 3.693951 | |
|
| 3.6357 | 0.15 | 6000 | 3.606057 | |
|
| 3.6164 | 0.2 | 8000 | 3.641231 | |
|
| 3.6208 | 0.25 | 10000 | 3.646924 | |
|
| 3.6360 | 0.29 | 12000 | 3.760965 | |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
- mybitnet 0.5.1 |
|
|
