|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: myBit-Llama2-jp-127M-6 |
|
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-6 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.5300 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 4.6845 | 0.05 | 2000 | 3.7571 | |
|
| 3.6263 | 0.1 | 4000 | 3.5463 | |
|
| 3.5645 | 0.15 | 6000 | 3.4975 | |
|
| 3.5418 | 0.2 | 8000 | 3.5903 | |
|
| 3.5333 | 0.25 | 10000 | 3.4952 | |
|
| 3.5572 | 0.29 | 12000 | 3.4898 | |
|
| 3.4671 | 0.34 | 14000 | 3.4466 | |
|
| 3.414 | 0.39 | 16000 | 3.4579 | |
|
| 3.4583 | 0.44 | 18000 | 3.4420 | |
|
| 3.4988 | 0.49 | 20000 | 3.5380 | |
|
| 3.5448 | 0.54 | 22000 | 3.4931 | |
|
| 3.4932 | 0.59 | 24000 | 3.4592 | |
|
| 3.5387 | 0.64 | 26000 | 3.5774 | |
|
| 3.6424 | 0.69 | 28000 | 4.0166 | |
|
| 3.8589 | 0.74 | 30000 | 3.7899 | |
|
| 3.7753 | 0.79 | 32000 | 3.7973 | |
|
| 3.7703 | 0.83 | 34000 | 3.7630 | |
|
| 3.7135 | 0.88 | 36000 | 3.6725 | |
|
| 3.6472 | 0.93 | 38000 | 3.5994 | |
|
| 3.5686 | 0.98 | 40000 | 3.5300 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
