|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- arrow |
|
|
model-index: |
|
|
- name: moe_b1 |
|
|
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. --> |
|
|
|
|
|
# moe_b1 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the arrow dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 4.8327 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 2 |
|
|
- gradient_accumulation_steps: 16 |
|
|
- total_train_batch_size: 1024 |
|
|
- total_eval_batch_size: 16 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- training_steps: 4583 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| No log | 0 | 0 | 10.9680 | |
|
|
| 6.4487 | 0.6545 | 1000 | 6.1736 | |
|
|
| 5.3049 | 1.3089 | 2000 | 5.2504 | |
|
|
| 5.0152 | 1.9634 | 3000 | 4.9769 | |
|
|
| 4.802 | 2.6178 | 4000 | 4.8600 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.1 |
|
|
- Pytorch 2.7.0+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
