|
|
--- |
|
|
library_name: transformers |
|
|
license: other |
|
|
base_model: Qwen/Qwen1.5-MoE-A2.7B |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: fine_tuned_per_domain_balanced_moe_c10 |
|
|
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. --> |
|
|
|
|
|
# fine_tuned_per_domain_balanced_moe_c10 |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen1.5-MoE-A2.7B](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.2149 |
|
|
- Accuracy: 0.5374 |
|
|
|
|
|
## 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: 2e-05 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Accuracy | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:--------:|:---------------:| |
|
|
| 7.9537 | 0.0006 | 100 | 0.5384 | 4.2406 | |
|
|
| 2.7142 | 0.0013 | 200 | 0.5386 | 6.1312 | |
|
|
| 2.5969 | 0.0019 | 300 | 0.4651 | 1.0811 | |
|
|
| 3.6087 | 0.0025 | 400 | 0.4655 | 1.7135 | |
|
|
| 3.217 | 0.0032 | 500 | 0.5386 | 2.4567 | |
|
|
| 2.0844 | 0.0038 | 600 | 0.4614 | 3.8137 | |
|
|
| 3.0955 | 0.0044 | 700 | 0.5386 | 1.2668 | |
|
|
| 2.0157 | 0.0051 | 800 | 0.5386 | 3.2796 | |
|
|
| 2.4513 | 0.0057 | 900 | 0.4614 | 2.2765 | |
|
|
| 2.482 | 0.0063 | 1000 | 0.5386 | 0.7492 | |
|
|
| 2.3079 | 0.0070 | 1100 | 0.5386 | 1.6933 | |
|
|
| 2.5698 | 0.0076 | 1200 | 0.5386 | 3.1721 | |
|
|
| 2.4214 | 0.0082 | 1300 | 0.5386 | 1.7702 | |
|
|
| 1.2708 | 0.0089 | 1400 | 0.4646 | 0.9111 | |
|
|
| 0.8665 | 0.0095 | 1500 | 0.5494 | 0.6819 | |
|
|
| 1.7844 | 0.0101 | 1600 | 0.5386 | 1.7757 | |
|
|
| 2.9675 | 0.0108 | 1700 | 0.5386 | 2.7387 | |
|
|
| 2.7119 | 0.0114 | 1800 | 0.5386 | 2.6287 | |
|
|
| 2.526 | 0.0120 | 1900 | 0.5386 | 1.4967 | |
|
|
| 3.2745 | 0.0127 | 2000 | 0.4614 | 4.2874 | |
|
|
| 3.4052 | 0.0133 | 2100 | 1.0082 | 0.4624 | |
|
|
| 1.7179 | 0.0139 | 2200 | 1.6046 | 0.4666 | |
|
|
| 2.7225 | 0.0146 | 2300 | 3.3510 | 0.5376 | |
|
|
| 2.2919 | 0.0152 | 2400 | 3.3149 | 0.5376 | |
|
|
| 1.729 | 0.0158 | 2500 | 2.1687 | 0.5376 | |
|
|
| 2.5072 | 0.0165 | 2600 | 2.9068 | 0.5376 | |
|
|
| 1.9138 | 0.0171 | 2700 | 1.4200 | 0.4624 | |
|
|
| 1.4881 | 0.0177 | 2800 | 2.2129 | 0.4631 | |
|
|
| 2.031 | 0.0184 | 2900 | 2.2580 | 0.5370 | |
|
|
| 1.998 | 0.0190 | 3000 | 2.2149 | 0.5374 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.49.0 |
|
|
- Pytorch 2.6.0+cu126 |
|
|
- Datasets 3.3.2 |
|
|
- Tokenizers 0.21.0 |
|
|
|
