Files
ModelHub XC 8df96c29f7 初始化项目,由ModelHub XC社区提供模型
Model: wincentIsMe/Qwen3-0.6B-finetuned-astro-horoscope-fsdp
Source: Original Platform
2026-06-13 17:42:16 +08:00

68 lines
1.8 KiB
Markdown

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- generated_from_trainer
model-index:
- name: Qwen3-0.6B-finetuned-astro-horoscope-fsdp
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. -->
# Qwen3-0.6B-finetuned-astro-horoscope-fsdp
This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2469
- Perplexity: 1.2800
## 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: 0.0002
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- optimizer: Use 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|:-------------:|:-----:|:----:|:---------------:|:----------:|
| No log | 1.0 | 39 | 1.4018 | 4.0626 |
| 2.1578 | 2.0 | 78 | 0.8331 | 2.3004 |
| 0.8726 | 3.0 | 117 | 0.5413 | 1.7182 |
| 0.4763 | 4.0 | 156 | 0.3450 | 1.4121 |
| 0.4763 | 5.0 | 195 | 0.2469 | 1.2800 |
### Framework versions
- Transformers 5.5.4
- Pytorch 2.11.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2