71 lines
1.8 KiB
Markdown
71 lines
1.8 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: other
|
|
base_model: Qwen/Qwen3-1.7B
|
|
tags:
|
|
- llama-factory
|
|
- full
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: medical-o1-sft-full
|
|
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. -->
|
|
|
|
# medical-o1-sft-full
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the medical_o1_train dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 1.4089
|
|
|
|
## 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: 16
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 8
|
|
- total_train_batch_size: 128
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_steps: 0.05
|
|
- num_epochs: 3.0
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 1.4962 | 0.3419 | 50 | 1.4686 |
|
|
| 1.4215 | 0.6838 | 100 | 1.4337 |
|
|
| 1.3304 | 1.0205 | 150 | 1.4194 |
|
|
| 1.3097 | 1.3624 | 200 | 1.4159 |
|
|
| 1.3175 | 1.7043 | 250 | 1.4089 |
|
|
| 1.2195 | 2.0410 | 300 | 1.4176 |
|
|
| 1.2726 | 2.3829 | 350 | 1.4229 |
|
|
| 1.1895 | 2.7248 | 400 | 1.4216 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 5.0.0
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.22.2
|