73 lines
1.9 KiB
Markdown
73 lines
1.9 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: other
|
|
base_model: Qwen/Qwen3-4B
|
|
tags:
|
|
- llama-factory
|
|
- full
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: medical-o1-sft-full-1e-5
|
|
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-1e-5
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the medical_o1_train dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 1.3088
|
|
|
|
## 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: 1e-05
|
|
- train_batch_size: 4
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 32
|
|
- 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 |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 1.3952 | 0.3009 | 44 | 1.3628 |
|
|
| 1.3153 | 0.6017 | 88 | 1.3319 |
|
|
| 1.3174 | 0.9026 | 132 | 1.3175 |
|
|
| 1.1758 | 1.1983 | 176 | 1.3184 |
|
|
| 1.2047 | 1.4991 | 220 | 1.3131 |
|
|
| 1.1961 | 1.8 | 264 | 1.3088 |
|
|
| 1.1401 | 2.0957 | 308 | 1.3254 |
|
|
| 1.1144 | 2.3966 | 352 | 1.3240 |
|
|
| 1.1196 | 2.6974 | 396 | 1.3236 |
|
|
| 1.0940 | 2.9983 | 440 | 1.3234 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 5.0.0
|
|
- Pytorch 2.10.0+cu128
|
|
- Datasets 4.0.0
|
|
- Tokenizers 0.22.2
|