---
library_name: transformers
license: other
base_model: saves/Yi-1.5-9B-sft-241128
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: 9B_241128_sft_special-task_241202
  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. -->

# 9B_241128_sft_special-task_241202

This model is a fine-tuned version of [saves/Yi-1.5-9B-sft-241128](https://huggingface.co/saves/Yi-1.5-9B-sft-241128) on the 10.TCM-SRT, the 2.TCM-DS, the 3.TCM-DID, the 4.TCM-FT-Lite, the 5.TCM-CHGD, the 6.Med-Treat, the 7.TCM-Clin, the 8.TCMeEE, the 9.TCM-LitData, the A_problem, the B_problem, the C_problem, the D_problem, the SPD-5038-gpt4oc, the zl_2 and the zl_3 datasets.
It achieves the following results on the evaluation set:
- Loss: 0.3506

## 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: 2.5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 5
- total_train_batch_size: 120
- total_eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.2796        | 1.8335 | 1000 | 0.3508          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1