Yi-1.5-6B-sft-241208
This model is a fine-tuned version of [saves/Yi-1.5-6B_pt_241207] on the chinese-medical-dialogue, the CMB, the cMedQA2, the CMExam, the CMtMedQA, the COIG-CQIA-full, the COIG_full, the HuatuoGPT_sft_data_v, the huatuo_encyclopedia_q, the huatuo_lite, the imcs21, the Med-single-choice, the Medical_dialogue_system_en_single_turn, the qizhengpt-sft-20, the self_cognition, the sharegpt_zh_38K_format, the shennong, the shibing642-medica, the tigerbot_sft_data, the xywy-KG and the zhongyi-zhiku datasets.
It achieves the following results on the evaluation set:
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: 8
- total_train_batch_size: 32
- total_eval_batch_size: 32
- 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 |
|---|
| 1.6946 | 0.1277 | 1000 | 1.6502 |
| 1.6006 | 0.2554 | 2000 | 1.6065 |
| 1.5703 | 0.3830 | 3000 | 1.5798 |
| 1.6069 | 0.5107 | 4000 | 1.5604 |
| 1.5473 | 0.6384 | 5000 | 1.5453 |
| 1.5206 | 0.7661 | 6000 | 1.5329 |
| 1.4961 | 0.8938 | 7000 | 1.5222 |
| 1.4639 | 1.0215 | 8000 | 1.5162 |
| 1.4879 | 1.1491 | 9000 | 1.5104 |
| 1.4931 | 1.2768 | 10000 | 1.5055 |
| 1.503 | 1.4045 | 11000 | 1.5014 |
| 1.4826 | 1.5322 | 12000 | 1.4985 |
| 1.4544 | 1.6599 | 13000 | 1.4966 |
| 1.4557 | 1.7875 | 14000 | 1.4958 |
| 1.4839 | 1.9152 | 15000 | 1.4955 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
