metadata
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: content/drive/MyDrive/LLaMA-Factory/saves/Yi-6B-Chat/lora/lora_8bit_20w
model-index:
- name: oncology
results: []
oncology
This model is a fine-tuned version of content/drive/MyDrive/LLaMA-Factory/saves/Yi-6B-Chat/lora/lora_8bit_20w on the oncology_train_raw dataset. It achieves the following results on the evaluation set:
- Loss: 1.6397
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7882 | 0.32 | 200 | 1.7318 |
| 1.604 | 0.64 | 400 | 1.7021 |
| 1.706 | 0.96 | 600 | 1.6814 |
| 1.5361 | 1.28 | 800 | 1.6756 |
| 1.5625 | 1.6 | 1000 | 1.6565 |
| 1.606 | 1.91 | 1200 | 1.6396 |
| 1.4462 | 2.23 | 1400 | 1.6514 |
| 1.3236 | 2.55 | 1600 | 1.6478 |
| 1.4728 | 2.87 | 1800 | 1.6453 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2