metadata
base_model: ../Baichuan2-7B-Chat
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: hc3zh
results: []
hc3zh
This model is a fine-tuned version of ../Baichuan2-7B-Chat on the hc3zh dataset. It achieves the following results on the evaluation set:
- Loss: 0.0150
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0199 | 0.42 | 500 | 0.0105 |
| 0.0011 | 0.85 | 1000 | 0.0118 |
| 0.0001 | 1.27 | 1500 | 0.0110 |
| 0.0143 | 1.7 | 2000 | 0.0135 |
| 0.0001 | 2.12 | 2500 | 0.0129 |
| 0.0001 | 2.55 | 3000 | 0.0145 |
| 0.002 | 2.97 | 3500 | 0.0150 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.13.2