la-sailor2-8b-10k-4bit_r32_alpha_16_lr1e-4_3ep
This model is a fine-tuned version of sail/Sailor2-8B-Chat on the la_chat_data_v4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2371
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5147 | 0.6649 | 10000 | 0.4314 |
| 0.3106 | 1.3299 | 20000 | 0.3119 |
| 0.2238 | 1.9948 | 30000 | 0.2371 |
Framework versions
- PEFT 0.11.1
- Transformers 4.46.1
- Pytorch 2.4.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3
- Downloads last month
- 4