llama-3-8b-hf-ft-chat-lora
This model is a fine-tuned version of ytcheng/llama-3-8b-hf-sm-lora-merged on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.2919
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.668 | 0.9959 | 121 | 1.6440 |
1.3927 | 2.0 | 243 | 1.3922 |
1.2658 | 2.9959 | 364 | 1.3038 |
1.1749 | 3.9835 | 484 | 1.2919 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 16
Model tree for ytcheng/llama-3-8b-hf-ft-chat-lora
Base model
ytcheng/llama-3-8b-hf-sm-lora-merged
Adapter
this model