llama-qLoRA
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9238
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2796 | 0.2022 | 100 | 1.2957 |
1.132 | 0.4044 | 200 | 1.1329 |
1.0712 | 0.6067 | 300 | 1.0974 |
1.0711 | 0.8089 | 400 | 1.0586 |
0.9632 | 1.0111 | 500 | 1.0059 |
0.9462 | 1.2133 | 600 | 0.9607 |
0.965 | 1.4156 | 700 | 0.9520 |
0.9302 | 1.6178 | 800 | 0.9470 |
0.9227 | 1.8200 | 900 | 0.9418 |
0.9023 | 2.0222 | 1000 | 0.9375 |
0.9093 | 2.2245 | 1100 | 0.9339 |
0.9202 | 2.4267 | 1200 | 0.9300 |
0.9061 | 2.6289 | 1300 | 0.9263 |
0.915 | 2.8311 | 1400 | 0.9238 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for dhanishetty/llama_qLoRA_Adapters_2
Base model
meta-llama/Meta-Llama-3-8B-Instruct