CodeLlama-7B-Instruct-AWQ-FaVe-10epochs
This model is a fine-tuned version of TheBloke/CodeLlama-7B-Instruct-AWQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5237
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.2685 | 10 | 2.2736 |
2.3722 | 0.5369 | 20 | 1.9052 |
2.3722 | 0.8054 | 30 | 1.4050 |
1.4539 | 1.0738 | 40 | 1.0251 |
1.4539 | 1.3423 | 50 | 0.8628 |
0.8443 | 1.6107 | 60 | 0.7667 |
0.8443 | 1.8792 | 70 | 0.7187 |
0.6683 | 2.1477 | 80 | 0.6908 |
0.6683 | 2.4161 | 90 | 0.6614 |
0.5718 | 2.6846 | 100 | 0.6412 |
0.5718 | 2.9530 | 110 | 0.6164 |
0.5354 | 3.2215 | 120 | 0.5959 |
0.5354 | 3.4899 | 130 | 0.5980 |
0.4453 | 3.7584 | 140 | 0.5692 |
0.4453 | 4.0268 | 150 | 0.5603 |
0.3873 | 4.2953 | 160 | 0.5546 |
0.3873 | 4.5638 | 170 | 0.5323 |
0.3814 | 4.8322 | 180 | 0.5307 |
0.3814 | 5.1007 | 190 | 0.5171 |
0.3078 | 5.3691 | 200 | 0.5125 |
0.3078 | 5.6376 | 210 | 0.5158 |
0.2949 | 5.9060 | 220 | 0.5012 |
0.2949 | 6.1745 | 230 | 0.5247 |
0.2317 | 6.4430 | 240 | 0.5248 |
0.2317 | 6.7114 | 250 | 0.5010 |
0.258 | 6.9799 | 260 | 0.5026 |
0.258 | 7.2483 | 270 | 0.5175 |
0.1984 | 7.5168 | 280 | 0.5152 |
0.1984 | 7.7852 | 290 | 0.5064 |
0.2118 | 8.0537 | 300 | 0.5096 |
0.2118 | 8.3221 | 310 | 0.5272 |
0.1956 | 8.5906 | 320 | 0.5177 |
0.1956 | 8.8591 | 330 | 0.5121 |
0.1732 | 9.1275 | 340 | 0.5162 |
0.1732 | 9.3960 | 350 | 0.5198 |
0.1632 | 9.6644 | 360 | 0.5231 |
0.1632 | 9.9329 | 370 | 0.5237 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0
Unable to determine this model’s pipeline type. Check the
docs
.