CodeLlama-7b-Instruct-hf-FaVe-10epochs
This model is a fine-tuned version of meta-llama/CodeLlama-7b-Instruct-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4855
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 | 2.4744 |
2.3302 | 0.5369 | 20 | 2.1711 |
2.3302 | 0.8054 | 30 | 1.6543 |
1.6527 | 1.0738 | 40 | 1.2271 |
1.6527 | 1.3423 | 50 | 0.9415 |
0.9181 | 1.6107 | 60 | 0.8054 |
0.9181 | 1.8792 | 70 | 0.7420 |
0.7125 | 2.1477 | 80 | 0.6950 |
0.7125 | 2.4161 | 90 | 0.6539 |
0.6106 | 2.6846 | 100 | 0.6225 |
0.6106 | 2.9530 | 110 | 0.5876 |
0.5355 | 3.2215 | 120 | 0.5650 |
0.5355 | 3.4899 | 130 | 0.5407 |
0.4625 | 3.7584 | 140 | 0.5409 |
0.4625 | 4.0268 | 150 | 0.5250 |
0.3806 | 4.2953 | 160 | 0.5336 |
0.3806 | 4.5638 | 170 | 0.5024 |
0.3932 | 4.8322 | 180 | 0.4939 |
0.3932 | 5.1007 | 190 | 0.4735 |
0.3664 | 5.3691 | 200 | 0.4728 |
0.3664 | 5.6376 | 210 | 0.4640 |
0.2907 | 5.9060 | 220 | 0.4797 |
0.2907 | 6.1745 | 230 | 0.4695 |
0.2464 | 6.4430 | 240 | 0.4592 |
0.2464 | 6.7114 | 250 | 0.4683 |
0.2722 | 6.9799 | 260 | 0.4633 |
0.2722 | 7.2483 | 270 | 0.4801 |
0.2171 | 7.5168 | 280 | 0.4690 |
0.2171 | 7.7852 | 290 | 0.4613 |
0.2341 | 8.0537 | 300 | 0.4608 |
0.2341 | 8.3221 | 310 | 0.4781 |
0.1833 | 8.5906 | 320 | 0.4763 |
0.1833 | 8.8591 | 330 | 0.4706 |
0.2394 | 9.1275 | 340 | 0.4620 |
0.2394 | 9.3960 | 350 | 0.4692 |
0.1667 | 9.6644 | 360 | 0.4837 |
0.1667 | 9.9329 | 370 | 0.4855 |
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
.