|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: src_prober_codellama-7b-last1unfreeze |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# src_prober_codellama-7b-last1unfreeze |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6729 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.7634 | 0.24 | 500 | 0.7745 | |
|
| 0.7376 | 0.48 | 1000 | 0.7399 | |
|
| 0.7006 | 0.72 | 1500 | 0.7138 | |
|
| 0.6721 | 0.97 | 2000 | 0.7015 | |
|
| 0.6753 | 1.21 | 2500 | 0.6941 | |
|
| 0.6716 | 1.45 | 3000 | 0.6894 | |
|
| 0.6595 | 1.69 | 3500 | 0.6865 | |
|
| 0.6743 | 1.93 | 4000 | 0.6848 | |
|
| 0.6647 | 2.17 | 4500 | 0.6819 | |
|
| 0.6721 | 2.42 | 5000 | 0.6797 | |
|
| 0.6642 | 2.66 | 5500 | 0.6780 | |
|
| 0.6653 | 2.9 | 6000 | 0.6764 | |
|
| 0.643 | 3.14 | 6500 | 0.6756 | |
|
| 0.6532 | 3.38 | 7000 | 0.6749 | |
|
| 0.6299 | 3.62 | 7500 | 0.6745 | |
|
| 0.6442 | 3.87 | 8000 | 0.6737 | |
|
| 0.6347 | 4.11 | 8500 | 0.6733 | |
|
| 0.6364 | 4.35 | 9000 | 0.6730 | |
|
| 0.6456 | 4.59 | 9500 | 0.6728 | |
|
| 0.6338 | 4.83 | 10000 | 0.6729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|