|
--- |
|
license: llama2 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: codellama/CodeLlama-7b-Instruct-hf |
|
model-index: |
|
- name: vendata-train |
|
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. --> |
|
|
|
# vendata-train |
|
|
|
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9052 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0633 | 0.1 | 10 | 1.0362 | |
|
| 1.2685 | 0.2 | 20 | 0.9920 | |
|
| 1.2542 | 0.3 | 30 | 0.9562 | |
|
| 1.1031 | 0.4 | 40 | 0.9356 | |
|
| 1.0196 | 0.5 | 50 | 0.9224 | |
|
| 0.9397 | 0.6 | 60 | 0.9140 | |
|
| 0.9485 | 0.7 | 70 | 0.9091 | |
|
| 0.9506 | 0.8 | 80 | 0.9064 | |
|
| 0.978 | 0.9 | 90 | 0.9054 | |
|
| 1.0167 | 1.0 | 100 | 0.9052 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
