|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: croissantllm/CroissantLLMChat-v0.1 |
|
model-index: |
|
- name: croissantllm_alector |
|
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. --> |
|
|
|
# croissantllm_alector |
|
|
|
This model is a fine-tuned version of [croissantllm/CroissantLLMChat-v0.1](https://huggingface.co/croissantllm/CroissantLLMChat-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4429 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 4.4674 | 1.4815 | 10 | 2.7493 | |
|
| 2.3361 | 2.9630 | 20 | 1.7841 | |
|
| 1.6418 | 4.4444 | 30 | 1.6253 | |
|
| 1.5506 | 5.9259 | 40 | 1.5834 | |
|
| 1.4118 | 7.4074 | 50 | 1.5230 | |
|
| 1.3397 | 8.8889 | 60 | 1.5239 | |
|
| 1.2705 | 10.3704 | 70 | 1.4704 | |
|
| 1.181 | 11.8519 | 80 | 1.4517 | |
|
| 1.1903 | 13.3333 | 90 | 1.4438 | |
|
| 1.1721 | 14.8148 | 100 | 1.4429 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
