|
--- |
|
license: apache-2.0 |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-Instruct-v0.2-absa-laptops |
|
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. --> |
|
|
|
# Mistral-7B-Instruct-v0.2-absa-laptops |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0271 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- training_steps: 400 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.1703 | 0.36 | 40 | 0.1843 | |
|
| 0.0773 | 0.72 | 80 | 0.0347 | |
|
| 0.0253 | 1.08 | 120 | 0.0303 | |
|
| 0.019 | 1.44 | 160 | 0.0313 | |
|
| 0.0188 | 1.8 | 200 | 0.0258 | |
|
| 0.0155 | 2.16 | 240 | 0.0300 | |
|
| 0.0134 | 2.52 | 280 | 0.0271 | |
|
| 0.0127 | 2.88 | 320 | 0.0245 | |
|
| 0.0104 | 3.24 | 360 | 0.0272 | |
|
| 0.0085 | 3.6 | 400 | 0.0271 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
