|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: Mistral_Sentiment_Classification_2024-05-17 |
|
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_Sentiment_Classification_2024-05-17 |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3003 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 0.03 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.4299 | 0.4587 | 100 | 0.3342 | |
|
| 0.3351 | 0.9174 | 200 | 0.3189 | |
|
| 0.3218 | 1.3761 | 300 | 0.3112 | |
|
| 0.3164 | 1.8349 | 400 | 0.3067 | |
|
| 0.3021 | 2.2936 | 500 | 0.3035 | |
|
| 0.2892 | 2.7523 | 600 | 0.3006 | |
|
| 0.2825 | 3.2110 | 700 | 0.3010 | |
|
| 0.2719 | 3.6697 | 800 | 0.2994 | |
|
| 0.2807 | 4.1284 | 900 | 0.3002 | |
|
| 0.2622 | 4.5872 | 1000 | 0.3003 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
