|
--- |
|
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- adapter |
|
- instruct-tuning |
|
- Mistral7B |
|
- Batch_Size-4 |
|
- Epoch-1 |
|
- trl |
|
- sft |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Epoch_1-FT-Unsloth_Mistral7B |
|
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. --> |
|
|
|
# PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Epoch_1-FT-Unsloth_Mistral7B |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3841 |
|
|
|
## 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: 4 |
|
- seed: 3407 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.356 | 0.1078 | 30 | 1.0690 | |
|
| 1.0215 | 0.2156 | 60 | 0.9446 | |
|
| 0.9024 | 0.3235 | 90 | 0.8369 | |
|
| 0.8971 | 0.4313 | 120 | 0.7261 | |
|
| 0.7858 | 0.5391 | 150 | 0.6317 | |
|
| 0.7608 | 0.6469 | 180 | 0.5461 | |
|
| 0.6772 | 0.7547 | 210 | 0.4775 | |
|
| 0.6375 | 0.8625 | 240 | 0.4176 | |
|
| 0.6158 | 0.9704 | 270 | 0.3841 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.3.0+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |