README.md

---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
- name: coinplusfire_llm_full
  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. -->

# coinplusfire_llm_full

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: 3.2466

## 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: 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
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.4186        | 0.99  | 51   | 2.4168          |
| 3.0802        | 1.99  | 103  | 3.3055          |
| 3.1087        | 3.0   | 155  | 3.0982          |
| 2.7192        | 4.0   | 207  | 2.9555          |
| 2.9335        | 4.99  | 258  | 3.0334          |
| 2.9269        | 5.99  | 310  | 3.0637          |
| 2.9669        | 7.0   | 362  | 3.1044          |
| 3.0386        | 8.0   | 414  | 3.1546          |
| 3.1866        | 8.99  | 465  | 3.2254          |
| 3.1436        | 9.86  | 510  | 3.2466          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2