---
license: apache-2.0
base_model: mosaicml/mpt-7b-instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: mpt_1000_STEPS_1e8_SFT_SFT
  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. -->

# mpt_1000_STEPS_1e8_SFT_SFT

This model is a fine-tuned version of [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8571

## 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: 1e-08
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8426        | 0.05  | 50   | 1.8573          |
| 1.8564        | 0.1   | 100  | 1.8576          |
| 1.8549        | 0.15  | 150  | 1.8573          |
| 1.8574        | 0.2   | 200  | 1.8573          |
| 1.8582        | 0.24  | 250  | 1.8569          |
| 1.8566        | 0.29  | 300  | 1.8573          |
| 1.8519        | 0.34  | 350  | 1.8572          |
| 1.8551        | 0.39  | 400  | 1.8572          |
| 1.8331        | 0.44  | 450  | 1.8573          |
| 1.858         | 0.49  | 500  | 1.8571          |
| 1.8439        | 0.54  | 550  | 1.8573          |
| 1.8436        | 0.59  | 600  | 1.8574          |
| 1.8627        | 0.64  | 650  | 1.8572          |
| 1.8485        | 0.68  | 700  | 1.8570          |
| 1.8685        | 0.73  | 750  | 1.8572          |
| 1.8604        | 0.78  | 800  | 1.8571          |
| 1.8732        | 0.83  | 850  | 1.8571          |
| 1.8554        | 0.88  | 900  | 1.8571          |
| 1.8664        | 0.93  | 950  | 1.8571          |
| 1.8697        | 0.98  | 1000 | 1.8571          |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2