---
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
- generated_from_trainer
model-index:
- name: moe_test
  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. -->

# moe_test

This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1210
- Learning Rate: 0.0

## 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: 4e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- 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: 50
- training_steps: 700

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rate   |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.1429        | 0.07  | 50   | 0.1353          | 4e-05  |
| 0.1442        | 0.14  | 100  | 0.1355          | 0.0000 |
| 0.1392        | 0.21  | 150  | 0.1331          | 0.0000 |
| 0.1398        | 0.29  | 200  | 0.1302          | 0.0000 |
| 0.1428        | 0.36  | 250  | 0.1281          | 0.0000 |
| 0.137         | 1.01  | 300  | 0.1259          | 0.0000 |
| 0.1439        | 1.08  | 350  | 0.1245          | 0.0000 |
| 0.1422        | 1.15  | 400  | 0.1253          | 0.0000 |
| 0.137         | 1.22  | 450  | 0.1219          | 0.0000 |
| 0.1397        | 1.29  | 500  | 0.1209          | 0.0000 |
| 0.1405        | 1.36  | 550  | 0.1209          | 0.0000 |
| 0.1376        | 2.01  | 600  | 0.1210          | 0.0000 |
| 0.1427        | 2.08  | 650  | 0.1210          | 0.0000 |
| 0.1404        | 2.15  | 700  | 0.1210          | 0.0    |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3