---
license: mit
datasets:
- Replete-AI/code_bagel
language:
- en
tags:
- code
---

### Base_model
microsoft/Phi-3-medium-128k-instruct</br>
(https://huggingface.co/microsoft/Phi-3-medium-128k-instruct)

### Datasets
Replete-AI/code_bagel</br>
(https://huggingface.co/datasets/Replete-AI/code_bagel)

### Train Loss
![image/png](https://cdn-uploads.huggingface.co/production/uploads/636f54b95d2050767e4a6317/tOBahj5rDAJzqCmftVdkX.png)

### Train State
Trainable params: 27852800 || all params: 13988090880 || trainable%: 0.1991</br>
Total Training Duration：69h18m17s
```json
{
    "epoch": 0.9999679800589659,
    "total_flos": 1.446273483573748e+20,
    "train_loss": 0.44412665014957775,
    "train_runtime": 249497.725,
    "train_samples_per_second": 13.018,
    "train_steps_per_second": 0.102
}
```

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1200
- num_epochs: 1.0