---
base_model: meta-llama/Llama-2-13b-hf
tags:
- generated_from_trainer
model-index:
- name: radiopaedia-inst_240215-llama2_13b-240215
  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. -->

# radiopaedia-inst_240215-llama2_13b-240215

This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7504

## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: 10
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.851         | 0.05  | 20   | 0.8541          |
| 0.8377        | 0.11  | 40   | 0.8270          |
| 0.795         | 0.16  | 60   | 0.8237          |
| 0.7699        | 0.21  | 80   | 0.8089          |
| 0.953         | 0.27  | 100  | 0.7974          |
| 0.6894        | 0.32  | 120  | 0.7884          |
| 0.8883        | 0.37  | 140  | 0.7836          |
| 0.8814        | 0.42  | 160  | 0.7792          |
| 0.8322        | 0.48  | 180  | 0.7668          |
| 0.783         | 0.53  | 200  | 0.7745          |
| 0.6963        | 0.58  | 220  | 0.7683          |
| 0.7508        | 0.64  | 240  | 0.7540          |
| 0.7326        | 0.69  | 260  | 0.7582          |
| 0.7751        | 0.74  | 280  | 0.7501          |
| 0.6995        | 0.8   | 300  | 0.7473          |
| 0.7759        | 0.85  | 320  | 0.7428          |
| 0.6506        | 0.9   | 340  | 0.7383          |
| 0.7285        | 0.96  | 360  | 0.7296          |
| 0.5833        | 1.01  | 380  | 0.7347          |
| 0.5223        | 1.06  | 400  | 0.7535          |
| 0.3866        | 1.12  | 420  | 0.7685          |
| 0.4375        | 1.17  | 440  | 0.7586          |
| 0.4582        | 1.22  | 460  | 0.7539          |
| 0.4946        | 1.27  | 480  | 0.7646          |
| 0.5255        | 1.33  | 500  | 0.7670          |
| 0.4355        | 1.38  | 520  | 0.7581          |
| 0.4287        | 1.43  | 540  | 0.7574          |
| 0.478         | 1.49  | 560  | 0.7602          |
| 0.4236        | 1.54  | 580  | 0.7590          |
| 0.4873        | 1.59  | 600  | 0.7602          |
| 0.5377        | 1.65  | 620  | 0.7582          |
| 0.4546        | 1.7   | 640  | 0.7556          |
| 0.444         | 1.75  | 660  | 0.7539          |
| 0.3584        | 1.81  | 680  | 0.7526          |
| 0.4446        | 1.86  | 700  | 0.7502          |
| 0.385         | 1.91  | 720  | 0.7506          |
| 0.5061        | 1.97  | 740  | 0.7504          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1