---
library_name: transformers
license: mit
base_model: gpt2
tags:
- bitnet
- 1.58b
- generated_from_trainer
model-index:
- name: distily_multi_experiment
  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. -->

# distily_multi_experiment

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 11.8595

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 1.0

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| No log        | 0      | 0     | 45.5392         |
| 19.25         | 0.0404 | 2500  | 20.5160         |
| 17.0          | 0.0808 | 5000  | 18.1646         |
| 16.375        | 0.1212 | 7500  | 16.8100         |
| 18.5          | 0.1616 | 10000 | 15.9662         |
| 18.125        | 0.2020 | 12500 | 14.8913         |
| 16.125        | 0.2424 | 15000 | 14.2909         |
| 13.875        | 0.2828 | 17500 | 13.9054         |
| 12.5625       | 0.3232 | 20000 | 13.4260         |
| 13.8125       | 0.3636 | 22500 | 12.9026         |
| 14.5625       | 0.4040 | 25000 | 12.6783         |
| 15.1875       | 0.4444 | 27500 | 12.5651         |
| 13.4375       | 0.4848 | 30000 | 12.5742         |
| 6.8125        | 0.5253 | 32500 | 12.5106         |
| 12.0          | 0.5657 | 35000 | 12.3849         |
| 13.9375       | 0.6061 | 37500 | 12.3297         |
| 5.375         | 0.6465 | 40000 | 12.2764         |
| 20.625        | 0.6869 | 42500 | 12.2612         |
| 10.0          | 0.7273 | 45000 | 12.0058         |
| 18.75         | 0.7677 | 47500 | 11.9614         |
| 10.0625       | 0.8081 | 50000 | 11.9339         |
| 16.0          | 0.8485 | 52500 | 11.9123         |
| 18.625        | 0.8889 | 55000 | 11.8770         |
| 15.875        | 0.9293 | 57500 | 11.8680         |
| 11.25         | 0.9697 | 60000 | 11.8611         |


### Framework versions

- Transformers 4.44.1
- Pytorch 2.5.0.dev20240821+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1