---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: rerun-09-19-2024-experiment-distill-tree-babylm2024-58-m1
  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. -->

# rerun-09-19-2024-experiment-distill-tree-babylm2024-58-m1

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1910

## 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: 0.00025
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 8.8813        | 1.0   | 2065  | 9.2448          |
| 4.4122        | 2.0   | 4130  | 4.8905          |
| 3.2954        | 3.0   | 6195  | 3.6870          |
| 2.8224        | 4.0   | 8260  | 3.1617          |
| 2.3662        | 5.0   | 10325 | 2.7829          |
| 2.2062        | 6.0   | 12390 | 2.5207          |
| 1.9854        | 7.0   | 14455 | 2.3516          |
| 1.8831        | 8.0   | 16520 | 2.2510          |
| 1.7908        | 9.0   | 18585 | 2.2022          |
| 1.8255        | 10.0  | 20650 | 2.1910          |


### Framework versions

- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1