---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: babylm-unablated_seed-42_1e-3
  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. -->

# babylm-unablated_seed-42_1e-3

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0136
- Accuracy: 0.4207

## 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: 0.001
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32000
- num_epochs: 20.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
| 6.1723        | 0.9999  | 1788  | 4.2504          | 0.3067   |
| 4.0454        | 1.9999  | 3576  | 3.7300          | 0.3471   |
| 3.6164        | 2.9998  | 5364  | 3.4747          | 0.3703   |
| 3.394         | 3.9997  | 7152  | 3.3376          | 0.3834   |
| 3.3055        | 4.9997  | 8940  | 3.2589          | 0.3908   |
| 3.2018        | 5.9996  | 10728 | 3.2086          | 0.3957   |
| 3.1366        | 6.9995  | 12516 | 3.1760          | 0.3991   |
| 3.093         | 8.0     | 14305 | 3.1520          | 0.4016   |
| 3.0613        | 8.9999  | 16093 | 3.1356          | 0.4037   |
| 3.0161        | 9.9999  | 17881 | 3.1245          | 0.4046   |
| 2.9952        | 10.9998 | 19669 | 3.1162          | 0.4061   |
| 2.9865        | 11.9997 | 21457 | 3.1086          | 0.4065   |
| 2.9786        | 12.9997 | 23245 | 3.1062          | 0.4073   |
| 2.9743        | 13.9996 | 25033 | 3.1010          | 0.4076   |
| 2.9328        | 14.9995 | 26821 | 3.0967          | 0.4084   |
| 2.9369        | 16.0    | 28610 | 3.0958          | 0.4086   |
| 2.9408        | 16.9999 | 30398 | 3.0929          | 0.4088   |
| 2.9445        | 17.9999 | 32186 | 3.0917          | 0.4094   |
| 2.8906        | 18.9998 | 33974 | 3.0351          | 0.4163   |
| 2.7359        | 19.9986 | 35760 | 3.0136          | 0.4207   |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 2.19.1
- Tokenizers 0.20.0