---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: wikipedia_13
  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. -->

# wikipedia_13

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: 2.9275

## 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: 16
- eval_batch_size: 16
- seed: 13
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step   | Validation Loss |
|:-------------:|:-------:|:------:|:---------------:|
| No log        | 1.4657  | 2000   | 8.0872          |
| 8.1326        | 2.9315  | 4000   | 7.3975          |
| 8.1326        | 4.3972  | 6000   | 7.2718          |
| 7.2846        | 5.8630  | 8000   | 7.1835          |
| 7.2846        | 7.3287  | 10000  | 7.0992          |
| 7.1078        | 8.7944  | 12000  | 7.0331          |
| 7.1078        | 10.2602 | 14000  | 6.9494          |
| 6.942         | 11.7259 | 16000  | 6.8899          |
| 6.942         | 13.1916 | 18000  | 6.7822          |
| 6.7676        | 14.6574 | 20000  | 6.7185          |
| 6.7676        | 16.1231 | 22000  | 6.6536          |
| 6.5959        | 17.5889 | 24000  | 6.5431          |
| 6.5959        | 19.0546 | 26000  | 6.3925          |
| 6.3624        | 20.5203 | 28000  | 6.2119          |
| 6.3624        | 21.9861 | 30000  | 5.9526          |
| 5.9309        | 23.4518 | 32000  | 5.4162          |
| 5.9309        | 24.9176 | 34000  | 5.0255          |
| 5.0575        | 26.3833 | 36000  | 4.7680          |
| 5.0575        | 27.8490 | 38000  | 4.5020          |
| 4.5282        | 29.3148 | 40000  | 4.3214          |
| 4.5282        | 30.7805 | 42000  | 4.1312          |
| 4.1335        | 32.2462 | 44000  | 3.9708          |
| 4.1335        | 33.7120 | 46000  | 3.8616          |
| 3.8339        | 35.1777 | 48000  | 3.7640          |
| 3.8339        | 36.6435 | 50000  | 3.7074          |
| 3.6042        | 38.1092 | 52000  | 3.6360          |
| 3.6042        | 39.5749 | 54000  | 3.5203          |
| 3.4291        | 41.0407 | 56000  | 3.4424          |
| 3.4291        | 42.5064 | 58000  | 3.4276          |
| 3.286         | 43.9722 | 60000  | 3.3797          |
| 3.286         | 45.4379 | 62000  | 3.3277          |
| 3.1748        | 46.9036 | 64000  | 3.2922          |
| 3.1748        | 48.3694 | 66000  | 3.2361          |
| 3.0842        | 49.8351 | 68000  | 3.2043          |
| 3.0842        | 51.3008 | 70000  | 3.1870          |
| 3.0082        | 52.7666 | 72000  | 3.1487          |
| 3.0082        | 54.2323 | 74000  | 3.1257          |
| 2.9483        | 55.6981 | 76000  | 3.1001          |
| 2.9483        | 57.1638 | 78000  | 3.0694          |
| 2.8885        | 58.6295 | 80000  | 3.0605          |
| 2.8885        | 60.0953 | 82000  | 3.0568          |
| 2.8416        | 61.5610 | 84000  | 3.0083          |
| 2.8416        | 63.0267 | 86000  | 3.0188          |
| 2.8064        | 64.4925 | 88000  | 3.0213          |
| 2.8064        | 65.9582 | 90000  | 2.9645          |
| 2.7717        | 67.4240 | 92000  | 2.9901          |
| 2.7717        | 68.8897 | 94000  | 2.9684          |
| 2.7441        | 70.3554 | 96000  | 2.9565          |
| 2.7441        | 71.8212 | 98000  | 2.9547          |
| 2.7289        | 73.2869 | 100000 | 2.9275          |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1