---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: BERT_BASE_TS_phonetic_wikitext_1.0
  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. -->

# BERT_BASE_TS_phonetic_wikitext_1.0

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9787

## 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: 0.0004
- train_batch_size: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 2.7605        | 0.3019 | 2000  | 2.4155          |
| 2.1368        | 0.6039 | 4000  | 1.8616          |
| 1.926         | 0.9058 | 6000  | 1.7315          |
| 1.7974        | 1.2077 | 8000  | 1.6337          |
| 1.7766        | 1.5097 | 10000 | 1.6091          |
| 1.6965        | 1.8116 | 12000 | 1.5455          |
| 1.5999        | 2.1135 | 14000 | 1.4758          |
| 1.5663        | 2.4155 | 16000 | 1.4532          |
| 1.5383        | 2.7174 | 18000 | 1.4057          |
| 1.4388        | 3.0193 | 20000 | 1.3795          |
| 1.4256        | 3.3213 | 22000 | 1.3358          |
| 1.4018        | 3.6232 | 24000 | 1.3338          |
| 1.3806        | 3.9251 | 26000 | 1.3115          |
| 1.321         | 4.2271 | 28000 | 1.2342          |
| 1.3078        | 4.5290 | 30000 | 1.2603          |
| 1.296         | 4.8309 | 32000 | 1.2310          |
| 1.2371        | 5.1329 | 34000 | 1.2157          |
| 1.2223        | 5.4348 | 36000 | 1.1823          |
| 1.2137        | 5.7367 | 38000 | 1.1880          |
| 1.164         | 6.0386 | 40000 | 1.1495          |
| 1.16          | 6.3406 | 42000 | 1.1544          |
| 1.1435        | 6.6425 | 44000 | 1.1177          |
| 1.1233        | 6.9444 | 46000 | 1.1045          |
| 1.0835        | 7.2464 | 48000 | 1.1160          |
| 1.0821        | 7.5483 | 50000 | 1.0977          |
| 1.066         | 7.8502 | 52000 | 1.0663          |
| 1.0505        | 8.1522 | 54000 | 1.0569          |
| 1.0252        | 8.4541 | 56000 | 1.0767          |
| 1.0164        | 8.7560 | 58000 | 1.0390          |
| 0.9905        | 9.0580 | 60000 | 1.0265          |
| 0.9705        | 9.3599 | 62000 | 1.0112          |
| 0.9722        | 9.6618 | 64000 | 0.9944          |
| 0.9688        | 9.9638 | 66000 | 0.9787          |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0