---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: roberta-mlm-model-v2.3
  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. -->

# roberta-mlm-model-v2.3

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 8.9041

## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 7.9415        | 0.8315 | 10000 | 8.9331          |
| 7.9409        | 1.6631 | 20000 | 8.9341          |
| 7.9309        | 2.4946 | 30000 | 8.8629          |
| 7.925         | 3.3261 | 40000 | 8.8897          |
| 7.9268        | 4.1577 | 50000 | 8.9509          |
| 7.9342        | 4.9892 | 60000 | 8.9041          |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1