mms-1b-all-bigc_mini-train-drodat-gdro-1.15e-5-dat-0.207-no-sd-0.00-42
This model is a fine-tuned version of facebook/mms-1b-all on the BIGC_MINI - BEM dataset. It achieves the following results on the evaluation set:
- Loss: 35.7283
- Cer: 0.1251
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: 500
- num_epochs: 30.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 219.7174 | 0.9579 | 500 | 195.1825 | 1.0000 |
| 42.3366 | 1.9157 | 1000 | 42.6461 | 0.1417 |
| 40.2162 | 2.8736 | 1500 | 41.0567 | 0.1373 |
| 39.9397 | 3.8314 | 2000 | 40.7670 | 0.1357 |
| 37.812 | 4.7893 | 2500 | 39.4371 | 0.1362 |
| 38.0786 | 5.7471 | 3000 | 38.4844 | 0.1308 |
| 34.2418 | 6.7050 | 3500 | 39.0268 | 0.1478 |
| 32.9267 | 7.6628 | 4000 | 38.6847 | 0.1393 |
| 32.2712 | 8.6207 | 4500 | 36.5903 | 0.1311 |
| 35.1994 | 9.5785 | 5000 | 36.0070 | 0.1258 |
| 34.3693 | 10.5364 | 5500 | 36.3179 | 0.1322 |
| 31.3216 | 11.4943 | 6000 | 35.7282 | 0.1251 |
| 34.6471 | 12.4521 | 6500 | 36.5029 | 0.1352 |
| 31.4675 | 13.4100 | 7000 | 35.8080 | 0.1284 |
| 29.9495 | 14.3678 | 7500 | 35.7959 | 0.1353 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.21.4