metadata
library_name: transformers
base_model: microsoft/infoxlm-base
tags:
- generated_from_trainer
model-index:
- name: mtl-infoxlm-base-dsc-1-9
results: []
mtl-infoxlm-base-dsc-1-9
This model is a fine-tuned version of microsoft/infoxlm-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5500
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1839 | 1.0 | 1544 | 1.2323 |
| 1.0202 | 2.0 | 3088 | 0.8503 |
| 0.7232 | 3.0 | 4632 | 0.7070 |
| 0.5335 | 4.0 | 6176 | 0.6425 |
| 0.9062 | 5.0 | 7720 | 0.6046 |
| 0.7088 | 6.0 | 9264 | 0.5787 |
| 0.5146 | 7.0 | 10808 | 0.6012 |
| 0.3288 | 8.0 | 12352 | 0.5725 |
| 0.3629 | 9.0 | 13896 | 0.5499 |
| 0.5917 | 10.0 | 15440 | 0.5500 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.0
- Datasets 3.2.0
- Tokenizers 0.21.0