metadata
library_name: transformers
base_model: microsoft/infoxlm-base
tags:
- generated_from_trainer
model-index:
- name: mtl-infoxlm-base-viwiki-7-3
results: []
mtl-infoxlm-base-viwiki-7-3
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: 0.5183
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 |
|---|---|---|---|
| 0.8645 | 1.0 | 960 | 0.7032 |
| 0.6379 | 2.0 | 1920 | 0.6165 |
| 0.5676 | 3.0 | 2880 | 0.5701 |
| 0.697 | 4.0 | 3840 | 0.5455 |
| 0.4617 | 5.0 | 4800 | 0.5375 |
| 0.5992 | 6.0 | 5760 | 0.5295 |
| 0.4295 | 7.0 | 6720 | 0.5158 |
| 0.3348 | 8.0 | 7680 | 0.5239 |
| 0.3642 | 9.0 | 8640 | 0.5185 |
| 0.2147 | 10.0 | 9600 | 0.5183 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.4.0
- Datasets 3.2.0
- Tokenizers 0.21.0