metadata
library_name: transformers
base_model: microsoft/infoxlm-base
tags:
- generated_from_trainer
model-index:
- name: mtl-infoxlm-base-dsc
results: []
mtl-infoxlm-base-dsc
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: 0.3796
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2818 | 1.0 | 1544 | 1.0238 |
| 0.7074 | 2.0 | 3088 | 0.7507 |
| 0.7236 | 3.0 | 4632 | 0.6240 |
| 0.5222 | 4.0 | 6176 | 0.5627 |
| 0.5053 | 5.0 | 7720 | 0.4812 |
| 0.454 | 6.0 | 9264 | 0.4393 |
| 0.3946 | 7.0 | 10808 | 0.4191 |
| 0.5369 | 8.0 | 12352 | 0.3957 |
| 0.3529 | 9.0 | 13896 | 0.3868 |
| 0.4244 | 10.0 | 15440 | 0.3796 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1