metadata
license: apache-2.0
base_model: google/muril-base-cased
tags:
- classification
- generated_from_trainer
model-index:
- name: MuRIL_relevance
results: []
MuRIL_relevance
This model is a fine-tuned version of google/muril-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0264
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.98 | 39 | 0.6917 |
| 0.6907 | 1.98 | 78 | 0.6750 |
| 0.6787 | 2.99 | 118 | 0.6189 |
| 0.6125 | 3.99 | 158 | 0.5301 |
| 0.6125 | 4.92 | 195 | 0.3716 |
| 0.3659 | 5.98 | 234 | 0.2228 |
| 0.2697 | 6.96 | 273 | 0.1203 |
| 0.1038 | 7.98 | 312 | 0.0648 |
| 0.0607 | 8.96 | 351 | 0.0458 |
| 0.0607 | 9.98 | 390 | 0.0264 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.2