metadata
library_name: peft
license: apache-2.0
base_model: google-bert/bert-base-multilingual-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: MBERT_uncased_CrossEntropyLoss_lora
results: []
MBERT_uncased_CrossEntropyLoss_lora
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.518
- F1: 0.6730
- Precision: 0.6613
- Recall: 0.6851
- Roc Auc: 0.3824
- Loss: 0.6924
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use 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: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Precision | Recall | Roc Auc | Validation Loss |
|---|---|---|---|---|---|---|---|---|
| No log | 0.992 | 31 | 0.347 | 0.4287 | 0.5847 | 0.3384 | 0.3540 | 0.7081 |
| No log | 1.984 | 62 | 0.479 | 0.6354 | 0.6440 | 0.6271 | 0.3588 | 0.6961 |
| No log | 2.976 | 93 | 0.518 | 0.6730 | 0.6613 | 0.6851 | 0.3824 | 0.6924 |
Framework versions
- PEFT 0.13.3.dev0
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3