metadata
license: apache-2.0
base_model: bert-large-uncased-whole-word-masking
tags:
- generated_from_trainer
model-index:
- name: pictalk
results: []
pictalk
This model is a fine-tuned version of bert-large-uncased-whole-word-masking on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5561
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5356 | 1.0 | 21 | 1.4643 |
| 0.5393 | 2.0 | 42 | 1.4886 |
| 0.518 | 3.0 | 63 | 1.5391 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0