metadata
library_name: transformers
tags:
- generated_from_trainer
datasets:
- Hartunka/processed_wikitext-103-raw-v1-km-50
metrics:
- accuracy
model-index:
- name: bert_base_km_50_v1
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: Hartunka/processed_wikitext-103-raw-v1-km-50
type: Hartunka/processed_wikitext-103-raw-v1-km-50
metrics:
- name: Accuracy
type: accuracy
value: 0.15398090071763576
bert_base_km_50_v1
This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-km-50 dataset. It achieves the following results on the evaluation set:
- Loss: 6.7808
- Accuracy: 0.1540
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: 0.0001
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- 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_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 7.0285 | 4.1982 | 10000 | 7.0776 | 0.1500 |
| 6.5312 | 8.3963 | 20000 | 6.8072 | 0.1518 |
| 6.2368 | 12.5945 | 30000 | 6.9131 | 0.1535 |
| 6.0623 | 16.7926 | 40000 | 7.1038 | 0.1515 |
| 5.966 | 20.9908 | 50000 | 7.3309 | 0.1519 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1