metadata
library_name: transformers
tags:
- generated_from_trainer
datasets:
- Hartunka/processed_wikitext-103-raw-v1-km-100
metrics:
- accuracy
model-index:
- name: distilbert_km_100_v1
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: Hartunka/processed_wikitext-103-raw-v1-km-100
type: Hartunka/processed_wikitext-103-raw-v1-km-100
metrics:
- name: Accuracy
type: accuracy
value: 0.15372662033112958
distilbert_km_100_v1
This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-km-100 dataset. It achieves the following results on the evaluation set:
- Loss: 7.0858
- Accuracy: 0.1537
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 |
|---|---|---|---|---|
| 7.2572 | 4.1982 | 10000 | 7.4186 | 0.1489 |
| 6.7045 | 8.3963 | 20000 | 7.0809 | 0.1525 |
| 6.3773 | 12.5945 | 30000 | 7.2005 | 0.1538 |
| 6.1723 | 16.7926 | 40000 | 7.3184 | 0.1517 |
| 6.0693 | 20.9908 | 50000 | 7.4671 | 0.1508 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1