|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- Hartunka/processed_wikitext-103-raw-v1-rand-100_v2 |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: distilbert_rand_100_v2 |
|
|
results: |
|
|
- task: |
|
|
name: Masked Language Modeling |
|
|
type: fill-mask |
|
|
dataset: |
|
|
name: Hartunka/processed_wikitext-103-raw-v1-rand-100_v2 |
|
|
type: Hartunka/processed_wikitext-103-raw-v1-rand-100_v2 |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.1535288466971803 |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# distilbert_rand_100_v2 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-rand-100_v2 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 10.8332 |
|
|
- Accuracy: 0.1535 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-------:|:-----:|:---------------:|:--------:| |
|
|
| 10.5487 | 4.1982 | 10000 | 10.8202 | 0.1511 | |
|
|
| 9.5005 | 8.3963 | 20000 | 11.3742 | 0.1526 | |
|
|
| 7.8068 | 12.5945 | 30000 | 12.6600 | 0.1529 | |
|
|
| 6.765 | 16.7926 | 40000 | 14.0306 | 0.1504 | |
|
|
| 6.4433 | 20.9908 | 50000 | 14.5562 | 0.1517 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.50.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
