metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- gokulsrinivasagan/processed_wikitext-103-raw-v1-ld
metrics:
- accuracy
model-index:
- name: bert_train_book_ent_15p_mid
results:
- task:
name: Masked Language Modeling
type: fill-mask
dataset:
name: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld
type: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld
metrics:
- name: Accuracy
type: accuracy
value: 0.05991486169102297
bert_train_book_ent_15p_mid
This model is a fine-tuned version of distilbert-base-uncased on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld dataset. It achieves the following results on the evaluation set:
- Loss: 7.1271
- Accuracy: 0.0599
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: 160
- eval_batch_size: 160
- 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 |
|---|---|---|---|---|
| 7.1643 | 6.9979 | 10000 | 7.1370 | 0.0599 |
| 7.1614 | 13.9958 | 20000 | 7.1271 | 0.0599 |
| 7.1621 | 20.9937 | 30000 | 7.1294 | 0.0599 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1