Hugging Face's logo

igorktech
/
hibial-bert-i3-mlm2

Fill-Mask
Transformers
PyTorch
hibial-bert
Generated from Trainer
custom_code
Model card Files
xet
Community
1
hibial-bert-i3-mlm2 / README.md
igorktech's picture
igorktech
update model card README.md
7862cb5
preview code
|
raw
history blame contribute delete
1.7 kB
metadata
base_model: /gpfs/home/ikuzmin/hier-bert-pytorch/data/hibial-model
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: hibial-bert-i3-mlm2
    results: []

hibial-bert-i3-mlm2

This model is a fine-tuned version of /gpfs/home/ikuzmin/hier-bert-pytorch/data/hibial-model on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1505
  • Accuracy: 0.5821

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: 0.001
  • train_batch_size: 16
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.5
  • training_steps: 50000

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.7518 1.55 25000 2.5873 0.5213
2.2587 3.1 50000 2.1487 0.5824

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3