gokuls's picture
update model card README.md
6cd0110
|
raw
history blame
2.27 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: add_bert_12_layer_model_complete_training_new
    results: []

add_bert_12_layer_model_complete_training_new

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Accuracy: 0.0000

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: 0.0005
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 10
  • distributed_type: multi-GPU
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 10000
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0 0.11 10000 nan 0.0000
0.0 0.22 20000 nan 0.0000
0.0 0.33 30000 nan 0.0000
0.0 0.44 40000 nan 0.0000
0.0 0.55 50000 nan 0.0000
0.0 0.66 60000 nan 0.0000
0.0 0.76 70000 nan 0.0000
0.0 0.87 80000 nan 0.0000
0.0 0.98 90000 nan 0.0000
0.0 1.09 100000 nan 0.0000
0.0 1.2 110000 nan 0.0000
0.0 1.31 120000 nan 0.0000
0.0 1.42 130000 nan 0.0000
0.0 1.53 140000 nan 0.0000

Framework versions

  • Transformers 4.29.2
  • Pytorch 1.14.0a0+410ce96
  • Datasets 2.12.0
  • Tokenizers 0.13.3