Kerem P
Model save
8ad2c9a
|
raw
history blame
1.62 kB
metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: opus-em-deberta-3-large-v2
    results: []

opus-em-deberta-3-large-v2

This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 253.1309
  • F1: 0.0

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: 8e-06
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss F1
429.225 1.0 28 329.4008 0.0
312.0525 2.0 56 266.1687 0.0
280.638 3.0 84 253.1309 0.0

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0