metadata

license: mit
base_model: FacebookAI/roberta-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - f1
model-index:
  - name: green_as_train_context_roberta-large
    results: []

green_as_train_context_roberta-large

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

Loss: 0.8427
Accuracy: 0.8885
Recall: 0.5802
F1: 0.6533

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: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	F1
0.1927	1.0	1012	0.3691	0.8916	0.5864	0.6620
0.1417	2.0	2024	0.4204	0.8944	0.6281	0.6829
0.0954	3.0	3036	0.5585	0.8932	0.6111	0.6746
0.0447	4.0	4048	0.7888	0.8890	0.5849	0.6563
0.0217	5.0	5060	0.8427	0.8885	0.5802	0.6533

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2