norbert2_sentiment_norec_en_gpu_3000_rader_2_test

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

• Loss: 0.6243
• Compute Metrics: :
• Accuracy: 0.6887
• Balanced Accuracy: 0.5020
• F1 Score: 0.8149
• Recall: 0.9932
• Precision: 0.6909

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Compute Metrics	Accuracy	Balanced Accuracy	F1 Score	Recall	Precision
0.6753	0.94	11	0.6527	:	0.669	0.5064	0.7957	0.9343	0.6929
0.7261	1.94	22	0.6292	:	0.6813	0.5032	0.8080	0.9720	0.6914
0.7124	2.94	33	0.6263	:	0.688	0.5012	0.8145	0.9928	0.6905
0.7036	3.94	44	0.6271	:	0.686	0.5015	0.8126	0.9870	0.6907
0.7035	4.94	55	0.6243	:	0.6887	0.5020	0.8149	0.9932	0.6909

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2