NTCAL/norbert2_sentiment_norec_en_gpu_500_rader_max_1

Kjøretid

{'train_runtime': 291.2967, 'train_samples_per_second': 51.494, 'train_steps_per_second': 0.189, 'train_loss': 0.6998663252050227, 'epoch': 4.94} Time: 291.30 Samples/second: 51.49

#SBATCH --nodes=1 #SBATCH --ntasks-per-node=1 #SBATCH --gres=gpu:A100m40:1

norbert2_sentiment_norec_en_gpu_500_rader_max_1

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: 0.6269
• Compute Metrics: :
• Accuracy: 0.682
• Balanced Accuracy: 0.5048
• F1 Score: 0.8073
• Recall: 0.9569
• Precision: 0.6981

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
No log	1.0	2	0.6311	:	0.688	0.4943	0.8152	0.9885	0.6935
No log	2.0	4	0.6316	:	0.674	0.5268	0.7939	0.9023	0.7088
No log	3.0	6	0.6199	:	0.686	0.5002	0.8120	0.9741	0.6961
No log	4.0	8	0.6475	:	0.652	0.5277	0.7717	0.8448	0.7101
0.6559	5.0	10	0.6269	:	0.682	0.5048	0.8073	0.9569	0.6981

Framework versions

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