NTCAL/norbert2_sentiment_norec_to_gpu_500_rader_8

Kjøretid:

{'train_runtime': 432.2459, 'train_samples_per_second': 5.784, 'train_steps_per_second': 0.012, 'train_loss': 0.6640925884246827, 'epoch': 5.0}

Time: 432.25

Samples/second: 5.78

GPU memory occupied: 11314 MB.

norbert2_sentiment_norec_to_gpu_500_rader_8

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: 0.6252
• Compute Metrics: :
• Accuracy: 0.692
• Balanced Accuracy: 0.4971
• F1 Score: 0.8180
• Recall: 0.9943
• Precision: 0.6948

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: 64
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• 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	1	0.6370	:	0.696	0.5	0.8208	1.0	0.696
No log	2.0	2	0.6319	:	0.684	0.4932	0.8119	0.9799	0.6931
No log	3.0	3	0.6415	:	0.692	0.4971	0.8180	0.9943	0.6948
No log	4.0	4	0.6299	:	0.692	0.4971	0.8180	0.9943	0.6948
No log	5.0	5	0.6252	:	0.692	0.4971	0.8180	0.9943	0.6948

Framework versions

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