augmented_model_fast_4_b_3e6batch16

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

• Loss: 1.2149
• Accuracy: 0.5193
• F1: 0.5214
• Precision: 0.5244
• Recall: 0.5196

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: 3e-06
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.567	0.1566	500	0.9748	0.6385	0.6316	0.6368	0.6321
0.6834	0.3133	1000	0.8564	0.6556	0.6458	0.6506	0.6474
0.6231	0.4699	1500	0.8447	0.6600	0.6517	0.6555	0.6526
0.6625	0.6266	2000	0.8117	0.6648	0.6574	0.6608	0.6579
0.6663	0.7832	2500	0.7971	0.6709	0.6634	0.6657	0.6640
0.6581	0.9398	3000	0.7967	0.6753	0.6674	0.6693	0.6682
0.5847	1.0965	3500	0.8181	0.6792	0.6707	0.6730	0.6717
0.5453	1.2531	4000	0.8346	0.6831	0.6743	0.6774	0.6755
0.5543	1.4098	4500	0.8275	0.6831	0.6739	0.6766	0.6753
0.5469	1.5664	5000	0.8255	0.6836	0.6754	0.6782	0.6763
0.5248	1.7231	5500	0.8275	0.6849	0.6757	0.6782	0.6771
0.5603	1.8797	6000	0.8228	0.6844	0.6752	0.6777	0.6766

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1