distilbert-base-uncased-finetuned-Multi_classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5588
• Accuracy: 0.7266
• Macro Averaged Precision: 0.6830
• Micro Averaged Precision: 0.7266
• Macro Averaged Recall: 0.5652
• Micro Averaged Recall: 0.7266
• Macro Averaged F1: 0.5513
• Micro Averaged F1: 0.7266

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro Averaged Precision	Micro Averaged Precision	Macro Averaged Recall	Micro Averaged Recall	Macro Averaged F1	Micro Averaged F1
0.5811	1.0	635	0.5745	0.7055	0.3527	0.7055	0.5	0.7055	0.4137	0.7055
0.5467	2.0	1270	0.5588	0.7266	0.6830	0.7266	0.5652	0.7266	0.5513	0.7266
0.4724	3.0	1905	0.6347	0.7109	0.6328	0.7109	0.5873	0.7109	0.5906	0.7109
0.2379	4.0	2540	0.9110	0.7078	0.6281	0.7078	0.5874	0.7078	0.5910	0.7078
0.1511	5.0	3175	1.2270	0.6953	0.6168	0.6953	0.5963	0.6953	0.6011	0.6953
0.1074	6.0	3810	1.6106	0.7188	0.6470	0.7188	0.5859	0.7188	0.5875	0.7188
0.0935	7.0	4445	1.8533	0.7070	0.6266	0.7070	0.5861	0.7070	0.5895	0.7070
0.037	8.0	5080	2.0315	0.6875	0.6082	0.6875	0.5923	0.6875	0.5964	0.6875
0.0294	9.0	5715	2.0726	0.7078	0.6295	0.7078	0.5928	0.7078	0.5975	0.7078
0.0238	10.0	6350	2.1236	0.7086	0.6303	0.7086	0.5918	0.7086	0.5963	0.7086

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.1+cu117
• Datasets 1.18.4
• Tokenizers 0.12.1