trainer8

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

• Loss: 1.6219
• Precision: 0.6754
• Recall: 0.6190
• F1: 0.6211
• Accuracy: 0.6190

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.8672	0.57	30	1.7381	0.3395	0.3810	0.2691	0.3810
1.5788	1.13	60	1.4116	0.3983	0.5	0.4344	0.5
1.1325	1.7	90	1.1528	0.6029	0.6071	0.5755	0.6071
0.7556	2.26	120	0.8986	0.6796	0.6310	0.6237	0.6310
0.458	2.83	150	0.9989	0.6815	0.6071	0.5981	0.6071
0.2407	3.4	180	1.2074	0.6018	0.5476	0.5200	0.5476
0.2018	3.96	210	1.0334	0.7163	0.6786	0.6847	0.6786
0.0545	4.53	240	1.2405	0.6544	0.5952	0.5899	0.5952
0.0464	5.09	270	1.1513	0.7442	0.6905	0.6869	0.6905
0.0105	5.66	300	1.5555	0.7304	0.6429	0.6344	0.6429
0.025	6.23	330	1.3049	0.7119	0.6310	0.6343	0.6310
0.0045	6.79	360	1.3200	0.6754	0.6190	0.6211	0.6190
0.0036	7.36	390	1.4460	0.6754	0.6190	0.6211	0.6190
0.0031	7.92	420	1.4770	0.6754	0.6190	0.6211	0.6190
0.0028	8.49	450	1.4846	0.6754	0.6190	0.6211	0.6190
0.0023	9.06	480	1.5149	0.6666	0.6071	0.6086	0.6071
0.0022	9.62	510	1.5523	0.6666	0.6071	0.6086	0.6071
0.002	10.19	540	1.5883	0.6754	0.6190	0.6211	0.6190
0.0019	10.75	570	1.6123	0.6754	0.6190	0.6211	0.6190
0.0016	11.32	600	1.6183	0.6754	0.6190	0.6211	0.6190
0.0017	11.89	630	1.6112	0.6754	0.6190	0.6211	0.6190
0.0016	12.45	660	1.6067	0.6754	0.6190	0.6211	0.6190
0.0015	13.02	690	1.6122	0.6754	0.6190	0.6211	0.6190
0.0014	13.58	720	1.6163	0.6754	0.6190	0.6211	0.6190
0.0014	14.15	750	1.6194	0.6754	0.6190	0.6211	0.6190
0.0015	14.72	780	1.6215	0.6754	0.6190	0.6211	0.6190

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2