robbert_seed33_1311

This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3569
• Precisions: 0.8341
• Recall: 0.8159
• F-measure: 0.8240
• Accuracy: 0.9424

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: 7.5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 33
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Precisions	Recall	F-measure	Accuracy
0.4471	1.0	236	0.2653	0.7696	0.7076	0.7131	0.9195
0.2264	2.0	472	0.2367	0.8184	0.7497	0.7777	0.9279
0.1443	3.0	708	0.2710	0.8069	0.7735	0.7817	0.9315
0.0869	4.0	944	0.2697	0.8391	0.7998	0.8150	0.9364
0.0531	5.0	1180	0.2877	0.8622	0.7952	0.8178	0.9393
0.0373	6.0	1416	0.3171	0.8338	0.8120	0.8204	0.9422
0.0238	7.0	1652	0.3312	0.8247	0.7921	0.8047	0.9390
0.0159	8.0	1888	0.3569	0.8341	0.8159	0.8240	0.9424
0.0122	9.0	2124	0.3832	0.8398	0.8127	0.8238	0.9422
0.0058	10.0	2360	0.4160	0.8288	0.7975	0.8098	0.9400
0.0059	11.0	2596	0.4153	0.8321	0.8012	0.8124	0.9405
0.0045	12.0	2832	0.4399	0.8130	0.7909	0.7994	0.9369
0.0024	13.0	3068	0.4357	0.8358	0.8026	0.8163	0.9409
0.0035	14.0	3304	0.4391	0.8374	0.8036	0.8175	0.9414

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1