robbert_seed35_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: 0.3736
• Precisions: 0.8703
• Recall: 0.8320
• F-measure: 0.8460
• Accuracy: 0.9455

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: 35
• 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
0.4597	1.0	236	0.2601	0.8795	0.7027	0.7178	0.9224
0.2359	2.0	472	0.2642	0.7554	0.7436	0.7448	0.9209
0.1425	3.0	708	0.2765	0.8100	0.7809	0.7872	0.9318
0.0893	4.0	944	0.2727	0.8404	0.7708	0.7885	0.9340
0.0597	5.0	1180	0.3136	0.8572	0.7712	0.7963	0.9361
0.0446	6.0	1416	0.3246	0.8474	0.7824	0.7947	0.9409
0.029	7.0	1652	0.3266	0.8266	0.7944	0.7985	0.9361
0.0181	8.0	1888	0.3377	0.8564	0.8139	0.8257	0.9422
0.0152	9.0	2124	0.3578	0.8240	0.8439	0.8297	0.9426
0.0121	10.0	2360	0.3270	0.8659	0.8292	0.8444	0.9475
0.0094	11.0	2596	0.3510	0.8742	0.8274	0.8455	0.9467
0.0057	12.0	2832	0.3674	0.8435	0.8350	0.8379	0.9441
0.0042	13.0	3068	0.3746	0.8708	0.8313	0.8458	0.9458
0.0027	14.0	3304	0.3736	0.8703	0.8320	0.8460	0.9455

Framework versions

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