fine_tuned_cb_sloroberta

This model is a fine-tuned version of EMBEDDIA/sloberta on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0242
• Accuracy: 0.6818
• F1: 0.6317

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7427	3.5714	50	1.4714	0.3182	0.1536
0.5036	7.1429	100	0.8326	0.6818	0.6352
0.229	10.7143	150	1.0356	0.6364	0.5893
0.0871	14.2857	200	0.6893	0.6818	0.6680
0.0344	17.8571	250	0.9159	0.7727	0.7671
0.0211	21.4286	300	1.0231	0.6818	0.6352
0.0169	25.0	350	1.0289	0.6364	0.5893
0.0159	28.5714	400	1.0242	0.6818	0.6317

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1