prompt_fine_tuned_CB_sloberta

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

• Loss: 1.7179
• Accuracy: 0.3182
• F1: 0.1591

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: 0.003
• 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
0.8289	3.5714	50	1.9695	0.3182	0.1536
0.7265	7.1429	100	1.4997	0.3636	0.2273
0.6323	10.7143	150	1.4937	0.3636	0.2891
0.5933	14.2857	200	1.7106	0.2727	0.2290
0.5496	17.8571	250	1.3607	0.3636	0.2821
0.4356	21.4286	300	1.4913	0.3182	0.1536
0.3874	25.0	350	1.6290	0.2727	0.1527
0.3719	28.5714	400	1.7179	0.3182	0.1591

Framework versions

• PEFT 0.11.1
• Transformers 4.40.2
• Pytorch 2.1.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1