This model is a fine-tuned version of iulik-pisik/horoscope_model_small on the Vreme ProTV dataset. It achieves the following results on the evaluation set:

Loss: 0.1875
Wer: 8.8779

Model description

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0134	5.79	1000	0.1508	9.515
0.0006	11.82	2000	0.1713	9.1862
0.0001	17.39	3000	0.1875	8.8779

Framework versions

Transformers 4.39.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

iulik-pisik/horoscop_vreme_small

Horoscope Model Base - finetuned on weather

Model description

Training procedure

Training hyperparameters

Training results

Framework versions

iulik-pisik/
horoscop_vreme_small