Edit model card

Vreme Model base - finetuned on horoscope

This model is a fine-tuned version of iulik-pisik/vreme_model_base on the Horoscop Neti Sandu dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3471
  • Wer: 17.6685

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: 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0111 9.71 1000 0.2991 18.3986
0.001 19.42 2000 0.3298 17.9119
0.0006 29.13 3000 0.3422 17.4252
0.0005 38.83 4000 0.3471 17.6685

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
5
Safetensors
Model size
72.6M params
Tensor type
F32
·
Invalid base_model specified in model card metadata. Needs to be a model id from hf.co/models.

Evaluation results