rus

This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2060
  • F1-micro: 0.7655
  • F1-macro: 0.7546

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: 3e-05
  • train_batch_size: 32
  • 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: 26
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss F1-micro F1-macro
0.4853 1.0 67 0.3468 0.3634 0.2305
0.3047 2.0 134 0.2638 0.6634 0.5848
0.2186 3.0 201 0.2191 0.7466 0.7307
0.1747 4.0 268 0.2060 0.7655 0.7546

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
167M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for jaycentg/rus

Finetuned
(1760)
this model