ossbert-onc-unlab-bs64-5epochs

This model is a fine-tuned version of ania3000/untrained-ossbert-e on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4311

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
5.6292 0.4515 1000 4.9285
4.7574 0.9029 2000 4.4274
4.3777 1.3544 3000 4.1482
4.1427 1.8059 4000 3.9402
3.9638 2.2573 5000 3.7863
3.8346 2.7088 6000 3.6773
3.7363 3.1603 7000 3.6001
3.661 3.6117 8000 3.5307
3.6089 4.0632 9000 3.4765
3.555 4.5147 10000 3.4482
3.5316 4.9661 11000 3.4311

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.9.1+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.1
Downloads last month
5
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AlexeySorokin/ossbert-onc-unlab-bs64-5epochs

Finetuned
(3)
this model
Finetunes
1 model