Edit model card

RoBERTa_EmpAI_FineTuned

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

  • Loss: 0.0707

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 483 7.4258
12.6437 2.0 967 2.1112
4.9019 3.0 1450 0.0872
0.4036 4.0 1934 0.0765
0.0802 4.99 2415 0.0754
0.0737 6.0 2898 0.0708
0.0749 7.0 3382 0.0705
0.0712 8.0 3865 0.0702
0.0708 9.0 4349 0.0692
0.0698 9.99 4830 0.0696

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
125M params
Tensor type
F32
·

Finetuned from