Hugging Face's logo

LuangMV97
/
DialoGPT_EmpAI_final_FineTuned2

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
DialoGPT_EmpAI_final_FineTuned2 / README.md
LuangMV97's picture
LuangMV97
End of training
ac5d772 verified
preview code
|
raw
history blame
1.69 kB
metadata
license: mit
base_model: LuangMV97/DialoGPT_EmpAI_final
tags:
  - generated_from_trainer
model-index:
  - name: DialoGPT_EmpAI_final_FineTuned2
    results: []

DialoGPT_EmpAI_final_FineTuned2

This model is a fine-tuned version of LuangMV97/DialoGPT_EmpAI_final on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6669

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 23000
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.6851 1.0 5998 2.7296
2.6523 2.0 11997 2.7154
2.567 3.0 17995 2.6948
2.5206 4.0 23994 2.6792
2.439 5.0 29990 2.6669

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2