LuangMV97's picture
End of training
c26d15c verified
|
raw
history blame
1.91 kB
metadata
license: mit
base_model: microsoft/DialoGPT-small
tags:
  - generated_from_trainer
model-index:
  - name: DialoGPT_EmpAI_smallPrueba2
    results: []

DialoGPT_EmpAI_smallPrueba2

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

  • Loss: 2.7999

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 3.5303
5.2957 2.0 967 3.1013
3.4534 3.0 1450 2.9551
3.1442 4.0 1934 2.8904
3.0052 5.0 2417 2.8491
2.9176 6.0 2901 2.8253
2.8624 7.0 3384 2.8110
2.8284 8.0 3868 2.8027
2.8079 9.0 4351 2.8005
2.8005 9.99 4830 2.7999

Framework versions

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