Hugging Face's logo

IProject-10
/
persona-chat-gpt-neo

Safetensors
gpt_neo
Generated from Trainer
Model card Files Community
persona-chat-gpt-neo / README.md
IProject-10's picture
IProject-10
End of training
86e3716 verified
preview code
|
raw
history blame
1.54 kB
metadata
license: mit
base_model: IProject-10/gpt-neo-daily-dialog
tags:
  - generated_from_trainer
model-index:
  - name: persona-chat-gpt-neo
    results: []

persona-chat-gpt-neo

This model is a fine-tuned version of IProject-10/gpt-neo-daily-dialog on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3551

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.8898 0.9998 1117 2.0927
0.7337 1.9996 2234 2.2669
0.6361 2.9993 3351 2.3551

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1