Edit model card

Chitti-Base-model-for-GPT-v7

This model is a fine-tuned version of Dhahlan2000/Chitti-Base-model-for-GPT-v6 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.9886
  • Bleu: 3.9298
  • Gen Len: 12.3167

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
3.2472 1.0 9282 3.0258 3.4033 12.52
3.2282 2.0 18564 3.0057 3.6317 12.416
3.2089 3.0 27846 2.9930 3.953 12.3507
3.1887 4.0 37128 2.9886 3.9298 12.3167

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from