Neo-VN-2.7B

Work-in-progress. Current version is very bad.

This model is a fine-tuned version of huggingface.co/EleutherAI/opt-neo-2.7b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4748
• Accuracy: 0.4671

Model description

Neo-VN-2.7B is a transformer model based on EleutherAI's replication of GPT-3.

Training procedure

Fine-tuned on 233MB of conversational data.

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: 32
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
2.3941	1	20460	0.4671	2.4748

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.12.1+cu116
• Datasets 2.4.0
• Tokenizers 0.12.1