RichardErkhov/KimByeongSu_-_gpt-neo-1.3B-cs-finetuning-500-1-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt-neo-1.3B-cs-finetuning-500-1 - bnb 8bits

• Model creator: https://huggingface.co/KimByeongSu/
• Original model: https://huggingface.co/KimByeongSu/gpt-neo-1.3B-cs-finetuning-500-1/

Original model description:

license: mit base_model: EleutherAI/gpt-neo-1.3B tags: - generated_from_trainer model-index: - name: gpt-neo-1.3B-cs-finetuning-500-1 results: []

gpt-neo-1.3B-cs-finetuning-500-1

This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8937

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	26	2.9272
No log	2.0	52	2.8625
No log	3.0	78	2.8937

Framework versions

• Transformers 4.36.2
• Pytorch 1.13.1+cu117
• Datasets 2.14.6
• Tokenizers 0.15.0