metadata

license: other
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: output_2
    results: []

monogptari-6.7b

This model is a fine-tuned version of facebook/opt-6.7b on an english monogatari (物語) dataset. It achieves the following results on the evaluation set:

Loss: 0.7030
Accuracy: 0.8436

Quick start

from transformers import pipeline

generator = pipeline('text-generation', model="tensorcat/monogptari-6.7b" , device=0, use_fast=False)
generator("I think its about time I talked about Kiss-Shot", min_length=100, max_length=800, 
    do_sample=True, early_stopping=True, temperature=.98, top_k=50, top_p=1.0)

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Framework versions

Transformers 4.22.0.dev0
Pytorch 1.11.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1