metadata

license: apache-2.0
base_model: openthaigpt/openthaigpt-gpt2-instructgpt-poc-0.0.4
tags:
  - generated_from_trainer
model-index:
  - name: test-asp
    results: []

test-asp

This model is a fine-tuned version of openthaigpt/openthaigpt-gpt2-instructgpt-poc-0.0.4 on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 0.1547
eval_precision: 0.7684
eval_recall: 0.8573
eval_f1: 0.8104
eval_accuracy: 0.9544
eval_runtime: 7.0634
eval_samples_per_second: 86.219
eval_steps_per_second: 2.832
epoch: 74.3
step: 1486

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 100

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1