GPT-2_para3M / README.md
Toflamus's picture
Toflamus/GPT-2_para3M
2156f95
|
raw
history blame
1.38 kB
metadata
license: mit
base_model: gpt2
tags:
  - generated_from_trainer
model-index:
  - name: GPT-2_para3M
    results: []

GPT-2_para3M

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

  • Loss: 2.3235

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: 0.0005
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
3.6451 0.47 5000 2.4368
2.5113 0.94 10000 2.3235

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3