GPT2-705-RUN1 / README.md
ninagroot's picture
ninagroot/GPT2-705Mtest
858dc8a verified
|
raw
history blame
1.88 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: GPT2-705M
    results: []

GPT2-705M

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

  • Loss: 4.3316

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: 0.00025
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 12
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
5.8964 1.0 69 5.8372
5.2016 2.0 138 5.0017
4.4098 3.0 207 4.6658
4.2459 4.0 276 4.5260
3.9837 5.0 345 4.4107
3.8526 6.0 414 4.3741
3.5545 7.0 483 4.3328
3.392 8.0 552 4.3175
3.3396 9.0 621 4.3236
3.0426 10.0 690 4.3322
3.028 11.0 759 4.3254
3.0344 12.0 828 4.3316

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0