prompt-extend / README.md
geek1024's picture
update model card README.md
d232af7
|
raw
history blame
1.71 kB
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: prompt-extend
    results: []

prompt-extend

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

  • Loss: 2.1502

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 64
  • 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_ratio: 0.1
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.3823 0.35 100 4.2083
3.72 0.69 200 3.2991
3.1185 1.04 300 2.8394
2.7284 1.39 400 2.5546
2.4932 1.74 500 2.3679
2.3408 2.08 600 2.2430
2.1997 2.43 700 2.1748
2.1631 2.78 800 2.1502

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.6.1
  • Tokenizers 0.13.2