masterkristall's picture
End of training
539dff3 verified
|
raw
history blame
2.21 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: ml_gen_seo_google_23_05_2024
    results: []

ml_gen_seo_google_23_05_2024

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7733

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.9707 0.1534 25 0.7829
0.942 0.3067 50 0.7871
0.8262 0.4601 75 0.7827
0.9281 0.6135 100 0.7894
0.9142 0.7669 125 0.7706
0.8757 0.9202 150 0.7701
0.8237 1.0736 175 0.7883
0.8219 1.2270 200 0.7684
0.8051 1.3804 225 0.7779
0.7711 1.5337 250 0.7831
0.8685 1.6871 275 0.7721
0.7802 1.8405 300 0.7804
0.778 1.9939 325 0.7812
0.7685 2.1472 350 0.7782
0.8233 2.3006 375 0.7678
0.7752 2.4540 400 0.7717
0.7144 2.6074 425 0.7722
0.7322 2.7607 450 0.7719
0.6849 2.9141 475 0.7733

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Tokenizers 0.19.1