Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

distily
/
distily_seq_len_batch_size

TensorBoard
Safetensors
Distily
llama
Generated from Trainer
Model card Files Files and versions
xet
Metrics Training metrics Community
distily_seq_len_batch_size / logs
34.4 MB
  • 1 contributor
History: 175 commits
lapp0's picture
lapp0
End of training
74211cb verified over 1 year ago
  • dataset_max_seq_length=1024, dataset_sample_size=1000000, per_device_train_batch_size=16
    Training in progress, step 5000 over 1 year ago
  • dataset_max_seq_length=1024, dataset_sample_size=1000000, per_device_train_batch_size=4
    End of training over 1 year ago
  • dataset_max_seq_length=2048, dataset_sample_size=500000, per_device_train_batch_size=4
    Training in progress, step 10000 over 1 year ago
  • dataset_max_seq_length=512, dataset_sample_size=2000000, learning_rate=0.0001, per_device_train_batch_size=16
    Training in progress, step 5000 over 1 year ago
  • dataset_max_seq_length=512, dataset_sample_size=2000000, per_device_train_batch_size=16, warmup_ratio=0.1
    Training in progress, step 5000 over 1 year ago
  • dataset_max_seq_length=512, dataset_sample_size=2000000, per_device_train_batch_size=16
    Training in progress, step 5000 over 1 year ago
  • dataset_max_seq_length=512, dataset_sample_size=2000000, per_device_train_batch_size=4
    Training in progress, step 20000 over 1 year ago