scan-8192-16M-test / README.md
zaydzuhri's picture
Model save
dacd8b6 verified
metadata
library_name: transformers
base_model: configs/scan_16M_8192.json
tags:
  - generated_from_trainer
model-index:
  - name: scan-8192-16M-test
    results: []

scan-8192-16M-test

This model is a fine-tuned version of configs/scan_16M_8192.json on an unknown dataset.

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: 0.0003
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine_with_min_lr
  • lr_scheduler_warmup_steps: 200
  • training_steps: 20000

Training results

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0