You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

moe_d_het

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

  • Loss: 4.7312

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: 32
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 1024
  • total_eval_batch_size: 64
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 15297
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 0 0 10.9726
6.3815 0.6537 1000 6.1101
5.6893 1.0 1530 5.4428
5.2263 1.3072 2000 5.1823
4.916 1.9609 3000 4.8803
4.916 2.0 3060 4.8665
4.6588 2.6145 4000 4.7204
4.4151 3.2680 5000 4.6267
4.3816 3.9217 6000 4.5479
4.1873 4.5752 7000 4.5310
3.9649 5.2288 8000 4.5390
3.9952 5.8825 9000 4.5147
3.7926 6.5360 10000 4.5653
3.5756 7.1896 11000 4.6144
3.6211 7.8432 12000 4.6217
3.4485 8.4968 13000 4.6837
3.4576 9.0 13770 4.6867
3.3107 9.1503 14000 4.7196
3.3235 9.8040 15000 4.7310

Framework versions

  • Transformers 4.53.1
  • Pytorch 2.7.0+cu126
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
-
Safetensors
Model size
0.5B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Evaluation results