kikusuka/breezy-78m-phase1

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

breezy-78m-phase1

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 4.8813

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: 0.0004
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 16
• —totaltrainbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosinewithmin_lr
• —lrschedulerwarmup_steps: 1000
• —training_steps: 50000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 5.0.0
• —Pytorch 2.10.0+cu128
• —Datasets 5.0.0
• —Tokenizers 0.22.2