yosefw/llama-3.2-amharic-32k-1024-v8

<!-- 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. -->

llama-3.2-amharic-32k-1024-v8

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 3.9086
• —evalmodelpreparation_time: 0.0016
• —eval_runtime: 16.8971
• —evalsamplesper_second: 619.276
• —evalstepsper_second: 5.563
• —epoch: 13.5067
• —step: 130151

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
• —trainbatchsize: 112
• —evalbatchsize: 112
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —lrschedulerwarmup_steps: 2000
• —num_epochs: 16
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.48.0
• —Pytorch 2.5.1+cu121
• —Datasets 3.2.0
• —Tokenizers 0.21.0