MobileLLM-125M-e3.9.24.4.1

This model is a fine-tuned version of facebook/MobileLLM-125M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 5.5191

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
25.7447	0.2016	63	6.5785
24.4652	0.4032	126	6.1067
22.3697	0.6048	189	5.7696
20.6637	0.8064	252	5.5191

Framework versions

• Transformers 4.47.1
• Pytorch 2.6.0.dev20241231+cu118
• Datasets 3.0.2
• Tokenizers 0.21.0