convergent-llama-300M-muon-window-64

<!-- 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-300M-v5-window_64

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

• Loss: 3.4520
• Num Input Tokens Seen: 9437184000

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: 32
• eval_batch_size: 32
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• total_eval_batch_size: 64
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Framework versions

• Transformers 5.3.0
• Pytorch 2.10.0+cu128
• Datasets 4.7.0
• Tokenizers 0.22.2