TBD-LLaMA-1B-final_direction_reverberation

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7797

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: 8e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 1884

Training results

Training Loss	Epoch	Step	Validation Loss
0.8284	0.1061	200	0.7949
0.7729	0.2122	400	0.7919
0.7951	0.3183	600	0.7891
0.7963	0.4244	800	0.7865
0.7935	0.5306	1000	0.7838
0.8194	0.6367	1200	0.7824
0.8018	0.7428	1400	0.7808
0.8178	0.8489	1600	0.7800
0.7927	0.9550	1800	0.7797

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0a0+5228986c39.nv25.05
• Datasets 4.0.0
• Tokenizers 0.22.0