JunxiongWang/llama3_mamba_0_5_sft

This model is a fine-tuned version of JunxiongWang/llama3_0.50_mamba_progressive on the JunxiongWang/sftdataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.6645

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.69	1.0	46554	0.6645

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1