1b_distill_width_prune

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

• Loss: 1.5712

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: 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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• training_steps: 20000

Training results

Training Loss	Epoch	Step	Validation Loss
1.3657	0.0413	10000	1.7362
1.2947	0.0827	20000	1.5713

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.1.2+cu121
• Datasets 2.20.0
• Tokenizers 0.20.3