Meta-Llama-3-8B-Instruct-mirage-mirage-gpt-4o-sft-instruct-llama-3

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the nthakur/mirage-gpt-4o-sft-instruct-llama-3 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2505

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.3599	0.1268	200	0.3172
0.3295	0.2536	400	0.2919
0.323	0.3803	600	0.2789
0.3274	0.5071	800	0.2686
0.3171	0.6339	1000	0.2597
0.3034	0.7607	1200	0.2540
0.265	0.8875	1400	0.2510

Framework versions

• PEFT 0.10.0
• Transformers 4.44.0
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1