Mistral-7B-Instruct-v0.2-mirage-bench-sft-teacher-mixtral

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the nthakur/mirage-mistral-sft-instruct dataset. It achieves the following results on the evaluation set:

• Loss: 0.2758

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• 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
0.2844	0.2480	200	0.3115
0.2638	0.4960	400	0.2921
0.2596	0.7440	600	0.2790
0.2458	0.9919	800	0.2758

Framework versions

• PEFT 0.7.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1