Mixtral_45b_SIG_v2

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5649
• eval_runtime: 6.9822
• eval_samples_per_second: 5.156
• eval_steps_per_second: 0.716
• epoch: 10.87
• step: 250

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: 2.5e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 0.03
• training_steps: 1000

Framework versions

• PEFT 0.10.0
• Transformers 4.37.2
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.1