mistral_instruct_generation_2000

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1720
• eval_runtime: 42.3872
• eval_samples_per_second: 3.232
• eval_steps_per_second: 0.425
• epoch: 8.43
• step: 1180

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• training_steps: 2000

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0