mistral-7b-finetuned-lime-5-epoch

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

• Loss: 0.6054

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.8705	1.0	21	0.9399
0.2649	2.0	42	0.5901
0.0873	3.0	63	0.5531
0.0295	4.0	84	0.5929
0.0134	5.0	105	0.6054

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.2
• Datasets 2.18.0
• Tokenizers 0.15.2