v3.0-RAFT-mistral-7b-lora

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: 1.1933

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 5
• total_train_batch_size: 5
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.5869	0.9856	41	1.6005
1.4884	1.9952	83	1.4960
1.4016	2.9808	124	1.4130
1.3449	3.9904	166	1.3445
1.2806	5.0	208	1.2857
1.2675	5.9856	249	1.2417
1.2617	6.9952	291	1.2131
1.2008	7.9808	332	1.1990
1.2042	8.9904	374	1.1938
1.2077	9.8558	410	1.1933

Framework versions

• PEFT 0.11.1
• Transformers 4.43.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1