mistral-instruct-resumebot

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8528

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.0684	0.7273	2	3.2486
2.4659	1.8182	5	2.7598
2.1876	2.9091	8	2.4245
1.9866	4.0	11	2.1931
2.7635	4.7273	13	2.0712
1.7349	5.8182	16	1.9333
1.671	6.9091	19	1.8615
1.3639	7.2727	20	1.8528

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1