suryagpt-ft

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

• Loss: 0.7170

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: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
3.9479	0.9412	8	2.9026
2.0922	2.0	17	1.5301
1.4095	2.9412	25	1.1705
1.0244	4.0	34	1.0004
1.0198	4.9412	42	0.9060
0.8214	6.0	51	0.8174
0.8465	6.9412	59	0.7645
0.7057	8.0	68	0.7328
0.7711	8.9412	76	0.7200
0.5994	9.4118	80	0.7170

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3