shawgpt-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: 1.3129

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 14
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.4825	1.0	13	3.0919
2.8203	2.0	26	2.5023
2.1986	3.0	39	1.9872
1.7371	4.0	52	1.6736
1.4784	5.0	65	1.4733
1.3057	6.0	78	1.4058
1.2249	7.0	91	1.3614
1.217	8.0	104	1.3388
1.1828	9.0	117	1.3264
1.1419	10.0	130	1.3190
1.1518	11.0	143	1.3171
1.1042	12.0	156	1.3147
1.1249	13.0	169	1.3136
1.0984	14.0	182	1.3129

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1