sexed-mistral-7b-sft-lora

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.2681

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.5069	0.8380	4	0.4851
0.4188	1.8854	9	0.4025
0.3461	2.9329	14	0.3485
0.3204	3.9804	19	0.3211
0.3053	4.8183	23	0.3053
0.2914	5.8658	28	0.2923
0.2802	6.9133	33	0.2851
0.2733	7.9607	38	0.2795
0.273	8.7987	42	0.2762
0.2746	9.8462	47	0.2732
0.2673	10.8936	52	0.2709
0.2591	11.9411	57	0.2695
0.2602	12.9885	62	0.2686
0.26	13.8265	66	0.2683
0.2668	14.8740	71	0.2682
0.2598	15.9214	76	0.2681
0.26	16.7594	80	0.2681

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.1.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1