mistral-qlora_v2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.2705
• Mean Token Accuracy: 0.6893
• Num Tokens: 896294

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Token Accuracy	Num Tokens
1.4786	0.3077	8	1.3624	0.6773	896294
1.3292	0.6154	16	1.3184	0.6833	896294
1.3818	0.9231	24	1.2928	0.6865	896294
1.2772	1.2308	32	1.2793	0.6878	896294
1.3531	1.5385	40	1.2725	0.6890	896294
1.2099	1.8462	48	1.2705	0.6893	896294

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.8.0+cu126
• Datasets 2.20.0
• Tokenizers 0.19.1