mistral-qlora_v4

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: 1.3065
• Mean Token Accuracy: 0.6847
• 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: 3e-05
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Token Accuracy	Num Tokens
1.4435	0.6452	20	1.3836	0.6751	896294
1.3568	1.2903	40	1.3390	0.6800	896294
1.3366	1.9355	60	1.3145	0.6837	896294
1.3456	2.5806	80	1.3065	0.6847	896294

Framework versions

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