mistral_instruct_generation_tr

This model is a fine-tuned version of malhajar/Mistral-7B-Instruct-v0.2-turkish on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.0124

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: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3331	0.1198	20	0.1119
0.0341	0.2395	40	0.0257
0.0207	0.3593	60	0.0180
0.0192	0.4790	80	0.0137
0.0139	0.5988	100	0.0124

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1