Llama3_AAID_mixed_train_deneme

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the AAID_mixed dataset. It achieves the following results on the evaluation set:

• Loss: 0.8216

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7577	0.0219	20	0.8374
0.4704	0.0438	40	0.8379
0.4495	0.0656	60	0.8216
0.4326	0.0875	80	0.8272
0.421	0.1094	100	0.8494
0.406	0.1313	120	0.8483
0.3974	0.1531	140	0.8315
0.3989	0.1750	160	0.8574

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1