TWON-Agent-OSN-Post-en

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.8993

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss
1.6374	1.1429	200	1.1784
1.2494	2.2857	400	1.0614
1.1835	3.4286	600	0.9980
1.1382	4.5714	800	0.9540
1.1128	5.7143	1000	0.9240
1.0937	6.8571	1200	0.9065
1.0809	8.0	1400	0.8993

Framework versions

• PEFT 0.12.0
• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0