OpenELM-450M_lora

This model is a fine-tuned version of apple/OpenELM-450M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6940
• Rewards/chosen: 0.0062
• Rewards/rejected: 0.0064
• Rewards/accuracies: 0.4748
• Rewards/margins: -0.0002
• Logps/rejected: -567.8893
• Logps/chosen: -579.9698
• Logits/rejected: -11.8584
• Logits/chosen: -12.0367

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-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6943	0.8975	300	0.6940	0.0062	0.0064	0.4748	-0.0002	-567.8893	-579.9698	-11.8584	-12.0367

Framework versions

• PEFT 0.11.0
• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1