zephyr-spin-llama2-data

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Rewards/real: 0.2528
• Rewards/generated: -40.2355
• Rewards/accuracies: 1.0
• Rewards/margins: 40.4883
• Logps/generated: -570.3447
• Logps/real: -131.4776
• Logits/generated: -2.7916
• Logits/real: -2.6700

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
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/real	Rewards/generated	Rewards/accuracies	Rewards/margins	Logps/generated	Logps/real	Logits/generated	Logits/real
0.001	0.29	500	0.0006	1.0682	-20.9797	1.0	22.0478	-377.7859	-123.3242	-2.8941	-2.9115
0.0002	0.58	1000	0.0000	1.4992	-30.9969	1.0	32.4961	-477.9584	-119.0138	-2.7728	-2.6975
0.0009	0.87	1500	0.0000	0.2528	-40.2355	1.0	40.4883	-570.3447	-131.4776	-2.7916	-2.6700

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2