phi3-spin-phi3-data

This model is a fine-tuned version of microsoft/Phi-3-small-8k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Rewards/real: -20.4314
• Rewards/generated: -59.7851
• Rewards/accuracies: 1.0
• Rewards/margins: 39.3538
• Logps/generated: -1415.6521
• Logps/real: -459.2887
• Logits/generated: -inf
• Logits/real: -inf

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
0.0013	0.32	500	0.0028	-15.0276	-43.9108	1.0	28.8832	-1256.9089	-405.2515	-inf	-inf
0.0007	0.64	1000	0.0001	-20.5002	-56.1393	1.0	35.6391	-1379.1938	-459.9772	-inf	-inf
0.0081	0.96	1500	0.0000	-20.4314	-59.7851	1.0	39.3538	-1415.6521	-459.2887	-inf	-inf

Framework versions

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