phi3-spin-Llama2-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: 0.0005
• Rewards/real: 0.7586
• Rewards/generated: -92.4366
• Rewards/accuracies: 1.0
• Rewards/margins: 93.1952
• Logps/generated: -1271.4552
• Logps/real: -248.8362
• 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
0.0901	0.29	500	0.0191	-0.2438	-52.9080	0.9922	52.6642	-876.1692	-258.8595	-inf	-inf
0.0024	0.58	1000	0.0014	1.6797	-78.7354	1.0	80.4151	-1134.4436	-239.6249	-inf	-inf
0.0926	0.87	1500	0.0005	0.7586	-92.4366	1.0	93.1952	-1271.4552	-248.8362	-inf	-inf

Framework versions

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