mistral-sft-kcenter-5k

This model is a fine-tuned version of AmberYifan/mistral-safe-sft-full on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1925
• Rewards/real: 5.5330
• Rewards/generated: -4.6681
• Rewards/accuracies: 0.9922
• Rewards/margins: 10.2011
• Logps/generated: -304.9019
• Logps/real: -157.3288
• Logits/generated: -2.8831
• Logits/real: -2.8163

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
0.1804	0.6369	100	0.1925	5.5330	-4.6681	0.9922	10.2011	-304.9019	-157.3288	-2.8831	-2.8163

Framework versions

• Transformers 4.43.3
• Pytorch 2.2.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1