yangzhao02/mistral-7b-opo

mistral-7b-base-neural_ndcg-listsize_8-tau_1.0-beta_0.05-batchsize_128

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:

• Loss: -0.9924
• Logps: -390.4838
• Logits: -0.7300

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 16
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Logps	Logits
-0.9908	0.4275	200	-0.9910	-365.4714	-0.6106
-0.9924	0.8549	400	-0.9923	-393.3539	-0.6678

Framework versions

• Transformers 4.42.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1