Edit model card

Visualize in Weights & Biases

mistral-7b-base-dpo-all_pairs-listsize_8-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: 0.3529
  • Logps: -322.9456
  • Logits: -1.9966

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
0.3733 0.4275 200 0.3720 -309.9268 -2.2792
0.355 0.8549 400 0.3534 -324.5089 -1.9703

Framework versions

  • Transformers 4.42.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
7.24B params
Tensor type
FP16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for yangzhao02/mistral-7b-dpo-all_pairs

Finetuned
(278)
this model

Collection including yangzhao02/mistral-7b-dpo-all_pairs