Hugging Face's logo

yangzhao02
/
mistral-7b-listmle

Safetensors
mistral
alignment-handbook
ndcg
trl
Generated from Trainer
Model card Files Community
mistral-7b-listmle / README.md
yangzhao02's picture
yangzhao02
End of training
80794cc verified
preview code
|
raw
history blame contribute delete
2.1 kB
metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
  - alignment-handbook
  - ndcg
  - trl
  - generated_from_trainer
  - trl
  - ndcg
  - generated_from_trainer
datasets:
  - yangzhao02/ListUltraFeedback
model-index:
  - name: mistral-7b-base-dpo-list_mle-listsize_8-beta_0.05-batchsize_128
    results: []

Visualize in Weights & Biases

mistral-7b-base-dpo-list_mle-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: 6.7425
  • Logps: -316.4365
  • Logits: -2.1289

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 Logits Logps Validation Loss
6.8406 0.5343 250 -2.2186 -311.0428 6.9513

Framework versions

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