Edit model card

dpo-xcomet_xl_xxl-10p-shuff-5e-8-full-from-sft-tiny

This model is a fine-tuned version of martimfasantos/sft-xcomet_xl_xxl-chosen-10lp-shuff-full-tiny_new on the Unbabel/TowerAligned-v0.1 dataset.

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-08
  • train_batch_size: 1
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 64
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
1.1B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for martimfasantos/dpo-xcomet_xl_xxl-10p-shuff-5e-8-full-from-sft-tiny