README.md

metadata

library_name: peft
license: mit
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
datasets:
  - tttx/test-star-9-step3-trajectories
model-index:
  - name: masked-star-test-star-9-step3
    results: []

masked-star-test-star-9-step3

This model is a fine-tuned version of tttx/masked-star-test-star-9-step2 on the tttx/test-star-9-step3-trajectories dataset. It achieves the following results on the evaluation set:

• Loss: 3.8717

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-05
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.3298	1.0	1	3.9557
0.4377	2.0	2	3.8717

Framework versions

• PEFT 0.13.2
• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3