metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct-1M
tags:
- alignment-handbook
- ndcg
- trl
- generated_from_trainer
- trl
- ndcg
- generated_from_trainer
datasets:
- yangzhao02/ListUltraFeedback
model-index:
- name: qwen2.5-7b-lipo
results: []
qwen2.5-7b-lipo
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct-1M on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:
- Loss: 0.0017
- Logps: -661.8630
- Logits: -0.6117
- Rank Correct Batch: 16.5203
- Rank Pair Batch: 28.0
- Rank Accuracy Batch: 0.5900
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: 8
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Logps | Logits | Rank Correct Batch | Rank Pair Batch | Rank Accuracy Batch |
|---|---|---|---|---|---|---|---|---|
| 0.0021 | 0.2672 | 125 | 0.0021 | -582.2852 | -0.6831 | 15.8902 | 28.0 | 0.5675 |
| 0.0019 | 0.5344 | 250 | 0.0018 | -642.7833 | -0.6304 | 16.4431 | 28.0 | 0.5873 |
| 0.0017 | 0.8016 | 375 | 0.0017 | -662.0203 | -0.6116 | 16.5244 | 28.0 | 0.5902 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.6.0+cu126
- Datasets 2.19.1
- Tokenizers 0.20.3