metadata
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
results: []
qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6598
- Rewards/chosen: -3.3421
- Rewards/rejected: -3.4735
- Rewards/accuracies: 0.5282
- Rewards/margins: 0.1314
- Logps/rejected: -1.3894
- Logps/chosen: -1.3368
- Logits/rejected: -5.2590
- Logits/chosen: -5.3573
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: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.6693 | 0.8549 | 400 | 1.6598 | -3.3421 | -3.4735 | 0.5282 | 0.1314 | -1.3894 | -1.3368 | -5.2590 | -5.3573 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1