metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mnoukhov/pythia410m-sft-tldr
model-index:
- name: pythia410m-dpo2-tldr
results: []
pythia410m-dpo2-tldr
This model is a fine-tuned version of mnoukhov/pythia410m-sft-tldr on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6932
- Rewards/chosen: -3.4853
- Rewards/rejected: -3.6484
- Rewards/accuracies: 0.5844
- Rewards/margins: 0.1631
- Logps/rejected: -139.9715
- Logps/chosen: -139.9715
- Logps/ref Rejected: -63.5119
- Logps/ref Chosen: -70.2656
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logps/ref Rejected | Logps/ref Chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 0.2016 | 63 | 0.6557 | -1.8039 | -1.9472 | 0.6162 | 0.1434 | -106.3432 | -106.3432 | -63.5119 | -70.2656 |
| 0.4864 | 0.4032 | 126 | 0.6728 | -2.6758 | -2.8365 | 0.5972 | 0.1608 | -123.7810 | -123.7810 | -63.5119 | -70.2656 |
| 0.4864 | 0.6048 | 189 | 0.6833 | -3.3025 | -3.4756 | 0.5913 | 0.1731 | -136.3158 | -136.3158 | -63.5119 | -70.2656 |
| 0.3802 | 0.8064 | 252 | 0.6932 | -3.4853 | -3.6484 | 0.5844 | 0.1631 | -139.9715 | -139.9715 | -63.5119 | -70.2656 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1