metadata
license: llama3
base_model: Magpie-Align/Llama-3-8B-Magpie-Pro-MT-SFT-v0.1
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: Llama-3-8B-Magpie-Pro-MT-UltraDPO2
results: []
Llama-3-8B-Magpie-Pro-MT-UltraDPO2
This model is a fine-tuned version of Magpie-Align/Llama-3-8B-Magpie-Pro-MT-SFT-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6088
- Rewards/chosen: -1.6321
- Rewards/rejected: -1.9785
- Rewards/accuracies: 0.6829
- Rewards/margins: 0.3464
- Logps/rejected: -459.1051
- Logps/chosen: -418.7560
- Logits/rejected: -0.6440
- Logits/chosen: -0.6435
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: 1e-06
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.628 | 0.2138 | 100 | 0.6641 | -0.8806 | -1.0146 | 0.6240 | 0.1340 | -362.7133 | -343.6060 | -0.7539 | -0.7528 |
| 0.6935 | 0.4275 | 200 | 0.6352 | -1.3660 | -1.6311 | 0.6545 | 0.2651 | -424.3628 | -392.1437 | -0.6649 | -0.6629 |
| 0.6376 | 0.6413 | 300 | 0.6178 | -1.3533 | -1.6413 | 0.6748 | 0.2880 | -425.3859 | -390.8818 | -0.6753 | -0.6758 |
| 0.5888 | 0.8550 | 400 | 0.6088 | -1.6321 | -1.9785 | 0.6829 | 0.3464 | -459.1051 | -418.7560 | -0.6440 | -0.6435 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1