metadata
base_model: Sunshine279/gammaPO-llama-3-8b-instruct
tags:
- alignment-handbook
- generated_from_trainer
- arxiv:2506.03690
datasets:
- princeton-nlp/llama3-ultrafeedback-armorm
model-index:
- name: Sunshine279/gammaPO-llama-3-8b-instruct
results: []
llama-3-8b-it-gmsimpo-beta10-gm0.4-tau10-lr1e-6
This model is a fine-tuned version of Sunshine279/gammaPO-llama-3-8b-instruct on the princeton-nlp/llama3-ultrafeedback-armorm dataset. It achieves the following results on the evaluation set:
- Loss: 1.1389
- Rewards/chosen: -20.8453
- Rewards/rejected: -29.4063
- Rewards/accuracies: 0.8679
- Rewards/margins: 8.5610
- Logps/rejected: -2.9406
- Logps/chosen: -2.0845
- Logits/rejected: -1.7197
- Logits/chosen: -1.7101
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.1544 | 0.8550 | 400 | 1.1389 | -20.8453 | -29.4063 | 0.8679 | 8.5610 | -2.9406 | -2.0845 | -1.7197 | -1.7101 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1