metadata
base_model: JunxiongWang/llama3_mamba_0_5_sft
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
- HuggingFaceH4/orca_dpo_pairs
- JunxiongWang/llama3-ultrafeedback-armorm
model-index:
- name: JunxiongWang/MambaInLlama_0_875
results: []
Please check here for details.
JunxiongWang/MambaInLlama_0_875
This model is a fine-tuned version of JunxiongWang/llama3_mamba_0_5_sft on the HuggingFaceH4/ultrafeedback_binarized, the HuggingFaceH4/orca_dpo_pairs and the JunxiongWang/llama3-ultrafeedback-armorm datasets. It achieves the following results on the evaluation set:
- Loss: 0.4393
- Rewards/chosen: -1.7352
- Rewards/rejected: -3.4828
- Rewards/accuracies: 0.8286
- Rewards/margins: 1.7476
- Logps/rejected: -623.4827
- Logps/chosen: -439.4573
- Logits/rejected: -0.6261
- Logits/chosen: -0.6084
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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4627 | 0.4798 | 2000 | 0.4641 | -1.4789 | -2.9625 | 0.8036 | 1.4836 | -571.4525 | -413.8262 | -0.7196 | -0.7049 |
| 0.4644 | 0.9597 | 4000 | 0.4393 | -1.7352 | -3.4828 | 0.8286 | 1.7476 | -623.4827 | -439.4573 | -0.6261 | -0.6084 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.1.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
@article{junxiongdaniele2024mambainllama,
title = {The Mamba in the Llama: Distilling and Accelerating Hybrid Models},
author = {Junxiong Wang and Daniele Paliotta and Avner May and Alexander M. Rush and Tri Dao},
journal = {arXiv preprint arXiv:2408.15237},
year = {2024}
}