Downloads · 30 days
17
5% of all-time downloads
Mamba2InLlama_0_875
JunxiongWang/Mamba2InLlama_0_875
Mamba2InLlama_0_875 is a machine learning model from JunxiongWang. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
330
Public
Repo size
34 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin34 GB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Aug 22, 2024
- Updated
- Sep 2, 2024
- SHA
- 4ad3df70
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Please check here for details.
JunxiongWang/Mamba2InLlama_0_875
This model is a fine-tuned version of JunxiongWang/llama3_0_875_mamba2_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: 0.4761
- Rewards/chosen: -1.4040
- Rewards/rejected: -2.6012
- Rewards/accuracies: 0.7982
- Rewards/margins: 1.1973
- Logps/rejected: -584.9104
- Logps/chosen: -459.0677
- Logits/rejected: 0.3408
- Logits/chosen: 0.3851
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5009 | 0.4798 | 2000 | 0.4998 | -1.4973 | -2.6147 | 0.7804 | 1.1175 | -586.2582 | -468.3976 | 0.4682 | 0.5136 |
| 0.4895 | 0.9597 | 4000 | 0.4761 | -1.4040 | -2.6012 | 0.7982 | 1.1973 | -584.9104 | -459.0677 | 0.3408 | 0.3851 |
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}
}
- Type
- llama
- Created
- Aug 22, 2024
- Updated
- Sep 2, 2024