Downloads · 30 days
10
7% of all-time downloads
mistral-sft-7b-dpo-qlora
MichaelR207/mistral-sft-7b-dpo-qlora
mistral-sft-7b-dpo-qlora is a machine learning model from MichaelR207. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
134
Public
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors671 MB · 100%
At a glance
- Library
- peft
- License
- mit
- Model type
- mistral
- Access
- Public
- Created
- Mar 4, 2024
- Updated
- Mar 4, 2024
- SHA
- 6b46192a
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. -->
mistral-sft-7b-dpo-qlora
This model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.6936
- Rewards/chosen: 0.0005
- Rewards/rejected: 0.0001
- Rewards/accuracies: 0.6875
- Rewards/margins: 0.0003
- Logps/rejected: -122.9776
- Logps/chosen: -86.4464
- Logits/rejected: -3.0453
- Logits/chosen: -2.9824
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-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 221
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 5
Training results
Framework versions
- PEFT 0.7.1
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.14.6
- Tokenizers 0.15.2
- Library
- peft
- Type
- mistral
- License
- mit
- Created
- Mar 4, 2024
- Updated
- Mar 4, 2024