HachiML/Mistral-7B-v0.3-m1-lora

Model Card for Model ID

• HachiML/Mistral-7B-v0.3-sft-lora_sr_5epのAdapterをマージしたモデル
• This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on following datasets.
  • HachiML/oasst1_for_self-rewarding_IFT
  • HachiML/oasst1_for_self-rewarding_EFT_MSv0.3
• It achieves the following results on the evaluation set:
  • Loss: 0.4237

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: HachiML
• Model type: Mistral-7B
• Language(s) (NLP): Japanese
• License: Apache-2.0
• Finetuned from model: mistralai/Mistral-7B-v0.3
• Finetuned type: SFT
• Finetuned dataset:
  • HachiML/oasst1_for_self-rewarding_IFT
  • HachiML/oasst1_for_self-rewarding_EFT_MSv0.3

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5.5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.1951	1.0	262	0.4563
0.9304	2.0	524	0.4279
0.9129	3.0	786	0.4242
0.9088	4.0	1048	0.4237
0.9089	5.0	1310	0.4237

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1