README.md

metadata

license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - alignment-handbook
  - generated_from_trainer
datasets:
  - AmberYifan/safeRLHF-SFT
model-index:
  - name: mistral-safe-sft-full
    results: []

mistral-safe-sft-full

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the AmberYifan/safeRLHF-SFT dataset. It achieves the following results on the evaluation set:

• Loss: 1.7972

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.9697	2.0	370	1.2888
0.4114	3.0	555	1.4739
0.1361	4.0	740	1.7972

Framework versions

• Transformers 4.43.3
• Pytorch 2.2.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1