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:
  - HuggingFaceH4/deita-10k-v0-sft
model-index:
  - name: mistral-7b-wo-kqa_golden-iter-sft-step1
    results: []

mistral-7b-wo-kqa_golden-iter-sft-step1

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

• Loss: 1.4157

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.0983	0.97	16	1.2722
1.4581	2.0	33	1.2942
0.9338	2.91	48	1.4157

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.2