README.md

metadata

base_model: checkpoints/Mistral-7B-Instruct-EI-Iter2
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - synthetic_data_mistral-7b-instruct-expert-iteration-iter3_score
model-index:
  - name: Mistral-7B-Instruct-EI-Iter3
    results: []

Mistral-7B-Instruct-EI-Iter3

This model is a fine-tuned version of checkpoints/Mistral-7B-Instruct-EI-Iter2 on the synthetic_data_mistral-7b-instruct-expert-iteration-iter3_score dataset. It achieves the following results on the evaluation set:

• Loss: 0.4722

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: 8
• total_train_batch_size: 64
• 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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6652	1.0	106	0.4722

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1