GREEN-Mistral-7b / README.md
justin13601's picture
Upload folder using huggingface_hub
8ebac4c verified
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - generated_from_trainer
model-index:
  - name: Mistral-7b
    results: []

Mistral-7b

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

  • Loss: 0.1919

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 2048
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 12.0

Training results

Training Loss Epoch Step Validation Loss
1.7591 0.64 25 4.9279
2.0299 1.28 50 0.8182
0.6558 1.92 75 0.5750
0.4785 2.56 100 0.3823
0.3837 3.2 125 0.2941
0.3073 3.84 150 0.2318
0.2119 4.48 175 0.1871
0.1632 5.12 200 0.1595
0.1297 5.76 225 0.1487
0.1035 6.39 250 0.1476
0.0856 7.03 275 0.1427
0.0574 7.67 300 0.1482
0.0448 8.31 325 0.1552
0.0318 8.95 350 0.1562
0.0196 9.59 375 0.1709
0.0146 10.23 400 0.1793
0.0084 10.87 425 0.1854
0.0058 11.51 450 0.1919

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2