falcon_1b_stage2 / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
fb54fe9
|
raw
history blame
1.84 kB
metadata
license: apache-2.0
base_model: euclaise/falcon_1b_stage1
tags:
  - generated_from_trainer
model-index:
  - name: falcon_1b_stage2
    results: []

falcon_1b_stage2

This model is a fine-tuned version of euclaise/falcon_1b_stage1 on the None dataset.

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: 6e-06
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8.0
  • total_train_batch_size: 128.0
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 32.9
ARC (25-shot) 35.49
HellaSwag (10-shot) 65.56
MMLU (5-shot) 23.83
TruthfulQA (0-shot) 38.32
Winogrande (5-shot) 62.35
GSM8K (5-shot) 0.0
DROP (3-shot) 4.72