⌘K

Models Leaderboard Activity Rescue Submit ZK Inference

Models Leaderboard Activity Rescue Submit ZK Inference

ResourcesArticles How it works 𝕏 @ThePirateFace

Language中文

Theme

Mission Worth rescuing Donate ProvenanceAgents Terms Listing policy Privacy

BramVanroy/bert-base-dutch-cased-hebban-reviews · Pirate Face

BramVanroy/bert-base-dutch-cased-hebban-reviews

Source: 🤗text-classificationmit109M params437 MBsafetensors✓ 6 checksumsupdated 1,152d ago

bert-base-dutch-cased-hebban-reviews

Dataset

dataset_name: BramVanroy/hebban-reviews
dataset_config: filtered_sentiment
dataset_revision: 2.0.0
labelcolumn: review_sentiment
textcolumn: review_text_without_quotes

Training

optim: adamw_hf
learning_rate: 5e-05
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
gradient_accumulation_steps: 1
max_steps: 5001
save_steps: 500
metric_for_best_model: qwk

Best checkedpoint based on validation

best_metric: 0.732569302631819
best_model_checkpoint: trained/hebban-reviews/bert-base-dutch-cased/checkpoint-3000

Test results of best checkpoint

accuracy: 0.8042406311637081
f1: 0.8125977499178383
precision: 0.8283602308368182
qwk: 0.7301452890386257
recall: 0.8042406311637081

Confusion matrix

Normalized confusion matrix

Environment

cuda_capabilities: 8.0; 8.0
cuda_device_count: 2
cuda_devices: NVIDIA A100-SXM4-80GB; NVIDIA A100-SXM4-80GB
finetuner_commit: 48bb3434fa8bbfc9b2d0061ca6c8feb87f78a7ef
platform: Linux-4.18.0-305.49.1.el8_4.x86_64-x86_64-with-glibc2.28
python_version: 3.9.5
toch_version: 1.10.0
transformers_version: 4.21.0

CommentsShare your thoughts and shape the future of sovereign AI.

@BramVanroy is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @BramVanroy

Files and sources

✓SourceAvailable on Hugging Face

2Checksums6 awaiting witness

3TorrentNot listed

4SwarmNot checked

Source revision: 04e818b74115…
Witnessed: Not yet
Weight files: 6
Model size: 437 MB
Downloads · last month: 21
Publisher: Unclaimed

Public checksum record coming on the next sync

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

or

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo BramVanroy/bert-base-dutch-cased-hebban-reviews ./model-folder