Waldbrand100/tiny-bert-sst2-distilled

Source: 🤗🏴‍☠️ Rescued by: isilicontext-classificationapache-2.04M params180 MBsafetensors✓ 7 checksumsupdated 694d ago

tiny-bert-sst2-distilled

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4375
Accuracy: 0.8073

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: 0.00030231468122836585
train_batch_size: 128
eval_batch_size: 128
seed: 33
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4362	1.0	527	0.4507	0.7970
0.3092	2.0	1054	0.4375	0.8073

Framework versions

Transformers 4.47.1
Pytorch 2.5.1
Datasets 3.2.0
Tokenizers 0.21.0

Loading…

CommentsShare your thoughts and shape the future of sovereign AI.

@Waldbrand100 is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @Waldbrand100

Files and sources

SourceAvailable on 🤗

Checksums7 awaiting witness

TorrentMagnet listed

Swarm1 seeders reported

Source revision: d79c4a87e2ab…
Witnessed: Not yet
Swarm checked: 14 Nov 2026, 00:35 UTC
Weight files: 7
Model size: 180 MB
Downloads · last month: 32
Publisher: Unclaimed

Public checksum record coming on the next sync

Weights

Original

F32176 MB
17 files
run-0/checkpoint-1054/optimizer.pt 35 MBrun-0/checkpoint-527/optimizer.pt 35 MBrun-1/checkpoint-527/optimizer.pt 35 MBmodel.safetensors 18 MBrun-0/checkpoint-1054/model.safetensors 18 MBrun-0/checkpoint-527/model.safetensors 18 MBrun-1/checkpoint-527/model.safetensors 18 MBrun-0/checkpoint-1054/rng_state.pth 14.1 kBrun-0/checkpoint-527/rng_state.pth 14.1 kBrun-1/checkpoint-527/rng_state.pth 14.1 kBtraining_args.bin 5.4 kBrun-0/checkpoint-1054/training_args.bin 5.4 kBrun-0/checkpoint-527/training_args.bin 5.4 kBrun-1/checkpoint-527/training_args.bin 5.4 kBrun-0/checkpoint-1054/scheduler.pt 1.1 kBrun-0/checkpoint-527/scheduler.pt 1.1 kBrun-1/checkpoint-527/scheduler.pt 1.1 kB

Family

↑ Finetuned from google/bert_uncased_L-2_H-128_A-2