GoEmotions fine-tune
The model card identifies the model as bert-base-uncased fine-tuned on the go_emotions dataset, with a dataset:go_emotions hub tag.
Open Source Model Profile · IsaacZhy
bert-base-goemotions
bert-base-goemotions is a BERT text-classification fine-tune from IsaacZhy. Its card documents fine-tuning of bert-base-uncased on go_emotions.
- Publisher
- IsaacZhy
- Task
- text-classification
- Model type
- bert
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
bert-base-goemotions is published by IsaacZhy as a BERT text-classification model. The captured configuration identifies BertForSequenceClassification with model type bert, and hub tags carry text-classification, dataset:go_emotions, and generated_from_trainer markers. The model card describes it as bert-base-uncased fine-tuned on go_emotions.
Recorded capabilities
Publisher-reported classification scores
According to the model card, the evaluation set yields loss 0.1539, F1 0.5727, ROC AUC 0.7796, and accuracy 0.4375.
Documented 10-epoch training setup
The model card lists learning rate 5e-05, batch size 16, seed 42, Adam with linear scheduling, 10 epochs, and Transformers 4.26.0 with PyTorch 1.13.1 and Datasets 2.9.0.
Use cases in the source record
- Emotion-classification experiments on short text using the documented go_emotions fine-tune and text-classification pipeline.
- Benchmark-aware classifier comparisons that can reuse the publisher's reported loss, F1, ROC AUC, and accuracy figures as a baseline.
Limitations and unknowns
- Intended uses, limitations, and training and evaluation data are marked as more information needed in the model card.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- No parameter, context-window, VRAM, quantization, or pricing figures were extracted.
Source and provenance
Source: IsaacZhy/bert-base-goemotions
Captured: Unknown. Processed: 2026-09-07T19:34:31.766700+00:00.
bert-base-goemotions This model is a fine-tuned version of bert-base-uncased on the go_emotions dataset. It achieves the following results on the evaluation set: Loss: 0.1539 F1: 0.5727 Roc Auc: 0.7796 Accuracy: 0.4375 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: 5e-05 train_batch_size: 16 eval_batch_size: 16 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear num_epochs: 10 Trai…
F001F002F003F004F005F006F008F009F010F011F012