Downloads · 30 days
5
13% of all-time downloads
yahoo-bert-32shot-stratified
otausendschoen/yahoo-bert-32shot-stratified
yahoo-bert-32shot-stratified is a text classification model from otausendschoen. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
38
Public
Parameters
109M
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 29, 2025
- Updated
- Jun 7, 2025
- SHA
- 2dbfa87d
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
yahoo-bert-32shot-stratified
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3218
- Accuracy: 0.1304
- Precision: 0.1344
- Recall: 0.1288
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: 2e-05
- train_batch_size: 100
- eval_batch_size: 100
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 200
- optimizer: Use OptimizerNames.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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|---|
| 1.1876 | 1.0 | 1 | 0.0946 | 2.3661 | 0.0650 | 0.1013 |
| 1.158 | 2.0 | 2 | 0.0989 | 2.3480 | 0.1079 | 0.1057 |
| 1.1027 | 3.0 | 3 | 0.105 | 2.3341 | 0.1324 | 0.1117 |
| 1.088 | 4.0 | 4 | 0.1063 | 2.3218 | 0.1204 | 0.1113 |
| 1.0536 | 5.0 | 5 | 0.1142 | 2.3119 | 0.1092 | 0.1161 |
| 1.0247 | 6.0 | 6 | 0.1195 | 2.3089 | 0.1095 | 0.1192 |
| 1.0023 | 7.0 | 7 | 0.1249 | 2.3080 | 0.1099 | 0.1234 |
| 1.0004 | 8.0 | 8 | 0.1276 | 2.3081 | 0.1141 | 0.1251 |
| 0.9842 | 9.0 | 9 | 0.1305 | 2.3084 | 0.1165 | 0.1270 |
| 0.955 | 10.0 | 10 | 0.1329 | 2.3099 | 0.1168 | 0.1293 |
| 0.9745 | 11.0 | 11 | 0.1343 | 2.3109 | 0.1176 | 0.1305 |
| 0.9449 | 12.0 | 12 | 0.1359 | 2.3124 | 0.1186 | 0.1321 |
| 0.948 | 13.0 | 13 | 0.1362 | 2.3142 | 0.1248 | 0.1329 |
| 0.9659 | 14.0 | 14 | 2.3168 | 0.1355 | 0.1294 | 0.1326 |
| 0.9338 | 15.0 | 15 | 2.3197 | 0.1332 | 0.1325 | 0.1309 |
| 0.917 | 16.0 | 16 | 2.3218 | 0.1304 | 0.1344 | 0.1288 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 29, 2025
- Updated
- Jun 7, 2025