Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Hartunka/bert_base_km_50_v1_mnli")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/bert_base_km_50_v1_mnli")Quick Links
bert_base_km_50_v1_mnli
This model is a fine-tuned version of Hartunka/bert_base_km_50_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.7719
- Accuracy: 0.6588
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: 256
- eval_batch_size: 256
- seed: 10
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9861 | 1.0 | 1534 | 0.9068 | 0.5751 |
| 0.8643 | 2.0 | 3068 | 0.8279 | 0.6256 |
| 0.7687 | 3.0 | 4602 | 0.7823 | 0.6574 |
| 0.6904 | 4.0 | 6136 | 0.7888 | 0.6566 |
| 0.6157 | 5.0 | 7670 | 0.8072 | 0.6703 |
| 0.5387 | 6.0 | 9204 | 0.8872 | 0.6685 |
| 0.4595 | 7.0 | 10738 | 0.9231 | 0.6663 |
| 0.3841 | 8.0 | 12272 | 1.0233 | 0.6580 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 5
Model tree for Hartunka/bert_base_km_50_v1_mnli
Base model
Hartunka/bert_base_km_50_v1Dataset used to train Hartunka/bert_base_km_50_v1_mnli
Evaluation results
- Accuracy on GLUE MNLIself-reported0.659
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/bert_base_km_50_v1_mnli")