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/tiny_bert_km_10_v1_mnli")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_10_v1_mnli")Quick Links
tiny_bert_km_10_v1_mnli
This model is a fine-tuned version of Hartunka/tiny_bert_km_10_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8382
- Accuracy: 0.6274
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 |
|---|---|---|---|---|
| 0.9971 | 1.0 | 1534 | 0.9425 | 0.5416 |
| 0.9096 | 2.0 | 3068 | 0.8861 | 0.5773 |
| 0.8541 | 3.0 | 4602 | 0.8557 | 0.6075 |
| 0.8053 | 4.0 | 6136 | 0.8488 | 0.6218 |
| 0.7589 | 5.0 | 7670 | 0.8369 | 0.6271 |
| 0.7141 | 6.0 | 9204 | 0.8613 | 0.6304 |
| 0.6695 | 7.0 | 10738 | 0.8625 | 0.6335 |
| 0.6257 | 8.0 | 12272 | 0.8963 | 0.6353 |
| 0.5833 | 9.0 | 13806 | 0.9534 | 0.6298 |
| 0.5404 | 10.0 | 15340 | 0.9587 | 0.6323 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Model tree for Hartunka/tiny_bert_km_10_v1_mnli
Base model
Hartunka/tiny_bert_km_10_v1Dataset used to train Hartunka/tiny_bert_km_10_v1_mnli
Evaluation results
- Accuracy on GLUE MNLIself-reported0.627
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_10_v1_mnli")