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_rand_20_v1_mnli")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_rand_20_v1_mnli")Quick Links
tiny_bert_rand_20_v1_mnli
This model is a fine-tuned version of Hartunka/tiny_bert_rand_20_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8709
- Accuracy: 0.5989
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 |
|---|---|---|---|---|
| 0.9987 | 1.0 | 1534 | 0.9482 | 0.5350 |
| 0.9153 | 2.0 | 3068 | 0.8893 | 0.5831 |
| 0.8571 | 3.0 | 4602 | 0.8752 | 0.5966 |
| 0.8033 | 4.0 | 6136 | 0.8718 | 0.6011 |
| 0.7482 | 5.0 | 7670 | 0.8747 | 0.6078 |
| 0.6947 | 6.0 | 9204 | 0.9125 | 0.6129 |
| 0.6416 | 7.0 | 10738 | 0.9405 | 0.6155 |
| 0.5894 | 8.0 | 12272 | 1.0253 | 0.6039 |
| 0.5403 | 9.0 | 13806 | 1.1121 | 0.6019 |
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_rand_20_v1_mnli
Base model
Hartunka/tiny_bert_rand_20_v1Dataset used to train Hartunka/tiny_bert_rand_20_v1_mnli
Evaluation results
- Accuracy on GLUE MNLIself-reported0.599
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_rand_20_v1_mnli")