metadata
language:
- en
base_model: Hartunka/tiny_bert_rand_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_rand_100_v1_mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.620626525630594
tiny_bert_rand_100_v1_mnli
This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.8518
- Accuracy: 0.6206
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9939 | 1.0 | 1534 | 0.9340 | 0.5477 |
| 0.9106 | 2.0 | 3068 | 0.8888 | 0.5792 |
| 0.8576 | 3.0 | 4602 | 0.8594 | 0.6055 |
| 0.8116 | 4.0 | 6136 | 0.8516 | 0.6134 |
| 0.7679 | 5.0 | 7670 | 0.8467 | 0.6204 |
| 0.7263 | 6.0 | 9204 | 0.8595 | 0.6275 |
| 0.6861 | 7.0 | 10738 | 0.8681 | 0.6259 |
| 0.6464 | 8.0 | 12272 | 0.9058 | 0.6231 |
| 0.6076 | 9.0 | 13806 | 0.9309 | 0.6247 |
| 0.5699 | 10.0 | 15340 | 0.9937 | 0.6231 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1