metadata
language:
- en
base_model: Hartunka/tiny_bert_rand_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_100_v1_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6985294117647058
- name: F1
type: f1
value: 0.8050713153724247
tiny_bert_rand_100_v1_mrpc
This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5959
- Accuracy: 0.6985
- F1: 0.8051
- Combined Score: 0.7518
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6273 | 1.0 | 15 | 0.6087 | 0.6887 | 0.8025 | 0.7456 |
| 0.5923 | 2.0 | 30 | 0.5959 | 0.6985 | 0.8051 | 0.7518 |
| 0.5507 | 3.0 | 45 | 0.6265 | 0.7059 | 0.8107 | 0.7583 |
| 0.5072 | 4.0 | 60 | 0.6902 | 0.6152 | 0.6879 | 0.6515 |
| 0.4237 | 5.0 | 75 | 0.7022 | 0.6667 | 0.7527 | 0.7097 |
| 0.3165 | 6.0 | 90 | 0.8693 | 0.6446 | 0.7290 | 0.6868 |
| 0.2385 | 7.0 | 105 | 0.9900 | 0.6446 | 0.7330 | 0.6888 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1