metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: mnli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MNLI
type: glue
args: mnli
metrics:
- name: Accuracy
type: accuracy
value: 0.8230268510984541
- task:
type: natural-language-inference
name: Natural Language Inference
dataset:
name: glue
type: glue
config: mnli
split: validation_matched
metrics:
- name: Accuracy
type: accuracy
value: 0.8189505858380031
verified: true
- name: Precision Macro
type: precision
value: 0.8179669104455792
verified: true
- name: Precision Micro
type: precision
value: 0.8189505858380031
verified: true
- name: Precision Weighted
type: precision
value: 0.8185679295201952
verified: true
- name: Recall Macro
type: recall
value: 0.8175820569584179
verified: true
- name: Recall Micro
type: recall
value: 0.8189505858380031
verified: true
- name: Recall Weighted
type: recall
value: 0.8189505858380031
verified: true
- name: F1 Macro
type: f1
value: 0.8176177699916428
verified: true
- name: F1 Micro
type: f1
value: 0.8189505858380031
verified: true
- name: F1 Weighted
type: f1
value: 0.8186059524762352
verified: true
- name: loss
type: loss
value: 0.46445730328559875
verified: true
mnli
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.4595
- Accuracy: 0.8230
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: 3e-05
- train_batch_size: 48
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.3
Training results
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0
- Datasets 2.2.2
- Tokenizers 0.12.1