metadata

base_model: Fsoft-AIC/videberta-xsmall
tags:
  - generated_from_trainer
datasets:
  - vietnamese_students_feedback
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: videberta-sentiment-analysis
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: vietnamese_students_feedback
          type: vietnamese_students_feedback
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9496688741721855
          - name: Precision
            type: precision
            value: 0.9539227895392279
          - name: Recall
            type: recall
            value: 0.9515527950310559
          - name: F1
            type: f1
            value: 0.9527363184079602

videberta-sentiment-analysis

This model is a fine-tuned version of Fsoft-AIC/videberta-xsmall on the vietnamese_students_feedback dataset. It achieves the following results on the evaluation set:

Loss: 0.2903
Accuracy: 0.9497
Precision: 0.9539
Recall: 0.9516
F1: 0.9527

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: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.2029	2.91	500	0.2022	0.9358	0.9414	0.9379	0.9396
0.1435	5.81	1000	0.2109	0.9325	0.9200	0.9565	0.9379
0.1023	8.72	1500	0.2648	0.9344	0.9263	0.9528	0.9394
0.08	11.63	2000	0.2360	0.9437	0.9455	0.9491	0.9473
0.0628	14.53	2500	0.2758	0.9417	0.9377	0.9540	0.9458
0.0493	17.44	3000	0.3189	0.9351	0.9223	0.9590	0.9403
0.0397	20.35	3500	0.3662	0.9377	0.9257	0.9602	0.9427
0.0318	23.26	4000	0.2903	0.9497	0.9539	0.9516	0.9527
0.0244	26.16	4500	0.3962	0.9450	0.9381	0.9602	0.9490
0.0176	29.07	5000	0.3940	0.9464	0.9425	0.9578	0.9501
0.0165	31.98	5500	0.3990	0.9411	0.9486	0.9404	0.9445
0.0139	34.88	6000	0.4565	0.9424	0.9336	0.9602	0.9467
0.0123	37.79	6500	0.3779	0.9457	0.9491	0.9491	0.9491
0.0118	40.7	7000	0.4308	0.9444	0.9380	0.9590	0.9484
0.0086	43.6	7500	0.4732	0.9404	0.9344	0.9553	0.9447
0.0076	46.51	8000	0.4197	0.9457	0.9547	0.9429	0.9487
0.0067	49.42	8500	0.4952	0.9444	0.9391	0.9578	0.9483
0.0062	52.33	9000	0.4907	0.9437	0.9444	0.9503	0.9474

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3