metadata

license: mit
base_model: neuraly/bert-base-italian-cased-sentiment
tags:
  - generated_from_trainer
datasets:
  - tweet_sentiment_multilingual
metrics:
  - accuracy
model-index:
  - name: sentiment_ita
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: tweet_sentiment_multilingual
          type: tweet_sentiment_multilingual
          config: italian
          split: validation
          args: italian
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6944444444444444

sentiment_ita

This model is a fine-tuned version of neuraly/bert-base-italian-cased-sentiment on the tweet_sentiment_multilingual dataset. It achieves the following results on the evaluation set:

Loss: 2.3610
Accuracy: 0.6944

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 800
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	171	0.7979	0.6574
0.8861	2.0	342	0.7423	0.6944
0.8861	3.0	513	0.8450	0.6914
0.3208	4.0	684	1.2621	0.6698
0.3208	5.0	855	1.3658	0.6790
0.1361	6.0	1026	1.9379	0.6883
0.1361	7.0	1197	2.2134	0.6667
0.0567	8.0	1368	2.4013	0.6728
0.0567	9.0	1539	2.3630	0.6914
0.0113	10.0	1710	2.3610	0.6944

Framework versions

Transformers 4.35.2
Pytorch 2.0.1
Datasets 2.15.0
Tokenizers 0.15.0