metadata

license: mit
base_model: facebook/xlm-v-base
tags:
  - generated_from_trainer
datasets:
  - massive
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-TCR-XLMV-1_data-AmazonScience_massive_all_1_1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: massive
          type: massive
          config: all_1.1
          split: validation
          args: all_1.1
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8472984221877483
          - name: F1
            type: f1
            value: 0.8225956665149763

scenario-TCR-XLMV-1_data-AmazonScience_massive_all_1_1

This model is a fine-tuned version of facebook/xlm-v-base on the massive dataset. It achieves the following results on the evaluation set:

Loss: 0.7886
Accuracy: 0.8473
F1: 0.8226

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: 32
eval_batch_size: 32
seed: 47
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.587	0.27	5000	0.7148	0.8166	0.7696
0.456	0.53	10000	0.6624	0.8415	0.8006
0.3711	0.8	15000	0.6803	0.8394	0.8064
0.2846	1.07	20000	0.7409	0.8406	0.8119
0.2698	1.34	25000	0.7120	0.8428	0.8129
0.2589	1.6	30000	0.7179	0.8478	0.8300
0.246	1.87	35000	0.7383	0.8455	0.8119
0.2079	2.14	40000	0.7911	0.8503	0.8162
0.2157	2.41	45000	0.7775	0.8434	0.8251
0.2111	2.67	50000	0.7737	0.8455	0.8196
0.2014	2.94	55000	0.7886	0.8473	0.8226

Framework versions

Transformers 4.33.3
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.13.3