Hugging Face's logo

haryoaw
/
scenario-TCR-XLMV-XCOPA-5_data-xcopa_all

Multiple Choice
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
scenario-TCR-XLMV-XCOPA-5_data-xcopa_all / README.md
haryoaw's picture
haryoaw
Initial Commit
5b04521 verified
preview code
|
raw history blame
4.57 kB
metadata
license: mit
base_model: facebook/xlm-v-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-TCR-XLMV-XCOPA-5_data-xcopa_all
    results: []

scenario-TCR-XLMV-XCOPA-5_data-xcopa_all

This model is a fine-tuned version of facebook/xlm-v-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6931
  • Accuracy: 0.5125
  • F1: 0.4891

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: 214
  • 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
No log 0.38 5 0.6925 0.5333 0.5246
No log 0.77 10 0.6931 0.4867 0.4680
No log 1.15 15 0.6932 0.475 0.4483
No log 1.54 20 0.6932 0.4658 0.4241
No log 1.92 25 0.6932 0.4975 0.4724
No log 2.31 30 0.6931 0.5175 0.4970
No log 2.69 35 0.6931 0.5142 0.4987
No log 3.08 40 0.6931 0.5167 0.5026
No log 3.46 45 0.6931 0.53 0.5146
No log 3.85 50 0.6931 0.5492 0.5292
No log 4.23 55 0.6931 0.5517 0.5394
No log 4.62 60 0.6931 0.5508 0.5357
No log 5.0 65 0.6931 0.5533 0.5387
No log 5.38 70 0.6930 0.5592 0.5428
No log 5.77 75 0.6930 0.5608 0.5453
No log 6.15 80 0.6931 0.54 0.5258
No log 6.54 85 0.6933 0.4958 0.4860
No log 6.92 90 0.6931 0.5308 0.4987
No log 7.31 95 0.6931 0.53 0.5130
No log 7.69 100 0.6931 0.5292 0.5074
No log 8.08 105 0.6931 0.5358 0.5101
No log 8.46 110 0.6931 0.5225 0.4943
No log 8.85 115 0.6925 0.5575 0.5354
No log 9.23 120 0.6931 0.5417 0.5250
No log 9.62 125 0.6931 0.5133 0.4804
No log 10.0 130 0.6931 0.5358 0.5004
No log 10.38 135 0.6931 0.5425 0.5163
No log 10.77 140 0.6931 0.5433 0.5142
No log 11.15 145 0.6931 0.5425 0.5103
No log 11.54 150 0.6931 0.5467 0.5099
No log 11.92 155 0.6931 0.5358 0.4986
No log 12.31 160 0.6931 0.5275 0.4841
No log 12.69 165 0.6931 0.5192 0.4825
No log 13.08 170 0.6931 0.5283 0.4910
No log 13.46 175 0.6930 0.5508 0.5131
No log 13.85 180 0.6930 0.5542 0.5303
No log 14.23 185 0.6932 0.4908 0.4664
No log 14.62 190 0.6931 0.5075 0.4802
No log 15.0 195 0.6932 0.5083 0.4806
No log 15.38 200 0.6932 0.4625 0.4377
No log 15.77 205 0.6932 0.48 0.4694
No log 16.15 210 0.6932 0.49 0.4742
No log 16.54 215 0.6931 0.5333 0.5130
No log 16.92 220 0.6931 0.5217 0.4884
No log 17.31 225 0.6931 0.5125 0.4891

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3