k4black's picture
update model card README.md
cf1a9e4
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - esnli
metrics:
  - f1
  - accuracy
model-index:
  - name: roberta-large-e-snli-classification-nli-base
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: esnli
          type: esnli
          config: plain_text
          split: validation
          args: plain_text
        metrics:
          - name: F1
            type: f1
            value: 0.9258678577111056
          - name: Accuracy
            type: accuracy
            value: 0.9260312944523471

roberta-large-e-snli-classification-nli-base

This model is a fine-tuned version of roberta-large on the esnli dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2221
  • F1: 0.9259
  • Accuracy: 0.9260

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: 1e-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
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss F1 Accuracy
0.9995 0.05 400 0.4236 0.8437 0.8465
0.4089 0.09 800 0.2961 0.8926 0.8933
0.3681 0.14 1200 0.2980 0.8914 0.8924
0.3467 0.19 1600 0.2872 0.8977 0.8990
0.324 0.23 2000 0.2506 0.9106 0.9110
0.3222 0.28 2400 0.2552 0.9132 0.9128
0.3138 0.33 2800 0.2379 0.9183 0.9183
0.3107 0.37 3200 0.2396 0.9152 0.9156
0.304 0.42 3600 0.2354 0.9174 0.9177
0.3027 0.47 4000 0.2360 0.9191 0.9191
0.2968 0.51 4400 0.2329 0.9182 0.9187
0.2888 0.56 4800 0.2462 0.9189 0.9196
0.2898 0.61 5200 0.2335 0.9206 0.9212
0.288 0.65 5600 0.2350 0.9220 0.9223
0.2746 0.7 6000 0.2208 0.9275 0.9278
0.2756 0.75 6400 0.2304 0.9209 0.9216
0.272 0.79 6800 0.2243 0.9237 0.9238
0.2809 0.84 7200 0.2176 0.9259 0.9261
0.2733 0.89 7600 0.2194 0.9271 0.9273
0.2723 0.93 8000 0.2221 0.9259 0.9260

Framework versions

  • Transformers 4.27.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.10.1
  • Tokenizers 0.13.2