metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - esnli
metrics:
  - f1
  - accuracy
model-index:
  - name: roberta-base-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: 0.9108298866502319
          - name: Accuracy
            type: accuracy
            value: 0.9109937004673847

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

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

Loss: 0.2611
F1: 0.9108
Accuracy: 0.9110

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
1.0317	0.05	400	0.5734	0.7771	0.7803
0.544	0.09	800	0.3994	0.8548	0.8555
0.4604	0.14	1200	0.3492	0.8681	0.8687
0.4235	0.19	1600	0.3323	0.8764	0.8777
0.3934	0.23	2000	0.3225	0.8831	0.8841
0.3863	0.28	2400	0.3086	0.8875	0.8872
0.3767	0.33	2800	0.2972	0.8892	0.8898
0.3726	0.37	3200	0.2910	0.8932	0.8936
0.3624	0.42	3600	0.2934	0.8934	0.8937
0.361	0.47	4000	0.2831	0.8989	0.8989
0.3553	0.51	4400	0.2905	0.8985	0.8993
0.3451	0.56	4800	0.2725	0.9019	0.9024
0.3475	0.61	5200	0.2712	0.9046	0.9051
0.3398	0.65	5600	0.2787	0.9024	0.9028
0.3322	0.7	6000	0.2697	0.9043	0.9046
0.3288	0.75	6400	0.2722	0.9006	0.9013
0.324	0.79	6800	0.2677	0.9066	0.9066
0.3335	0.84	7200	0.2629	0.9075	0.9077
0.3309	0.89	7600	0.2577	0.9058	0.9061
0.3236	0.93	8000	0.2561	0.9121	0.9121
0.3183	0.98	8400	0.2556	0.9084	0.9088
0.3022	1.03	8800	0.2668	0.9056	0.9064
0.2974	1.07	9200	0.2519	0.9087	0.9092
0.29	1.12	9600	0.2554	0.9103	0.9109
0.2855	1.16	10000	0.2611	0.9108	0.9110

Framework versions

Transformers 4.27.1
Pytorch 1.12.1+cu113
Datasets 2.10.1
Tokenizers 0.13.2