README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - crows_pairs
metrics:
  - accuracy
model-index:
  - name: xlnet-base-cased_crows_pairs_finetuned
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: crows_pairs
          type: crows_pairs
          config: crows_pairs
          split: test
          args: crows_pairs
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5066225165562914

xlnet-base-cased_crows_pairs_finetuned

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

• Loss: 0.6932
• Accuracy: 0.5066

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: 0.0005
• 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
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9006	0.53	10	0.7493	0.4934
0.7565	1.05	20	0.7202	0.4934
0.7303	1.58	30	0.6968	0.4934
0.7495	2.11	40	0.7210	0.5066
0.8008	2.63	50	0.6944	0.5066
0.7251	3.16	60	0.6982	0.5066
0.7193	3.68	70	0.7032	0.5066
0.7118	4.21	80	0.6975	0.5066
0.7419	4.74	90	0.7311	0.5066
0.7175	5.26	100	0.6946	0.5066
0.7293	5.79	110	0.7008	0.4934
0.7208	6.32	120	0.6940	0.4934
0.7101	6.84	130	0.6975	0.5066
0.7138	7.37	140	0.7065	0.4934
0.7112	7.89	150	0.6931	0.5066
0.7093	8.42	160	0.6931	0.5066
0.6996	8.95	170	0.6931	0.5066
0.6948	9.47	180	0.7050	0.4934
0.7118	10.0	190	0.6935	0.4934
0.7015	10.53	200	0.6993	0.5066
0.6985	11.05	210	0.6941	0.4934
0.6983	11.58	220	0.7118	0.4934
0.7031	12.11	230	0.7110	0.5066
0.6987	12.63	240	0.7643	0.4934
0.7483	13.16	250	0.7019	0.5066
0.7065	13.68	260	0.7018	0.4934
0.7008	14.21	270	0.6931	0.5066
0.7074	14.74	280	0.6932	0.4934
0.7097	15.26	290	0.6931	0.5066
0.7284	15.79	300	0.6956	0.4934
0.7045	16.32	310	0.6948	0.5066
0.7041	16.84	320	0.7176	0.4934
0.7118	17.37	330	0.6941	0.5066
0.7044	17.89	340	0.6931	0.5066
0.7034	18.42	350	0.6938	0.4934
0.683	18.95	360	0.6984	0.4934
0.7024	19.47	370	0.7009	0.4934
0.6988	20.0	380	0.6999	0.5066
0.6977	20.53	390	0.6974	0.4934
0.709	21.05	400	0.6932	0.5066
0.6991	21.58	410	0.6940	0.4934
0.7058	22.11	420	0.6931	0.5066
0.7101	22.63	430	0.6934	0.4934
0.7086	23.16	440	0.6956	0.4934
0.6973	23.68	450	0.6970	0.5066
0.7059	24.21	460	0.6931	0.5066
0.7021	24.74	470	0.6988	0.4934
0.6996	25.26	480	0.7006	0.4934
0.6963	25.79	490	0.6931	0.5066
0.6962	26.32	500	0.6932	0.5066
0.691	26.84	510	0.6944	0.4934
0.7003	27.37	520	0.6933	0.4934
0.6944	27.89	530	0.6934	0.4934
0.6988	28.42	540	0.6931	0.5066
0.7009	28.95	550	0.6931	0.5066
0.699	29.47	560	0.6933	0.5066
0.696	30.0	570	0.6932	0.5066

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1
• Datasets 2.10.1
• Tokenizers 0.13.2