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: 0.5

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: 0.6933
• Accuracy: 0.5
• Tp: 0.5
• Tn: 0.0
• Fp: 0.5
• Fn: 0.0

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: 0.0001
• 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Tp	Tn	Fp	Fn
0.7406	1.05	20	0.6941	0.5	0.5	0.0	0.5	0.0
0.7008	2.11	40	0.6959	0.5	0.5	0.0	0.5	0.0
0.7067	3.16	60	0.6932	0.5	0.5	0.0	0.5	0.0
0.7029	4.21	80	0.6937	0.5	0.0	0.5	0.0	0.5
0.7103	5.26	100	0.6932	0.5	0.0	0.5	0.0	0.5
0.7085	6.32	120	0.7004	0.5	0.5	0.0	0.5	0.0
0.7061	7.37	140	0.6933	0.5	0.5	0.0	0.5	0.0
0.7013	8.42	160	0.6954	0.5	0.0	0.5	0.0	0.5
0.6952	9.47	180	0.6933	0.5	0.0	0.5	0.0	0.5
0.7084	10.53	200	0.7079	0.5	0.0	0.5	0.0	0.5
0.71	11.58	220	0.6999	0.5	0.5	0.0	0.5	0.0
0.7036	12.63	240	0.6932	0.5	0.5	0.0	0.5	0.0
0.7043	13.68	260	0.6942	0.5	0.5	0.0	0.5	0.0
0.7058	14.74	280	0.6947	0.5	0.5	0.0	0.5	0.0
0.6993	15.79	300	0.6951	0.5	0.5	0.0	0.5	0.0
0.7009	16.84	320	0.6936	0.5	0.0	0.5	0.0	0.5
0.7069	17.89	340	0.7002	0.5	0.0	0.5	0.0	0.5
0.7068	18.95	360	0.6970	0.5	0.5	0.0	0.5	0.0
0.7042	20.0	380	0.6935	0.5	0.5	0.0	0.5	0.0
0.6999	21.05	400	0.6957	0.5	0.5	0.0	0.5	0.0
0.6966	22.11	420	0.6936	0.5	0.5	0.0	0.5	0.0
0.6975	23.16	440	0.6934	0.5	0.5	0.0	0.5	0.0
0.7043	24.21	460	0.6934	0.5	0.0	0.5	0.0	0.5
0.7002	25.26	480	0.6932	0.5	0.0	0.5	0.0	0.5
0.7039	26.32	500	0.7004	0.5	0.5	0.0	0.5	0.0
0.6927	27.37	520	0.6932	0.5	0.5	0.0	0.5	0.0
0.7078	28.42	540	0.6941	0.5	0.0	0.5	0.0	0.5
0.6999	29.47	560	0.6969	0.5	0.0	0.5	0.0	0.5
0.7063	30.53	580	0.6936	0.5	0.0	0.5	0.0	0.5
0.7011	31.58	600	0.6934	0.5	0.0	0.5	0.0	0.5
0.7061	32.63	620	0.6958	0.5	0.0	0.5	0.0	0.5
0.6971	33.68	640	0.6932	0.5	0.5	0.0	0.5	0.0
0.7007	34.74	660	0.6932	0.5	0.5	0.0	0.5	0.0
0.7014	35.79	680	0.6954	0.5	0.0	0.5	0.0	0.5
0.6976	36.84	700	0.6951	0.5	0.5	0.0	0.5	0.0
0.6957	37.89	720	0.6936	0.5	0.0	0.5	0.0	0.5
0.7009	38.95	740	0.6950	0.5	0.0	0.5	0.0	0.5
0.6941	40.0	760	0.6933	0.5	0.5	0.0	0.5	0.0
0.6989	41.05	780	0.6948	0.5	0.0	0.5	0.0	0.5
0.6935	42.11	800	0.6974	0.5	0.5	0.0	0.5	0.0
0.6939	43.16	820	0.6956	0.5	0.0	0.5	0.0	0.5
0.6975	44.21	840	0.6955	0.5	0.5	0.0	0.5	0.0
0.669	45.26	860	0.7089	0.5132	0.1623	0.3510	0.1490	0.3377
0.6896	46.32	880	0.7088	0.4669	0.4106	0.0563	0.4437	0.0894
0.6942	47.37	900	0.6944	0.5	0.5	0.0	0.5	0.0
0.6942	48.42	920	0.6933	0.5	0.5	0.0	0.5	0.0
0.6921	49.47	940	0.6933	0.5	0.5	0.0	0.5	0.0

Framework versions

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