metadata

license: mit
base_model: xlnet/xlnet-base-cased
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: xlnet-base-cased-airlines-news-multi-label
    results: []

xlnet-base-cased-airlines-news-multi-label

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

Loss: 0.2567
F1: 0.8989
Roc Auc: 0.6475

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: 7e-05
train_batch_size: 12
eval_batch_size: 12
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 150
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc
No log	1.0	170	0.2834	0.8827	0.5576
No log	2.0	340	0.2670	0.8918	0.6102
0.2923	3.0	510	0.2567	0.8989	0.6475
0.2923	4.0	680	0.2526	0.8910	0.6685
0.2923	5.0	850	0.2512	0.8825	0.6352
0.2571	6.0	1020	0.2514	0.8863	0.6708
0.2571	7.0	1190	0.2454	0.8872	0.6490
0.2571	8.0	1360	0.2495	0.8884	0.6660
0.2468	9.0	1530	0.2467	0.8881	0.6725
0.2468	10.0	1700	0.2554	0.8815	0.6514
0.2468	11.0	1870	0.2474	0.8883	0.6603
0.2363	12.0	2040	0.2478	0.8912	0.6943
0.2363	13.0	2210	0.2492	0.8964	0.6976
0.2363	14.0	2380	0.2530	0.8936	0.7121
0.2332	15.0	2550	0.2497	0.8893	0.6830
0.2332	16.0	2720	0.2483	0.8922	0.7008
0.2332	17.0	2890	0.2489	0.8905	0.6782
0.23	18.0	3060	0.2496	0.8877	0.6927
0.23	19.0	3230	0.2494	0.8855	0.6652
0.23	20.0	3400	0.2483	0.8929	0.6903
0.2246	21.0	3570	0.2503	0.8902	0.6838
0.2246	22.0	3740	0.2506	0.8854	0.6805
0.2246	23.0	3910	0.2515	0.8900	0.6887
0.2214	24.0	4080	0.2501	0.8894	0.6773
0.2214	25.0	4250	0.2528	0.8878	0.6870
0.2214	26.0	4420	0.2519	0.8918	0.6895
0.2203	27.0	4590	0.2558	0.8897	0.6830
0.2203	28.0	4760	0.2554	0.8919	0.6952
0.2203	29.0	4930	0.2537	0.8957	0.7025
0.2193	30.0	5100	0.2513	0.8951	0.7025
0.2193	31.0	5270	0.2565	0.8946	0.7130
0.2193	32.0	5440	0.2542	0.8935	0.6960
0.2178	33.0	5610	0.2545	0.8970	0.7090
0.2178	34.0	5780	0.2546	0.8960	0.7138
0.2178	35.0	5950	0.2550	0.8942	0.7073
0.2173	36.0	6120	0.2545	0.8942	0.7073
0.2173	37.0	6290	0.2537	0.8925	0.7008
0.2173	38.0	6460	0.2541	0.8942	0.7073
0.2164	39.0	6630	0.2537	0.8940	0.7016
0.2164	40.0	6800	0.2540	0.8942	0.7073

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1