metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: tabert-500-naamapadam
    results: []

tabert-500-naamapadam

This model is a fine-tuned version of livinNector/tabert-500 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2821
Precision: 0.7818
Recall: 0.8089
F1: 0.7951
Accuracy: 0.9070

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: 5e-05
train_batch_size: 64
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4684	0.05	400	0.3956	0.6972	0.6926	0.6949	0.8720
0.3901	0.1	800	0.3706	0.7099	0.7338	0.7216	0.8811
0.3658	0.15	1200	0.3551	0.7349	0.7388	0.7369	0.8854
0.3535	0.21	1600	0.3445	0.7333	0.7458	0.7395	0.8875
0.3512	0.26	2000	0.3353	0.7547	0.7408	0.7477	0.8917
0.3377	0.31	2400	0.3302	0.7417	0.7636	0.7525	0.8916
0.3297	0.36	2800	0.3279	0.7681	0.7330	0.7501	0.8931
0.3331	0.41	3200	0.3252	0.7448	0.7833	0.7636	0.8961
0.3247	0.46	3600	0.3210	0.7479	0.7847	0.7659	0.8960
0.3175	0.51	4000	0.3155	0.7684	0.7597	0.7640	0.8975
0.3142	0.57	4400	0.3113	0.7510	0.7833	0.7668	0.8977
0.315	0.62	4800	0.3131	0.7574	0.7830	0.7700	0.8969
0.3078	0.67	5200	0.3155	0.7569	0.7821	0.7693	0.8980
0.3101	0.72	5600	0.3117	0.7708	0.7730	0.7719	0.8990
0.3078	0.77	6000	0.3070	0.7665	0.7824	0.7744	0.8992
0.304	0.82	6400	0.3055	0.7680	0.7875	0.7776	0.8992
0.2954	0.87	6800	0.3019	0.7675	0.7929	0.7800	0.9002
0.2955	0.93	7200	0.3107	0.7804	0.7755	0.7779	0.9000
0.2979	0.98	7600	0.2992	0.7721	0.7931	0.7825	0.9021
0.2816	1.03	8000	0.3022	0.7695	0.7971	0.7831	0.9029
0.2768	1.08	8400	0.3043	0.7538	0.8045	0.7783	0.9003
0.2775	1.13	8800	0.2990	0.7687	0.8003	0.7842	0.9024
0.2704	1.18	9200	0.2948	0.7724	0.7987	0.7853	0.9023
0.2734	1.23	9600	0.2932	0.7764	0.7993	0.7877	0.9041
0.2746	1.29	10000	0.2918	0.7841	0.7949	0.7894	0.9046
0.2678	1.34	10400	0.2909	0.7775	0.8039	0.7905	0.9046
0.272	1.39	10800	0.2909	0.7786	0.7952	0.7868	0.9034
0.2636	1.44	11200	0.2900	0.7815	0.7959	0.7886	0.9044
0.2663	1.49	11600	0.2863	0.7747	0.8086	0.7913	0.9047
0.2617	1.54	12000	0.2876	0.7759	0.8042	0.7898	0.9051
0.2634	1.59	12400	0.2896	0.7677	0.8123	0.7894	0.9038
0.2651	1.65	12800	0.2871	0.7799	0.8024	0.7910	0.9058
0.2676	1.7	13200	0.2870	0.7863	0.8008	0.7935	0.9061
0.273	1.75	13600	0.2836	0.7804	0.8108	0.7953	0.9064
0.2611	1.8	14000	0.2821	0.7821	0.8052	0.7935	0.9064
0.2683	1.85	14400	0.2815	0.7791	0.8108	0.7946	0.9064
0.2624	1.9	14800	0.2818	0.7819	0.8090	0.7952	0.9071
0.2628	1.95	15200	0.2821	0.7818	0.8089	0.7951	0.9070

Framework versions

Transformers 4.29.2
Pytorch 2.0.0
Datasets 2.12.0
Tokenizers 0.13.3