metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: IndicBERTv2-MLM-Sam-TLM-NER
    results: []

IndicBERTv2-MLM-Sam-TLM-NER

This model is a fine-tuned version of ai4bharat/IndicBERTv2-MLM-Sam-TLM on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4521
Precision: 0.7629
Recall: 0.7792
F1: 0.7710
Accuracy: 0.9038

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: 128
eval_batch_size: 256
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3268	0.49	1000	0.3440	0.7207	0.7602	0.7399	0.8887
0.2763	0.99	2000	0.3083	0.7568	0.7732	0.7649	0.8983
0.2604	1.48	3000	0.3312	0.7309	0.7494	0.7401	0.8909
0.2501	1.98	4000	0.3017	0.7415	0.7956	0.7676	0.9014
0.2269	2.47	5000	0.2930	0.7528	0.7970	0.7743	0.9050
0.223	2.96	6000	0.2963	0.7590	0.7963	0.7772	0.9053
0.2011	3.46	7000	0.2939	0.7627	0.7946	0.7783	0.9079
0.1999	3.95	8000	0.3036	0.7676	0.7903	0.7788	0.9069
0.1815	4.44	9000	0.3125	0.7618	0.7915	0.7764	0.9056
0.1777	4.94	10000	0.3083	0.7748	0.7957	0.7851	0.9098
0.1622	5.43	11000	0.3251	0.7721	0.7909	0.7814	0.9089
0.1598	5.93	12000	0.3197	0.7767	0.7947	0.7856	0.9092
0.145	6.42	13000	0.3366	0.7718	0.7986	0.7850	0.9101
0.1436	6.91	14000	0.3247	0.7776	0.7977	0.7875	0.9112
0.1306	7.41	15000	0.3502	0.7779	0.7958	0.7867	0.9107
0.1311	7.9	16000	0.3585	0.7857	0.7909	0.7883	0.9105
0.12	8.4	17000	0.3717	0.7768	0.7911	0.7839	0.9099
0.1202	8.89	18000	0.3667	0.7796	0.7882	0.7839	0.9100
0.1141	9.38	19000	0.3860	0.7857	0.7900	0.7879	0.9100
0.1113	9.88	20000	0.3824	0.7758	0.7970	0.7862	0.9094
0.1056	10.37	21000	0.4041	0.7740	0.7952	0.7845	0.9084
0.1073	10.86	22000	0.4062	0.7735	0.7929	0.7831	0.9094
0.1063	11.36	23000	0.4197	0.7720	0.7866	0.7793	0.9071
0.1026	11.85	24000	0.4179	0.7625	0.7767	0.7695	0.9040
0.1042	12.35	25000	0.4392	0.7639	0.7748	0.7693	0.9037
0.101	12.84	26000	0.4373	0.7533	0.7795	0.7662	0.9029
0.1003	13.33	27000	0.4554	0.7535	0.7774	0.7653	0.9021
0.0993	13.83	28000	0.4530	0.7555	0.7773	0.7663	0.9019
0.0978	14.32	29000	0.4467	0.7637	0.7843	0.7738	0.9050
0.0946	14.81	30000	0.4521	0.7629	0.7792	0.7710	0.9038

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu117
Datasets 2.11.0
Tokenizers 0.13.3