metadata

library_name: transformers
license: apache-2.0
base_model: albert/albert-base-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: albert-base-v2-grammar-ner-generic
    results: []

albert-base-v2-grammar-ner-generic

This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0991
Accuracy: 0.9891
F1 Macro: 0.9176
F1 Micro: 0.9176
Precision Macro: 0.9647
Precision Micro: 0.9647
Recall Macro: 0.875
Recall Micro: 0.875

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: 24
eval_batch_size: 24
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Micro	Precision Macro	Precision Micro	Recall Macro	Recall Micro
0.244	1.0	93	0.1830	0.9305	0.2897	0.2897	0.3892	0.3892	0.2308	0.2308
0.1652	2.0	186	0.1476	0.9450	0.4236	0.4236	0.6644	0.6644	0.3109	0.3109
0.1119	3.0	279	0.1070	0.9656	0.6759	0.6759	0.7313	0.7313	0.6282	0.6282
0.0629	4.0	372	0.0884	0.9751	0.7764	0.7764	0.8453	0.8453	0.7179	0.7179
0.0408	5.0	465	0.0954	0.9748	0.7911	0.7911	0.7873	0.7873	0.7949	0.7949
0.028	6.0	558	0.0830	0.9799	0.8143	0.8143	0.9194	0.9194	0.7308	0.7308
0.0185	7.0	651	0.0756	0.9831	0.8700	0.8700	0.8714	0.8714	0.8686	0.8686
0.0125	8.0	744	0.0815	0.9841	0.8591	0.8591	0.9134	0.9134	0.8109	0.8109
0.0073	9.0	837	0.0809	0.9854	0.8773	0.8773	0.8963	0.8963	0.8590	0.8590
0.0046	10.0	930	0.0895	0.9870	0.8908	0.8908	0.9526	0.9526	0.8365	0.8365
0.0022	11.0	1023	0.0903	0.9867	0.8972	0.8972	0.9136	0.9136	0.8814	0.8814
0.0009	12.0	1116	0.0957	0.9889	0.9130	0.9130	0.9545	0.9545	0.875	0.875
0.0005	13.0	1209	0.0931	0.9891	0.9149	0.9149	0.9547	0.9547	0.8782	0.8782
0.0002	14.0	1302	0.0978	0.9891	0.9176	0.9176	0.9647	0.9647	0.875	0.875
0.0001	15.0	1395	0.0982	0.9891	0.9176	0.9176	0.9647	0.9647	0.875	0.875
0.0	16.0	1488	0.0986	0.9889	0.9161	0.9161	0.9613	0.9613	0.875	0.875
0.0	17.0	1581	0.0990	0.9891	0.9176	0.9176	0.9647	0.9647	0.875	0.875
0.0	18.0	1674	0.0991	0.9891	0.9176	0.9176	0.9647	0.9647	0.875	0.875

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.20.3