metadata

license: apache-2.0
base_model: casual/nlp_til2
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: nlp_til2
    results: []

nlp_til2

This model is a fine-tuned version of casual/nlp_til2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0128
Precision: 0.9739
Recall: 0.9708
F1: 0.9723
Accuracy: 0.9960

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	219	0.0548	0.8595	0.8533	0.8564	0.9777
No log	2.0	438	0.0538	0.8705	0.8560	0.8632	0.9788
0.0699	3.0	657	0.0531	0.8735	0.8626	0.8680	0.9785
0.0699	4.0	876	0.0459	0.8872	0.8833	0.8853	0.9816
0.0635	5.0	1095	0.0437	0.8876	0.8934	0.8905	0.9829
0.0635	6.0	1314	0.0358	0.9093	0.9001	0.9047	0.9859
0.0567	7.0	1533	0.0333	0.9170	0.9111	0.9140	0.9874
0.0567	8.0	1752	0.0303	0.9364	0.9229	0.9296	0.9889
0.0567	9.0	1971	0.0263	0.9432	0.9285	0.9358	0.9905
0.0498	10.0	2190	0.0258	0.9320	0.9419	0.9369	0.9908
0.0498	11.0	2409	0.0237	0.9431	0.9445	0.9438	0.9916
0.0437	12.0	2628	0.0187	0.9646	0.9534	0.9590	0.9936
0.0437	13.0	2847	0.0179	0.9636	0.9609	0.9623	0.9945
0.0425	14.0	3066	0.0159	0.9671	0.9642	0.9657	0.9949
0.0425	15.0	3285	0.0146	0.9654	0.9648	0.9651	0.9952
0.0464	16.0	3504	0.0137	0.9691	0.9687	0.9689	0.9956
0.0464	17.0	3723	0.0135	0.9713	0.9695	0.9704	0.9957
0.0464	18.0	3942	0.0128	0.9739	0.9708	0.9723	0.9960

Framework versions

Transformers 4.40.2
Pytorch 2.0.1+cu117
Datasets 2.19.1
Tokenizers 0.19.1