metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - f1
base_model: distilbert-base-uncased
model-index:
  - name: distilbert-base-uncased_fold_6_binary
    results: []

distilbert-base-uncased_fold_6_binary

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

Loss: 1.6838
F1: 0.7881

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	290	0.4181	0.7732
0.4097	2.0	580	0.3967	0.7697
0.4097	3.0	870	0.5811	0.7797
0.2034	4.0	1160	0.8684	0.7320
0.2034	5.0	1450	0.9116	0.7718
0.0794	6.0	1740	1.0588	0.7690
0.0278	7.0	2030	1.2092	0.7738
0.0278	8.0	2320	1.2180	0.7685
0.0233	9.0	2610	1.3005	0.7676
0.0233	10.0	2900	1.4009	0.7634
0.0093	11.0	3190	1.4528	0.7805
0.0093	12.0	3480	1.4803	0.7859
0.0088	13.0	3770	1.4775	0.7750
0.0077	14.0	4060	1.6171	0.7699
0.0077	15.0	4350	1.6429	0.7636
0.0047	16.0	4640	1.5619	0.7819
0.0047	17.0	4930	1.5833	0.7724
0.0034	18.0	5220	1.6400	0.7853
0.0008	19.0	5510	1.6508	0.7792
0.0008	20.0	5800	1.6838	0.7881
0.0009	21.0	6090	1.6339	0.7829
0.0009	22.0	6380	1.6824	0.7806
0.0016	23.0	6670	1.6867	0.7876
0.0016	24.0	6960	1.7107	0.7877
0.0013	25.0	7250	1.6933	0.7812

Framework versions

Transformers 4.21.0
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1