metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: distil_bert_own_txt_clf_model
    results: []

distil_bert_own_txt_clf_model

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

Loss: 1.2314
Accuracy: 0.8
F1: 0.7950
Precision: 0.8053
Recall: 0.8084

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: 16
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.3619	3.33	50	1.1190	0.5083	0.3510	0.3025	0.4690
1.0373	6.67	100	0.6955	0.75	0.7245	0.7800	0.7244
0.4461	10.0	150	0.8629	0.6833	0.6799	0.7370	0.6928
0.0585	13.33	200	1.3333	0.7333	0.7132	0.7888	0.7391
0.002	16.67	250	1.2095	0.775	0.7688	0.8003	0.7797
0.0053	20.0	300	1.0637	0.7833	0.7728	0.7803	0.7773
0.0006	23.33	350	1.0393	0.7833	0.7731	0.7866	0.7804
0.0004	26.67	400	1.0850	0.7917	0.7825	0.8004	0.7913
0.0004	30.0	450	1.0655	0.7833	0.7731	0.7866	0.7804
0.0003	33.33	500	1.0775	0.7833	0.7731	0.7866	0.7804
0.0003	36.67	550	1.0626	0.7833	0.7731	0.7866	0.7804
0.0003	40.0	600	1.0474	0.775	0.7636	0.7736	0.7695
0.0003	43.33	650	1.0526	0.775	0.7636	0.7736	0.7695
0.0003	46.67	700	1.0609	0.775	0.7636	0.7736	0.7695
0.0003	50.0	750	1.0607	0.775	0.7636	0.7736	0.7695

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2