metadata

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

results_distilbert-base-uncased

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: 0.3782
Accuracy: 0.744

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: 1e-05
train_batch_size: 32
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: 600
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6859	0.12	30	0.6867	0.304
0.6759	0.24	60	0.6723	0.3535
0.6508	0.36	90	0.6433	0.43
0.6046	0.48	120	0.5999	0.4915
0.5845	0.6	150	0.5733	0.491
0.579	0.72	180	0.5633	0.6455
0.5599	0.84	210	0.5484	0.5705
0.526	0.96	240	0.5208	0.679
0.4968	1.08	270	0.4765	0.7115
0.4763	1.2	300	0.4524	0.7165
0.4565	1.32	330	0.4341	0.7205
0.4345	1.44	360	0.4254	0.7235
0.4338	1.56	390	0.4161	0.73
0.4292	1.68	420	0.4119	0.729
0.4129	1.8	450	0.4061	0.7345
0.4036	1.92	480	0.3966	0.739
0.4019	2.04	510	0.3984	0.726
0.3794	2.16	540	0.3961	0.74
0.3756	2.28	570	0.3981	0.728
0.4565	2.4	600	0.3903	0.73
0.376	2.52	630	0.3997	0.7285
0.4023	2.64	660	0.3850	0.7435
0.3511	2.76	690	0.3802	0.742
0.3601	2.88	720	0.3782	0.744
0.3771	3.0	750	0.3792	0.742

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1