metadata

license: apache-2.0
base_model: line-corporation/line-distilbert-base-japanese
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: fc-binary-prompt-model
    results: []

fc-binary-prompt-model

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

Loss: 0.3462
Accuracy: 0.8652

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: 0.0001
train_batch_size: 64
eval_batch_size: 8
seed: 42
distributed_type: tpu
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	306	0.3968	0.8594
0.425	2.0	612	0.3885	0.8594
0.425	3.0	918	0.3809	0.8594
0.4028	4.0	1224	0.3771	0.8594
0.3962	5.0	1530	0.3717	0.8594
0.3962	6.0	1836	0.3704	0.8594
0.3919	7.0	2142	0.3708	0.8594
0.3919	8.0	2448	0.3648	0.8594
0.3897	9.0	2754	0.3759	0.8613
0.3836	10.0	3060	0.3570	0.8594
0.3836	11.0	3366	0.3643	0.8613
0.3864	12.0	3672	0.3559	0.8613
0.3864	13.0	3978	0.3557	0.8613
0.3823	14.0	4284	0.3516	0.8613
0.3808	15.0	4590	0.3580	0.8613
0.3808	16.0	4896	0.3529	0.8613
0.3759	17.0	5202	0.3498	0.8613
0.3793	18.0	5508	0.3485	0.8613
0.3793	19.0	5814	0.3495	0.8613
0.3757	20.0	6120	0.3442	0.8613
0.3757	21.0	6426	0.3481	0.8613
0.3741	22.0	6732	0.3475	0.8633
0.3775	23.0	7038	0.3478	0.8633
0.3775	24.0	7344	0.3486	0.8633
0.375	25.0	7650	0.3489	0.8652
0.375	26.0	7956	0.3485	0.8652
0.37	27.0	8262	0.3446	0.8613
0.3712	28.0	8568	0.3463	0.8652
0.3712	29.0	8874	0.3466	0.8652
0.3748	30.0	9180	0.3462	0.8652

Framework versions

Transformers 4.34.0
Pytorch 2.0.0+cu118
Datasets 2.14.5
Tokenizers 0.14.0