metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: >-
      fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
    results: []

fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05

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

Loss: 1.0942
Exact Match: 64.3979
F1: 69.8535

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Exact Match	F1
6.1478	0.49	36	2.4099	49.8691	49.8691
3.581	0.98	72	1.9550	49.8691	49.8691
2.195	1.48	108	1.8446	49.3455	49.8564
2.195	1.97	144	1.7512	49.4764	51.2613
2.0071	2.46	180	1.6324	49.6073	52.3994
1.8105	2.95	216	1.5278	52.7487	55.8533
1.6668	3.45	252	1.3938	56.6754	60.5142
1.6668	3.94	288	1.3243	56.9372	62.8755
1.4715	4.44	324	1.2475	60.6021	66.5376
1.3112	4.93	360	1.2257	59.4241	65.0059
1.3112	5.42	396	1.1793	60.9948	66.2895
1.2443	5.91	432	1.1485	63.4817	69.0854
1.1586	6.41	468	1.1178	64.1361	69.5844
1.0895	6.9	504	1.1404	63.0890	68.6016
1.0895	7.4	540	1.0862	65.7068	70.8093
1.054	7.89	576	1.0959	64.7906	70.2001
1.0231	8.38	612	1.1036	64.3979	69.7053
1.0231	8.87	648	1.0698	65.8377	71.1488
0.9985	9.37	684	1.0777	66.0995	71.3149
0.9736	9.86	720	1.0942	64.3979	69.8535

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu117
Datasets 2.2.0
Tokenizers 0.13.2