End of training

6b0fe9d 11 months ago

6.3 kB

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

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# distilbert-base-uncased-xsum-factuality

	This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.6850
	- Accuracy: 0.6332
	- F1: 0.6212
	- Precision: 0.6526
	- Recall: 0.6332

	## 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-06
	- train_batch_size: 2
	- eval_batch_size: 2
	- seed: 42
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_ratio: 0.1
	- num_epochs: 7

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| Precision \| Recall \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\|
	\| 0.7275 \| 0.13 \| 20 \| 0.6961 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.672 \| 0.27 \| 40 \| 0.6959 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6743 \| 0.4 \| 60 \| 0.6958 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7083 \| 0.53 \| 80 \| 0.6954 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7069 \| 0.67 \| 100 \| 0.6950 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7094 \| 0.8 \| 120 \| 0.6944 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6825 \| 0.93 \| 140 \| 0.6939 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6965 \| 1.07 \| 160 \| 0.6934 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6848 \| 1.2 \| 180 \| 0.6924 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6991 \| 1.33 \| 200 \| 0.6916 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6803 \| 1.47 \| 220 \| 0.6916 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6991 \| 1.6 \| 240 \| 0.6918 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.718 \| 1.73 \| 260 \| 0.6910 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6908 \| 1.87 \| 280 \| 0.6905 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7071 \| 2.0 \| 300 \| 0.6903 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6866 \| 2.13 \| 320 \| 0.6902 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7129 \| 2.27 \| 340 \| 0.6897 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6852 \| 2.4 \| 360 \| 0.6895 \| 0.4985 \| 0.3327 \| 0.2496 \| 0.4985 \|
	\| 0.686 \| 2.53 \| 380 \| 0.6888 \| 0.4985 \| 0.3479 \| 0.4804 \| 0.4985 \|
	\| 0.7026 \| 2.67 \| 400 \| 0.6888 \| 0.5030 \| 0.3501 \| 0.5508 \| 0.5030 \|
	\| 0.709 \| 2.8 \| 420 \| 0.6882 \| 0.5015 \| 0.3494 \| 0.5231 \| 0.5015 \|
	\| 0.7102 \| 2.93 \| 440 \| 0.6877 \| 0.5150 \| 0.4151 \| 0.5472 \| 0.5150 \|
	\| 0.7141 \| 3.07 \| 460 \| 0.6877 \| 0.5135 \| 0.4142 \| 0.5418 \| 0.5135 \|
	\| 0.6761 \| 3.2 \| 480 \| 0.6874 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6923 \| 3.33 \| 500 \| 0.6872 \| 0.5165 \| 0.4355 \| 0.5386 \| 0.5165 \|
	\| 0.6735 \| 3.47 \| 520 \| 0.6873 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6907 \| 3.6 \| 540 \| 0.6871 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.7049 \| 3.73 \| 560 \| 0.6872 \| 0.5090 \| 0.4114 \| 0.5267 \| 0.5090 \|
	\| 0.6839 \| 3.87 \| 580 \| 0.6868 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6914 \| 4.0 \| 600 \| 0.6867 \| 0.5374 \| 0.4734 \| 0.5729 \| 0.5374 \|
	\| 0.6785 \| 4.13 \| 620 \| 0.6867 \| 0.5210 \| 0.4385 \| 0.5508 \| 0.5210 \|
	\| 0.6806 \| 4.27 \| 640 \| 0.6864 \| 0.5329 \| 0.4701 \| 0.5626 \| 0.5329 \|
	\| 0.6832 \| 4.4 \| 660 \| 0.6863 \| 0.5734 \| 0.5362 \| 0.6079 \| 0.5734 \|
	\| 0.676 \| 4.53 \| 680 \| 0.6863 \| 0.5479 \| 0.4940 \| 0.5835 \| 0.5479 \|
	\| 0.6957 \| 4.67 \| 700 \| 0.6861 \| 0.5644 \| 0.5219 \| 0.5998 \| 0.5644 \|
	\| 0.6786 \| 4.8 \| 720 \| 0.6860 \| 0.5838 \| 0.5497 \| 0.6204 \| 0.5838 \|
	\| 0.6845 \| 4.93 \| 740 \| 0.6860 \| 0.5689 \| 0.5255 \| 0.6086 \| 0.5689 \|
	\| 0.6917 \| 5.07 \| 760 \| 0.6858 \| 0.6108 \| 0.5895 \| 0.6397 \| 0.6108 \|
	\| 0.6941 \| 5.2 \| 780 \| 0.6856 \| 0.6213 \| 0.6031 \| 0.6485 \| 0.6213 \|
	\| 0.6904 \| 5.33 \| 800 \| 0.6855 \| 0.6332 \| 0.6176 \| 0.6593 \| 0.6332 \|
	\| 0.6722 \| 5.47 \| 820 \| 0.6854 \| 0.6332 \| 0.6176 \| 0.6593 \| 0.6332 \|
	\| 0.6947 \| 5.6 \| 840 \| 0.6853 \| 0.6362 \| 0.6239 \| 0.6568 \| 0.6362 \|
	\| 0.706 \| 5.73 \| 860 \| 0.6852 \| 0.6347 \| 0.6225 \| 0.6547 \| 0.6347 \|
	\| 0.6733 \| 5.87 \| 880 \| 0.6852 \| 0.6392 \| 0.6266 \| 0.6611 \| 0.6392 \|
	\| 0.6925 \| 6.0 \| 900 \| 0.6851 \| 0.6437 \| 0.6306 \| 0.6676 \| 0.6437 \|
	\| 0.6782 \| 6.13 \| 920 \| 0.6851 \| 0.6377 \| 0.6252 \| 0.6589 \| 0.6377 \|
	\| 0.7056 \| 6.27 \| 940 \| 0.6851 \| 0.6377 \| 0.6252 \| 0.6589 \| 0.6377 \|
	\| 0.6972 \| 6.4 \| 960 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.7065 \| 6.53 \| 980 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.6754 \| 6.67 \| 1000 \| 0.6850 \| 0.6317 \| 0.6199 \| 0.6505 \| 0.6317 \|
	\| 0.6751 \| 6.8 \| 1020 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.6904 \| 6.93 \| 1040 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|


	### Framework versions

	- Transformers 4.35.0
	- Pytorch 2.0.1
	- Datasets 2.14.6
	- Tokenizers 0.14.1

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

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# distilbert-base-uncased-xsum-factuality

	This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.6850
	- Accuracy: 0.6332
	- F1: 0.6212
	- Precision: 0.6526
	- Recall: 0.6332

	## 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-06
	- train_batch_size: 2
	- eval_batch_size: 2
	- seed: 42
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_ratio: 0.1
	- num_epochs: 7

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| Precision \| Recall \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\|:---------:\|:------:\|
	\| 0.7275 \| 0.13 \| 20 \| 0.6961 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.672 \| 0.27 \| 40 \| 0.6959 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6743 \| 0.4 \| 60 \| 0.6958 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7083 \| 0.53 \| 80 \| 0.6954 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7069 \| 0.67 \| 100 \| 0.6950 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7094 \| 0.8 \| 120 \| 0.6944 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6825 \| 0.93 \| 140 \| 0.6939 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6965 \| 1.07 \| 160 \| 0.6934 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6848 \| 1.2 \| 180 \| 0.6924 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6991 \| 1.33 \| 200 \| 0.6916 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6803 \| 1.47 \| 220 \| 0.6916 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6991 \| 1.6 \| 240 \| 0.6918 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.718 \| 1.73 \| 260 \| 0.6910 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6908 \| 1.87 \| 280 \| 0.6905 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7071 \| 2.0 \| 300 \| 0.6903 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6866 \| 2.13 \| 320 \| 0.6902 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.7129 \| 2.27 \| 340 \| 0.6897 \| 0.5 \| 0.3333 \| 0.25 \| 0.5 \|
	\| 0.6852 \| 2.4 \| 360 \| 0.6895 \| 0.4985 \| 0.3327 \| 0.2496 \| 0.4985 \|
	\| 0.686 \| 2.53 \| 380 \| 0.6888 \| 0.4985 \| 0.3479 \| 0.4804 \| 0.4985 \|
	\| 0.7026 \| 2.67 \| 400 \| 0.6888 \| 0.5030 \| 0.3501 \| 0.5508 \| 0.5030 \|
	\| 0.709 \| 2.8 \| 420 \| 0.6882 \| 0.5015 \| 0.3494 \| 0.5231 \| 0.5015 \|
	\| 0.7102 \| 2.93 \| 440 \| 0.6877 \| 0.5150 \| 0.4151 \| 0.5472 \| 0.5150 \|
	\| 0.7141 \| 3.07 \| 460 \| 0.6877 \| 0.5135 \| 0.4142 \| 0.5418 \| 0.5135 \|
	\| 0.6761 \| 3.2 \| 480 \| 0.6874 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6923 \| 3.33 \| 500 \| 0.6872 \| 0.5165 \| 0.4355 \| 0.5386 \| 0.5165 \|
	\| 0.6735 \| 3.47 \| 520 \| 0.6873 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6907 \| 3.6 \| 540 \| 0.6871 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.7049 \| 3.73 \| 560 \| 0.6872 \| 0.5090 \| 0.4114 \| 0.5267 \| 0.5090 \|
	\| 0.6839 \| 3.87 \| 580 \| 0.6868 \| 0.5195 \| 0.4375 \| 0.5467 \| 0.5195 \|
	\| 0.6914 \| 4.0 \| 600 \| 0.6867 \| 0.5374 \| 0.4734 \| 0.5729 \| 0.5374 \|
	\| 0.6785 \| 4.13 \| 620 \| 0.6867 \| 0.5210 \| 0.4385 \| 0.5508 \| 0.5210 \|
	\| 0.6806 \| 4.27 \| 640 \| 0.6864 \| 0.5329 \| 0.4701 \| 0.5626 \| 0.5329 \|
	\| 0.6832 \| 4.4 \| 660 \| 0.6863 \| 0.5734 \| 0.5362 \| 0.6079 \| 0.5734 \|
	\| 0.676 \| 4.53 \| 680 \| 0.6863 \| 0.5479 \| 0.4940 \| 0.5835 \| 0.5479 \|
	\| 0.6957 \| 4.67 \| 700 \| 0.6861 \| 0.5644 \| 0.5219 \| 0.5998 \| 0.5644 \|
	\| 0.6786 \| 4.8 \| 720 \| 0.6860 \| 0.5838 \| 0.5497 \| 0.6204 \| 0.5838 \|
	\| 0.6845 \| 4.93 \| 740 \| 0.6860 \| 0.5689 \| 0.5255 \| 0.6086 \| 0.5689 \|
	\| 0.6917 \| 5.07 \| 760 \| 0.6858 \| 0.6108 \| 0.5895 \| 0.6397 \| 0.6108 \|
	\| 0.6941 \| 5.2 \| 780 \| 0.6856 \| 0.6213 \| 0.6031 \| 0.6485 \| 0.6213 \|
	\| 0.6904 \| 5.33 \| 800 \| 0.6855 \| 0.6332 \| 0.6176 \| 0.6593 \| 0.6332 \|
	\| 0.6722 \| 5.47 \| 820 \| 0.6854 \| 0.6332 \| 0.6176 \| 0.6593 \| 0.6332 \|
	\| 0.6947 \| 5.6 \| 840 \| 0.6853 \| 0.6362 \| 0.6239 \| 0.6568 \| 0.6362 \|
	\| 0.706 \| 5.73 \| 860 \| 0.6852 \| 0.6347 \| 0.6225 \| 0.6547 \| 0.6347 \|
	\| 0.6733 \| 5.87 \| 880 \| 0.6852 \| 0.6392 \| 0.6266 \| 0.6611 \| 0.6392 \|
	\| 0.6925 \| 6.0 \| 900 \| 0.6851 \| 0.6437 \| 0.6306 \| 0.6676 \| 0.6437 \|
	\| 0.6782 \| 6.13 \| 920 \| 0.6851 \| 0.6377 \| 0.6252 \| 0.6589 \| 0.6377 \|
	\| 0.7056 \| 6.27 \| 940 \| 0.6851 \| 0.6377 \| 0.6252 \| 0.6589 \| 0.6377 \|
	\| 0.6972 \| 6.4 \| 960 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.7065 \| 6.53 \| 980 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.6754 \| 6.67 \| 1000 \| 0.6850 \| 0.6317 \| 0.6199 \| 0.6505 \| 0.6317 \|
	\| 0.6751 \| 6.8 \| 1020 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|
	\| 0.6904 \| 6.93 \| 1040 \| 0.6850 \| 0.6332 \| 0.6212 \| 0.6526 \| 0.6332 \|


	### Framework versions

	- Transformers 4.35.0
	- Pytorch 2.0.1
	- Datasets 2.14.6
	- Tokenizers 0.14.1