Upload tokenizer

20c6de1 verified about 1 month ago

6.4 kB

	---
	base_model: FacebookAI/xlm-roberta-base
	library_name: transformers
	license: mit
	metrics:
	- precision
	- recall
	- f1
	- accuracy
	tags:
	- generated_from_trainer
	model-index:
	- name: scenario-non-kd-pre-ner-full-xlmr_data-univner_half44
	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. -->

	# scenario-non-kd-pre-ner-full-xlmr_data-univner_half44

	This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.1667
	- Precision: 0.8
	- Recall: 0.8085
	- F1: 0.8042
	- Accuracy: 0.9794

	## 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: 3e-05
	- train_batch_size: 32
	- eval_batch_size: 32
	- seed: 44
	- 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 \| Precision \| Recall \| F1 \| Accuracy \|
	\|:-------------:\|:-------:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.1407 \| 0.5828 \| 500 \| 0.0805 \| 0.7146 \| 0.7383 \| 0.7262 \| 0.9736 \|
	\| 0.0685 \| 1.1655 \| 1000 \| 0.0771 \| 0.7453 \| 0.7904 \| 0.7672 \| 0.9766 \|
	\| 0.0504 \| 1.7483 \| 1500 \| 0.0763 \| 0.7569 \| 0.7948 \| 0.7754 \| 0.9778 \|
	\| 0.0384 \| 2.3310 \| 2000 \| 0.0867 \| 0.7371 \| 0.7931 \| 0.7641 \| 0.9760 \|
	\| 0.0306 \| 2.9138 \| 2500 \| 0.0880 \| 0.7501 \| 0.8074 \| 0.7777 \| 0.9768 \|
	\| 0.0223 \| 3.4965 \| 3000 \| 0.0928 \| 0.7585 \| 0.8097 \| 0.7833 \| 0.9775 \|
	\| 0.0202 \| 4.0793 \| 3500 \| 0.0958 \| 0.7641 \| 0.7971 \| 0.7803 \| 0.9777 \|
	\| 0.0151 \| 4.6620 \| 4000 \| 0.0985 \| 0.7690 \| 0.8044 \| 0.7863 \| 0.9778 \|
	\| 0.0134 \| 5.2448 \| 4500 \| 0.1051 \| 0.7857 \| 0.7963 \| 0.7910 \| 0.9787 \|
	\| 0.0112 \| 5.8275 \| 5000 \| 0.1080 \| 0.7677 \| 0.8016 \| 0.7843 \| 0.9786 \|
	\| 0.0096 \| 6.4103 \| 5500 \| 0.1158 \| 0.7698 \| 0.8083 \| 0.7886 \| 0.9781 \|
	\| 0.0092 \| 6.9930 \| 6000 \| 0.1130 \| 0.7857 \| 0.8009 \| 0.7932 \| 0.9783 \|
	\| 0.0074 \| 7.5758 \| 6500 \| 0.1161 \| 0.7749 \| 0.8068 \| 0.7906 \| 0.9785 \|
	\| 0.0067 \| 8.1585 \| 7000 \| 0.1194 \| 0.7887 \| 0.7922 \| 0.7905 \| 0.9783 \|
	\| 0.0058 \| 8.7413 \| 7500 \| 0.1179 \| 0.7796 \| 0.8129 \| 0.7959 \| 0.9786 \|
	\| 0.0053 \| 9.3240 \| 8000 \| 0.1266 \| 0.7824 \| 0.8088 \| 0.7954 \| 0.9782 \|
	\| 0.0049 \| 9.9068 \| 8500 \| 0.1273 \| 0.7858 \| 0.7960 \| 0.7909 \| 0.9786 \|
	\| 0.0043 \| 10.4895 \| 9000 \| 0.1301 \| 0.7965 \| 0.7977 \| 0.7971 \| 0.9789 \|
	\| 0.0041 \| 11.0723 \| 9500 \| 0.1289 \| 0.7992 \| 0.7941 \| 0.7966 \| 0.9784 \|
	\| 0.0035 \| 11.6550 \| 10000 \| 0.1344 \| 0.7904 \| 0.8088 \| 0.7995 \| 0.9786 \|
	\| 0.0033 \| 12.2378 \| 10500 \| 0.1391 \| 0.7889 \| 0.8032 \| 0.7960 \| 0.9786 \|
	\| 0.0032 \| 12.8205 \| 11000 \| 0.1431 \| 0.7642 \| 0.8096 \| 0.7862 \| 0.9777 \|
	\| 0.0029 \| 13.4033 \| 11500 \| 0.1359 \| 0.8006 \| 0.7969 \| 0.7987 \| 0.9787 \|
	\| 0.0028 \| 13.9860 \| 12000 \| 0.1393 \| 0.7874 \| 0.8137 \| 0.8003 \| 0.9790 \|
	\| 0.0023 \| 14.5688 \| 12500 \| 0.1426 \| 0.7907 \| 0.8012 \| 0.7959 \| 0.9787 \|
	\| 0.0022 \| 15.1515 \| 13000 \| 0.1441 \| 0.7945 \| 0.8096 \| 0.8020 \| 0.9791 \|
	\| 0.002 \| 15.7343 \| 13500 \| 0.1498 \| 0.7860 \| 0.8041 \| 0.7950 \| 0.9782 \|
	\| 0.0023 \| 16.3170 \| 14000 \| 0.1442 \| 0.7844 \| 0.8090 \| 0.7965 \| 0.9787 \|
	\| 0.0016 \| 16.8998 \| 14500 \| 0.1534 \| 0.7943 \| 0.8080 \| 0.8011 \| 0.9789 \|
	\| 0.0017 \| 17.4825 \| 15000 \| 0.1483 \| 0.7915 \| 0.8019 \| 0.7967 \| 0.9789 \|
	\| 0.0017 \| 18.0653 \| 15500 \| 0.1521 \| 0.8066 \| 0.7932 \| 0.7999 \| 0.9791 \|
	\| 0.0014 \| 18.6480 \| 16000 \| 0.1517 \| 0.7984 \| 0.8022 \| 0.8003 \| 0.9792 \|
	\| 0.0014 \| 19.2308 \| 16500 \| 0.1549 \| 0.7820 \| 0.8136 \| 0.7975 \| 0.9789 \|
	\| 0.0011 \| 19.8135 \| 17000 \| 0.1546 \| 0.7980 \| 0.8035 \| 0.8007 \| 0.9792 \|
	\| 0.0012 \| 20.3963 \| 17500 \| 0.1601 \| 0.7842 \| 0.8062 \| 0.7950 \| 0.9785 \|
	\| 0.0011 \| 20.9790 \| 18000 \| 0.1596 \| 0.7830 \| 0.8012 \| 0.7920 \| 0.9785 \|
	\| 0.0009 \| 21.5618 \| 18500 \| 0.1616 \| 0.7911 \| 0.8116 \| 0.8012 \| 0.9788 \|
	\| 0.0012 \| 22.1445 \| 19000 \| 0.1617 \| 0.7834 \| 0.8087 \| 0.7958 \| 0.9782 \|
	\| 0.0008 \| 22.7273 \| 19500 \| 0.1621 \| 0.7917 \| 0.8104 \| 0.8009 \| 0.9792 \|
	\| 0.0009 \| 23.3100 \| 20000 \| 0.1637 \| 0.7927 \| 0.8010 \| 0.7968 \| 0.9786 \|
	\| 0.0007 \| 23.8928 \| 20500 \| 0.1637 \| 0.7720 \| 0.8126 \| 0.7918 \| 0.9784 \|
	\| 0.0006 \| 24.4755 \| 21000 \| 0.1628 \| 0.8003 \| 0.7995 \| 0.7999 \| 0.9791 \|
	\| 0.0007 \| 25.0583 \| 21500 \| 0.1635 \| 0.7904 \| 0.8094 \| 0.7998 \| 0.9789 \|
	\| 0.0005 \| 25.6410 \| 22000 \| 0.1651 \| 0.7942 \| 0.8121 \| 0.8031 \| 0.9793 \|
	\| 0.0005 \| 26.2238 \| 22500 \| 0.1652 \| 0.7958 \| 0.8114 \| 0.8035 \| 0.9792 \|
	\| 0.0005 \| 26.8065 \| 23000 \| 0.1653 \| 0.7936 \| 0.8087 \| 0.8011 \| 0.9792 \|
	\| 0.0005 \| 27.3893 \| 23500 \| 0.1661 \| 0.8005 \| 0.8097 \| 0.8050 \| 0.9794 \|
	\| 0.0004 \| 27.9720 \| 24000 \| 0.1661 \| 0.7953 \| 0.8100 \| 0.8026 \| 0.9792 \|
	\| 0.0004 \| 28.5548 \| 24500 \| 0.1668 \| 0.7940 \| 0.8108 \| 0.8023 \| 0.9793 \|
	\| 0.0004 \| 29.1375 \| 25000 \| 0.1666 \| 0.7944 \| 0.8081 \| 0.8012 \| 0.9791 \|
	\| 0.0003 \| 29.7203 \| 25500 \| 0.1667 \| 0.8 \| 0.8085 \| 0.8042 \| 0.9794 \|


	### Framework versions

	- Transformers 4.44.2
	- Pytorch 2.1.1+cu121
	- Datasets 2.14.5
	- Tokenizers 0.19.1

	---
	base_model: FacebookAI/xlm-roberta-base
	library_name: transformers
	license: mit
	metrics:
	- precision
	- recall
	- f1
	- accuracy
	tags:
	- generated_from_trainer
	model-index:
	- name: scenario-non-kd-pre-ner-full-xlmr_data-univner_half44
	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. -->

	# scenario-non-kd-pre-ner-full-xlmr_data-univner_half44

	This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.1667
	- Precision: 0.8
	- Recall: 0.8085
	- F1: 0.8042
	- Accuracy: 0.9794

	## 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: 3e-05
	- train_batch_size: 32
	- eval_batch_size: 32
	- seed: 44
	- 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 \| Precision \| Recall \| F1 \| Accuracy \|
	\|:-------------:\|:-------:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.1407 \| 0.5828 \| 500 \| 0.0805 \| 0.7146 \| 0.7383 \| 0.7262 \| 0.9736 \|
	\| 0.0685 \| 1.1655 \| 1000 \| 0.0771 \| 0.7453 \| 0.7904 \| 0.7672 \| 0.9766 \|
	\| 0.0504 \| 1.7483 \| 1500 \| 0.0763 \| 0.7569 \| 0.7948 \| 0.7754 \| 0.9778 \|
	\| 0.0384 \| 2.3310 \| 2000 \| 0.0867 \| 0.7371 \| 0.7931 \| 0.7641 \| 0.9760 \|
	\| 0.0306 \| 2.9138 \| 2500 \| 0.0880 \| 0.7501 \| 0.8074 \| 0.7777 \| 0.9768 \|
	\| 0.0223 \| 3.4965 \| 3000 \| 0.0928 \| 0.7585 \| 0.8097 \| 0.7833 \| 0.9775 \|
	\| 0.0202 \| 4.0793 \| 3500 \| 0.0958 \| 0.7641 \| 0.7971 \| 0.7803 \| 0.9777 \|
	\| 0.0151 \| 4.6620 \| 4000 \| 0.0985 \| 0.7690 \| 0.8044 \| 0.7863 \| 0.9778 \|
	\| 0.0134 \| 5.2448 \| 4500 \| 0.1051 \| 0.7857 \| 0.7963 \| 0.7910 \| 0.9787 \|
	\| 0.0112 \| 5.8275 \| 5000 \| 0.1080 \| 0.7677 \| 0.8016 \| 0.7843 \| 0.9786 \|
	\| 0.0096 \| 6.4103 \| 5500 \| 0.1158 \| 0.7698 \| 0.8083 \| 0.7886 \| 0.9781 \|
	\| 0.0092 \| 6.9930 \| 6000 \| 0.1130 \| 0.7857 \| 0.8009 \| 0.7932 \| 0.9783 \|
	\| 0.0074 \| 7.5758 \| 6500 \| 0.1161 \| 0.7749 \| 0.8068 \| 0.7906 \| 0.9785 \|
	\| 0.0067 \| 8.1585 \| 7000 \| 0.1194 \| 0.7887 \| 0.7922 \| 0.7905 \| 0.9783 \|
	\| 0.0058 \| 8.7413 \| 7500 \| 0.1179 \| 0.7796 \| 0.8129 \| 0.7959 \| 0.9786 \|
	\| 0.0053 \| 9.3240 \| 8000 \| 0.1266 \| 0.7824 \| 0.8088 \| 0.7954 \| 0.9782 \|
	\| 0.0049 \| 9.9068 \| 8500 \| 0.1273 \| 0.7858 \| 0.7960 \| 0.7909 \| 0.9786 \|
	\| 0.0043 \| 10.4895 \| 9000 \| 0.1301 \| 0.7965 \| 0.7977 \| 0.7971 \| 0.9789 \|
	\| 0.0041 \| 11.0723 \| 9500 \| 0.1289 \| 0.7992 \| 0.7941 \| 0.7966 \| 0.9784 \|
	\| 0.0035 \| 11.6550 \| 10000 \| 0.1344 \| 0.7904 \| 0.8088 \| 0.7995 \| 0.9786 \|
	\| 0.0033 \| 12.2378 \| 10500 \| 0.1391 \| 0.7889 \| 0.8032 \| 0.7960 \| 0.9786 \|
	\| 0.0032 \| 12.8205 \| 11000 \| 0.1431 \| 0.7642 \| 0.8096 \| 0.7862 \| 0.9777 \|
	\| 0.0029 \| 13.4033 \| 11500 \| 0.1359 \| 0.8006 \| 0.7969 \| 0.7987 \| 0.9787 \|
	\| 0.0028 \| 13.9860 \| 12000 \| 0.1393 \| 0.7874 \| 0.8137 \| 0.8003 \| 0.9790 \|
	\| 0.0023 \| 14.5688 \| 12500 \| 0.1426 \| 0.7907 \| 0.8012 \| 0.7959 \| 0.9787 \|
	\| 0.0022 \| 15.1515 \| 13000 \| 0.1441 \| 0.7945 \| 0.8096 \| 0.8020 \| 0.9791 \|
	\| 0.002 \| 15.7343 \| 13500 \| 0.1498 \| 0.7860 \| 0.8041 \| 0.7950 \| 0.9782 \|
	\| 0.0023 \| 16.3170 \| 14000 \| 0.1442 \| 0.7844 \| 0.8090 \| 0.7965 \| 0.9787 \|
	\| 0.0016 \| 16.8998 \| 14500 \| 0.1534 \| 0.7943 \| 0.8080 \| 0.8011 \| 0.9789 \|
	\| 0.0017 \| 17.4825 \| 15000 \| 0.1483 \| 0.7915 \| 0.8019 \| 0.7967 \| 0.9789 \|
	\| 0.0017 \| 18.0653 \| 15500 \| 0.1521 \| 0.8066 \| 0.7932 \| 0.7999 \| 0.9791 \|
	\| 0.0014 \| 18.6480 \| 16000 \| 0.1517 \| 0.7984 \| 0.8022 \| 0.8003 \| 0.9792 \|
	\| 0.0014 \| 19.2308 \| 16500 \| 0.1549 \| 0.7820 \| 0.8136 \| 0.7975 \| 0.9789 \|
	\| 0.0011 \| 19.8135 \| 17000 \| 0.1546 \| 0.7980 \| 0.8035 \| 0.8007 \| 0.9792 \|
	\| 0.0012 \| 20.3963 \| 17500 \| 0.1601 \| 0.7842 \| 0.8062 \| 0.7950 \| 0.9785 \|
	\| 0.0011 \| 20.9790 \| 18000 \| 0.1596 \| 0.7830 \| 0.8012 \| 0.7920 \| 0.9785 \|
	\| 0.0009 \| 21.5618 \| 18500 \| 0.1616 \| 0.7911 \| 0.8116 \| 0.8012 \| 0.9788 \|
	\| 0.0012 \| 22.1445 \| 19000 \| 0.1617 \| 0.7834 \| 0.8087 \| 0.7958 \| 0.9782 \|
	\| 0.0008 \| 22.7273 \| 19500 \| 0.1621 \| 0.7917 \| 0.8104 \| 0.8009 \| 0.9792 \|
	\| 0.0009 \| 23.3100 \| 20000 \| 0.1637 \| 0.7927 \| 0.8010 \| 0.7968 \| 0.9786 \|
	\| 0.0007 \| 23.8928 \| 20500 \| 0.1637 \| 0.7720 \| 0.8126 \| 0.7918 \| 0.9784 \|
	\| 0.0006 \| 24.4755 \| 21000 \| 0.1628 \| 0.8003 \| 0.7995 \| 0.7999 \| 0.9791 \|
	\| 0.0007 \| 25.0583 \| 21500 \| 0.1635 \| 0.7904 \| 0.8094 \| 0.7998 \| 0.9789 \|
	\| 0.0005 \| 25.6410 \| 22000 \| 0.1651 \| 0.7942 \| 0.8121 \| 0.8031 \| 0.9793 \|
	\| 0.0005 \| 26.2238 \| 22500 \| 0.1652 \| 0.7958 \| 0.8114 \| 0.8035 \| 0.9792 \|
	\| 0.0005 \| 26.8065 \| 23000 \| 0.1653 \| 0.7936 \| 0.8087 \| 0.8011 \| 0.9792 \|
	\| 0.0005 \| 27.3893 \| 23500 \| 0.1661 \| 0.8005 \| 0.8097 \| 0.8050 \| 0.9794 \|
	\| 0.0004 \| 27.9720 \| 24000 \| 0.1661 \| 0.7953 \| 0.8100 \| 0.8026 \| 0.9792 \|
	\| 0.0004 \| 28.5548 \| 24500 \| 0.1668 \| 0.7940 \| 0.8108 \| 0.8023 \| 0.9793 \|
	\| 0.0004 \| 29.1375 \| 25000 \| 0.1666 \| 0.7944 \| 0.8081 \| 0.8012 \| 0.9791 \|
	\| 0.0003 \| 29.7203 \| 25500 \| 0.1667 \| 0.8 \| 0.8085 \| 0.8042 \| 0.9794 \|


	### Framework versions

	- Transformers 4.44.2
	- Pytorch 2.1.1+cu121
	- Datasets 2.14.5
	- Tokenizers 0.19.1