Upload tokenizer

0834d11 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_half55
	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_half55

	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: 0.1716
	- Precision: 0.7969
	- Recall: 0.7989
	- F1: 0.7979
	- Accuracy: 0.9786

	## 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: 55
	- 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 \|
	\|:-------------:\|:-------:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.144 \| 0.5828 \| 500 \| 0.0813 \| 0.6995 \| 0.7625 \| 0.7297 \| 0.9732 \|
	\| 0.0678 \| 1.1655 \| 1000 \| 0.0775 \| 0.7546 \| 0.7816 \| 0.7678 \| 0.9772 \|
	\| 0.0531 \| 1.7483 \| 1500 \| 0.0810 \| 0.7244 \| 0.8137 \| 0.7665 \| 0.9760 \|
	\| 0.0368 \| 2.3310 \| 2000 \| 0.0831 \| 0.7742 \| 0.7919 \| 0.7830 \| 0.9782 \|
	\| 0.0311 \| 2.9138 \| 2500 \| 0.0871 \| 0.7695 \| 0.7917 \| 0.7804 \| 0.9773 \|
	\| 0.0222 \| 3.4965 \| 3000 \| 0.0916 \| 0.7856 \| 0.7860 \| 0.7858 \| 0.9785 \|
	\| 0.0196 \| 4.0793 \| 3500 \| 0.0982 \| 0.7778 \| 0.7990 \| 0.7883 \| 0.9781 \|
	\| 0.0145 \| 4.6620 \| 4000 \| 0.1004 \| 0.7769 \| 0.7927 \| 0.7847 \| 0.9778 \|
	\| 0.0131 \| 5.2448 \| 4500 \| 0.1058 \| 0.7719 \| 0.7878 \| 0.7798 \| 0.9769 \|
	\| 0.0108 \| 5.8275 \| 5000 \| 0.1116 \| 0.7830 \| 0.7919 \| 0.7875 \| 0.9775 \|
	\| 0.0086 \| 6.4103 \| 5500 \| 0.1137 \| 0.7743 \| 0.8018 \| 0.7878 \| 0.9778 \|
	\| 0.009 \| 6.9930 \| 6000 \| 0.1180 \| 0.7739 \| 0.8078 \| 0.7905 \| 0.9778 \|
	\| 0.0066 \| 7.5758 \| 6500 \| 0.1189 \| 0.7761 \| 0.8090 \| 0.7922 \| 0.9782 \|
	\| 0.007 \| 8.1585 \| 7000 \| 0.1281 \| 0.7813 \| 0.7869 \| 0.7841 \| 0.9777 \|
	\| 0.0059 \| 8.7413 \| 7500 \| 0.1222 \| 0.7781 \| 0.8070 \| 0.7923 \| 0.9785 \|
	\| 0.0057 \| 9.3240 \| 8000 \| 0.1298 \| 0.7694 \| 0.8124 \| 0.7903 \| 0.9781 \|
	\| 0.0053 \| 9.9068 \| 8500 \| 0.1260 \| 0.7919 \| 0.7951 \| 0.7935 \| 0.9787 \|
	\| 0.0043 \| 10.4895 \| 9000 \| 0.1356 \| 0.7719 \| 0.8062 \| 0.7887 \| 0.9778 \|
	\| 0.0042 \| 11.0723 \| 9500 \| 0.1309 \| 0.7850 \| 0.7982 \| 0.7915 \| 0.9786 \|
	\| 0.0042 \| 11.6550 \| 10000 \| 0.1356 \| 0.7789 \| 0.7922 \| 0.7855 \| 0.9779 \|
	\| 0.0034 \| 12.2378 \| 10500 \| 0.1367 \| 0.7781 \| 0.8013 \| 0.7895 \| 0.9782 \|
	\| 0.0032 \| 12.8205 \| 11000 \| 0.1409 \| 0.7732 \| 0.8123 \| 0.7923 \| 0.9781 \|
	\| 0.0022 \| 13.4033 \| 11500 \| 0.1498 \| 0.7707 \| 0.8068 \| 0.7883 \| 0.9778 \|
	\| 0.0031 \| 13.9860 \| 12000 \| 0.1454 \| 0.7704 \| 0.8133 \| 0.7913 \| 0.9781 \|
	\| 0.0022 \| 14.5688 \| 12500 \| 0.1436 \| 0.7922 \| 0.7934 \| 0.7928 \| 0.9784 \|
	\| 0.0024 \| 15.1515 \| 13000 \| 0.1461 \| 0.7734 \| 0.8077 \| 0.7902 \| 0.9778 \|
	\| 0.0023 \| 15.7343 \| 13500 \| 0.1465 \| 0.7918 \| 0.7996 \| 0.7957 \| 0.9786 \|
	\| 0.0017 \| 16.3170 \| 14000 \| 0.1506 \| 0.7838 \| 0.8022 \| 0.7929 \| 0.9783 \|
	\| 0.0018 \| 16.8998 \| 14500 \| 0.1466 \| 0.7953 \| 0.7973 \| 0.7963 \| 0.9787 \|
	\| 0.0018 \| 17.4825 \| 15000 \| 0.1502 \| 0.7941 \| 0.8012 \| 0.7976 \| 0.9789 \|
	\| 0.0019 \| 18.0653 \| 15500 \| 0.1515 \| 0.7871 \| 0.8052 \| 0.7960 \| 0.9786 \|
	\| 0.0018 \| 18.6480 \| 16000 \| 0.1501 \| 0.8062 \| 0.7780 \| 0.7918 \| 0.9782 \|
	\| 0.0016 \| 19.2308 \| 16500 \| 0.1547 \| 0.7887 \| 0.7963 \| 0.7924 \| 0.9780 \|
	\| 0.001 \| 19.8135 \| 17000 \| 0.1650 \| 0.7819 \| 0.8070 \| 0.7942 \| 0.9778 \|
	\| 0.0009 \| 20.3963 \| 17500 \| 0.1612 \| 0.7971 \| 0.7833 \| 0.7901 \| 0.9780 \|
	\| 0.0012 \| 20.9790 \| 18000 \| 0.1569 \| 0.7903 \| 0.8023 \| 0.7962 \| 0.9785 \|
	\| 0.0008 \| 21.5618 \| 18500 \| 0.1640 \| 0.7787 \| 0.8081 \| 0.7931 \| 0.9779 \|
	\| 0.0009 \| 22.1445 \| 19000 \| 0.1640 \| 0.7950 \| 0.7924 \| 0.7937 \| 0.9781 \|
	\| 0.0008 \| 22.7273 \| 19500 \| 0.1650 \| 0.7982 \| 0.8023 \| 0.8003 \| 0.9789 \|
	\| 0.0007 \| 23.3100 \| 20000 \| 0.1635 \| 0.7962 \| 0.8022 \| 0.7992 \| 0.9787 \|
	\| 0.0008 \| 23.8928 \| 20500 \| 0.1678 \| 0.7852 \| 0.8005 \| 0.7927 \| 0.9784 \|
	\| 0.0006 \| 24.4755 \| 21000 \| 0.1686 \| 0.7970 \| 0.8025 \| 0.7997 \| 0.9788 \|
	\| 0.0006 \| 25.0583 \| 21500 \| 0.1686 \| 0.7963 \| 0.7970 \| 0.7967 \| 0.9785 \|
	\| 0.0006 \| 25.6410 \| 22000 \| 0.1706 \| 0.7941 \| 0.7948 \| 0.7945 \| 0.9784 \|
	\| 0.0005 \| 26.2238 \| 22500 \| 0.1681 \| 0.7935 \| 0.7963 \| 0.7949 \| 0.9785 \|
	\| 0.0005 \| 26.8065 \| 23000 \| 0.1688 \| 0.8008 \| 0.7938 \| 0.7973 \| 0.9788 \|
	\| 0.0004 \| 27.3893 \| 23500 \| 0.1700 \| 0.7898 \| 0.7996 \| 0.7947 \| 0.9784 \|
	\| 0.0005 \| 27.9720 \| 24000 \| 0.1708 \| 0.7914 \| 0.8096 \| 0.8004 \| 0.9786 \|
	\| 0.0003 \| 28.5548 \| 24500 \| 0.1713 \| 0.7965 \| 0.7979 \| 0.7972 \| 0.9785 \|
	\| 0.0004 \| 29.1375 \| 25000 \| 0.1710 \| 0.7951 \| 0.8010 \| 0.7980 \| 0.9786 \|
	\| 0.0005 \| 29.7203 \| 25500 \| 0.1716 \| 0.7969 \| 0.7989 \| 0.7979 \| 0.9786 \|


	### 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_half55
	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_half55

	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: 0.1716
	- Precision: 0.7969
	- Recall: 0.7989
	- F1: 0.7979
	- Accuracy: 0.9786

	## 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: 55
	- 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 \|
	\|:-------------:\|:-------:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.144 \| 0.5828 \| 500 \| 0.0813 \| 0.6995 \| 0.7625 \| 0.7297 \| 0.9732 \|
	\| 0.0678 \| 1.1655 \| 1000 \| 0.0775 \| 0.7546 \| 0.7816 \| 0.7678 \| 0.9772 \|
	\| 0.0531 \| 1.7483 \| 1500 \| 0.0810 \| 0.7244 \| 0.8137 \| 0.7665 \| 0.9760 \|
	\| 0.0368 \| 2.3310 \| 2000 \| 0.0831 \| 0.7742 \| 0.7919 \| 0.7830 \| 0.9782 \|
	\| 0.0311 \| 2.9138 \| 2500 \| 0.0871 \| 0.7695 \| 0.7917 \| 0.7804 \| 0.9773 \|
	\| 0.0222 \| 3.4965 \| 3000 \| 0.0916 \| 0.7856 \| 0.7860 \| 0.7858 \| 0.9785 \|
	\| 0.0196 \| 4.0793 \| 3500 \| 0.0982 \| 0.7778 \| 0.7990 \| 0.7883 \| 0.9781 \|
	\| 0.0145 \| 4.6620 \| 4000 \| 0.1004 \| 0.7769 \| 0.7927 \| 0.7847 \| 0.9778 \|
	\| 0.0131 \| 5.2448 \| 4500 \| 0.1058 \| 0.7719 \| 0.7878 \| 0.7798 \| 0.9769 \|
	\| 0.0108 \| 5.8275 \| 5000 \| 0.1116 \| 0.7830 \| 0.7919 \| 0.7875 \| 0.9775 \|
	\| 0.0086 \| 6.4103 \| 5500 \| 0.1137 \| 0.7743 \| 0.8018 \| 0.7878 \| 0.9778 \|
	\| 0.009 \| 6.9930 \| 6000 \| 0.1180 \| 0.7739 \| 0.8078 \| 0.7905 \| 0.9778 \|
	\| 0.0066 \| 7.5758 \| 6500 \| 0.1189 \| 0.7761 \| 0.8090 \| 0.7922 \| 0.9782 \|
	\| 0.007 \| 8.1585 \| 7000 \| 0.1281 \| 0.7813 \| 0.7869 \| 0.7841 \| 0.9777 \|
	\| 0.0059 \| 8.7413 \| 7500 \| 0.1222 \| 0.7781 \| 0.8070 \| 0.7923 \| 0.9785 \|
	\| 0.0057 \| 9.3240 \| 8000 \| 0.1298 \| 0.7694 \| 0.8124 \| 0.7903 \| 0.9781 \|
	\| 0.0053 \| 9.9068 \| 8500 \| 0.1260 \| 0.7919 \| 0.7951 \| 0.7935 \| 0.9787 \|
	\| 0.0043 \| 10.4895 \| 9000 \| 0.1356 \| 0.7719 \| 0.8062 \| 0.7887 \| 0.9778 \|
	\| 0.0042 \| 11.0723 \| 9500 \| 0.1309 \| 0.7850 \| 0.7982 \| 0.7915 \| 0.9786 \|
	\| 0.0042 \| 11.6550 \| 10000 \| 0.1356 \| 0.7789 \| 0.7922 \| 0.7855 \| 0.9779 \|
	\| 0.0034 \| 12.2378 \| 10500 \| 0.1367 \| 0.7781 \| 0.8013 \| 0.7895 \| 0.9782 \|
	\| 0.0032 \| 12.8205 \| 11000 \| 0.1409 \| 0.7732 \| 0.8123 \| 0.7923 \| 0.9781 \|
	\| 0.0022 \| 13.4033 \| 11500 \| 0.1498 \| 0.7707 \| 0.8068 \| 0.7883 \| 0.9778 \|
	\| 0.0031 \| 13.9860 \| 12000 \| 0.1454 \| 0.7704 \| 0.8133 \| 0.7913 \| 0.9781 \|
	\| 0.0022 \| 14.5688 \| 12500 \| 0.1436 \| 0.7922 \| 0.7934 \| 0.7928 \| 0.9784 \|
	\| 0.0024 \| 15.1515 \| 13000 \| 0.1461 \| 0.7734 \| 0.8077 \| 0.7902 \| 0.9778 \|
	\| 0.0023 \| 15.7343 \| 13500 \| 0.1465 \| 0.7918 \| 0.7996 \| 0.7957 \| 0.9786 \|
	\| 0.0017 \| 16.3170 \| 14000 \| 0.1506 \| 0.7838 \| 0.8022 \| 0.7929 \| 0.9783 \|
	\| 0.0018 \| 16.8998 \| 14500 \| 0.1466 \| 0.7953 \| 0.7973 \| 0.7963 \| 0.9787 \|
	\| 0.0018 \| 17.4825 \| 15000 \| 0.1502 \| 0.7941 \| 0.8012 \| 0.7976 \| 0.9789 \|
	\| 0.0019 \| 18.0653 \| 15500 \| 0.1515 \| 0.7871 \| 0.8052 \| 0.7960 \| 0.9786 \|
	\| 0.0018 \| 18.6480 \| 16000 \| 0.1501 \| 0.8062 \| 0.7780 \| 0.7918 \| 0.9782 \|
	\| 0.0016 \| 19.2308 \| 16500 \| 0.1547 \| 0.7887 \| 0.7963 \| 0.7924 \| 0.9780 \|
	\| 0.001 \| 19.8135 \| 17000 \| 0.1650 \| 0.7819 \| 0.8070 \| 0.7942 \| 0.9778 \|
	\| 0.0009 \| 20.3963 \| 17500 \| 0.1612 \| 0.7971 \| 0.7833 \| 0.7901 \| 0.9780 \|
	\| 0.0012 \| 20.9790 \| 18000 \| 0.1569 \| 0.7903 \| 0.8023 \| 0.7962 \| 0.9785 \|
	\| 0.0008 \| 21.5618 \| 18500 \| 0.1640 \| 0.7787 \| 0.8081 \| 0.7931 \| 0.9779 \|
	\| 0.0009 \| 22.1445 \| 19000 \| 0.1640 \| 0.7950 \| 0.7924 \| 0.7937 \| 0.9781 \|
	\| 0.0008 \| 22.7273 \| 19500 \| 0.1650 \| 0.7982 \| 0.8023 \| 0.8003 \| 0.9789 \|
	\| 0.0007 \| 23.3100 \| 20000 \| 0.1635 \| 0.7962 \| 0.8022 \| 0.7992 \| 0.9787 \|
	\| 0.0008 \| 23.8928 \| 20500 \| 0.1678 \| 0.7852 \| 0.8005 \| 0.7927 \| 0.9784 \|
	\| 0.0006 \| 24.4755 \| 21000 \| 0.1686 \| 0.7970 \| 0.8025 \| 0.7997 \| 0.9788 \|
	\| 0.0006 \| 25.0583 \| 21500 \| 0.1686 \| 0.7963 \| 0.7970 \| 0.7967 \| 0.9785 \|
	\| 0.0006 \| 25.6410 \| 22000 \| 0.1706 \| 0.7941 \| 0.7948 \| 0.7945 \| 0.9784 \|
	\| 0.0005 \| 26.2238 \| 22500 \| 0.1681 \| 0.7935 \| 0.7963 \| 0.7949 \| 0.9785 \|
	\| 0.0005 \| 26.8065 \| 23000 \| 0.1688 \| 0.8008 \| 0.7938 \| 0.7973 \| 0.9788 \|
	\| 0.0004 \| 27.3893 \| 23500 \| 0.1700 \| 0.7898 \| 0.7996 \| 0.7947 \| 0.9784 \|
	\| 0.0005 \| 27.9720 \| 24000 \| 0.1708 \| 0.7914 \| 0.8096 \| 0.8004 \| 0.9786 \|
	\| 0.0003 \| 28.5548 \| 24500 \| 0.1713 \| 0.7965 \| 0.7979 \| 0.7972 \| 0.9785 \|
	\| 0.0004 \| 29.1375 \| 25000 \| 0.1710 \| 0.7951 \| 0.8010 \| 0.7980 \| 0.9786 \|
	\| 0.0005 \| 29.7203 \| 25500 \| 0.1716 \| 0.7969 \| 0.7989 \| 0.7979 \| 0.9786 \|


	### Framework versions

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