End of training

b2261ea verified 8 days ago

7.28 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: google/t5-efficient-tiny
	tags:
	- generated_from_trainer
	metrics:
	- accuracy
	- precision
	- recall
	- f1
	model-index:
	- name: sunflower_language_classification_v1
	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. -->

	# sunflower_language_classification_v1

	This model is a fine-tuned version of [google/t5-efficient-tiny](https://huggingface.co/google/t5-efficient-tiny) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.7212
	- Accuracy: 0.8297
	- Precision: 0.8471
	- Recall: 0.8297
	- F1: 0.8191

	## 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: 0.001
	- train_batch_size: 64
	- eval_batch_size: 64
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_steps: 10
	- training_steps: 30000

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Precision \| Recall \| F1 \|
	\|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:---------:\|:------:\|:------:\|
	\| 2.3995 \| 0.0167 \| 500 \| 2.0015 \| 0.5145 \| 0.4412 \| 0.5145 \| 0.4517 \|
	\| 1.3282 \| 0.0334 \| 1000 \| 1.6467 \| 0.5688 \| 0.4908 \| 0.5688 \| 0.5080 \|
	\| 1.1086 \| 0.0502 \| 1500 \| 1.5051 \| 0.6304 \| 0.5784 \| 0.6304 \| 0.5766 \|
	\| 0.9882 \| 0.0669 \| 2000 \| 1.4518 \| 0.6268 \| 0.6374 \| 0.6268 \| 0.5891 \|
	\| 0.9187 \| 0.0836 \| 2500 \| 1.3470 \| 0.6522 \| 0.6245 \| 0.6522 \| 0.6093 \|
	\| 0.8546 \| 0.1003 \| 3000 \| 1.3747 \| 0.6159 \| 0.5871 \| 0.6159 \| 0.5760 \|
	\| 0.8214 \| 0.1170 \| 3500 \| 1.2708 \| 0.6703 \| 0.6316 \| 0.6703 \| 0.6323 \|
	\| 0.7843 \| 0.1338 \| 4000 \| 1.1659 \| 0.6848 \| 0.6639 \| 0.6848 \| 0.6461 \|
	\| 0.7470 \| 0.1505 \| 4500 \| 1.1969 \| 0.6848 \| 0.6534 \| 0.6848 \| 0.6491 \|
	\| 0.7299 \| 0.1672 \| 5000 \| 1.0592 \| 0.7101 \| 0.7030 \| 0.7101 \| 0.6748 \|
	\| 0.7041 \| 0.1839 \| 5500 \| 1.0536 \| 0.6848 \| 0.6728 \| 0.6848 \| 0.6534 \|
	\| 0.6755 \| 0.2006 \| 6000 \| 1.0265 \| 0.7138 \| 0.7298 \| 0.7138 \| 0.6852 \|
	\| 0.6683 \| 0.2174 \| 6500 \| 1.0049 \| 0.7428 \| 0.7403 \| 0.7428 \| 0.7089 \|
	\| 0.6573 \| 0.2341 \| 7000 \| 1.0702 \| 0.7029 \| 0.7052 \| 0.7029 \| 0.6764 \|
	\| 0.6372 \| 0.2508 \| 7500 \| 1.0260 \| 0.7210 \| 0.7143 \| 0.7210 \| 0.6998 \|
	\| 0.6173 \| 0.2675 \| 8000 \| 0.9654 \| 0.7428 \| 0.7492 \| 0.7428 \| 0.7141 \|
	\| 0.6009 \| 0.2842 \| 8500 \| 1.0185 \| 0.7464 \| 0.7504 \| 0.7464 \| 0.7167 \|
	\| 0.5924 \| 0.3010 \| 9000 \| 1.0028 \| 0.7283 \| 0.7652 \| 0.7283 \| 0.7052 \|
	\| 0.5916 \| 0.3177 \| 9500 \| 0.9581 \| 0.7174 \| 0.7217 \| 0.7174 \| 0.6893 \|
	\| 0.5806 \| 0.3344 \| 10000 \| 1.0011 \| 0.7355 \| 0.7618 \| 0.7355 \| 0.7149 \|
	\| 0.5672 \| 0.3511 \| 10500 \| 0.8978 \| 0.7572 \| 0.7429 \| 0.7572 \| 0.7307 \|
	\| 0.5580 \| 0.3678 \| 11000 \| 0.9525 \| 0.7210 \| 0.7308 \| 0.7210 \| 0.7013 \|
	\| 0.5520 \| 0.3846 \| 11500 \| 0.8647 \| 0.7645 \| 0.7695 \| 0.7645 \| 0.7391 \|
	\| 0.5552 \| 0.4013 \| 12000 \| 0.8977 \| 0.7536 \| 0.7698 \| 0.7536 \| 0.7358 \|
	\| 0.5341 \| 0.4180 \| 12500 \| 0.8526 \| 0.7536 \| 0.7625 \| 0.7536 \| 0.7305 \|
	\| 0.5284 \| 0.4347 \| 13000 \| 0.8496 \| 0.7464 \| 0.7310 \| 0.7464 \| 0.7166 \|
	\| 0.5322 \| 0.4514 \| 13500 \| 0.7672 \| 0.8007 \| 0.8006 \| 0.8007 \| 0.7827 \|
	\| 0.5229 \| 0.4681 \| 14000 \| 0.8253 \| 0.7754 \| 0.7698 \| 0.7754 \| 0.7515 \|
	\| 0.5007 \| 0.4849 \| 14500 \| 0.8496 \| 0.7826 \| 0.7649 \| 0.7826 \| 0.7547 \|
	\| 0.5109 \| 0.5016 \| 15000 \| 0.7700 \| 0.7754 \| 0.7767 \| 0.7754 \| 0.7518 \|
	\| 0.4989 \| 0.5183 \| 15500 \| 0.8338 \| 0.7645 \| 0.7741 \| 0.7645 \| 0.7419 \|
	\| 0.4991 \| 0.5350 \| 16000 \| 0.7927 \| 0.7754 \| 0.7928 \| 0.7754 \| 0.7625 \|
	\| 0.4977 \| 0.5517 \| 16500 \| 0.7859 \| 0.7790 \| 0.7670 \| 0.7790 \| 0.7551 \|
	\| 0.4854 \| 0.5685 \| 17000 \| 0.7915 \| 0.7862 \| 0.7907 \| 0.7862 \| 0.7630 \|
	\| 0.4826 \| 0.5852 \| 17500 \| 0.7628 \| 0.8043 \| 0.7964 \| 0.8043 \| 0.7846 \|
	\| 0.4765 \| 0.6019 \| 18000 \| 0.7632 \| 0.7971 \| 0.8008 \| 0.7971 \| 0.7791 \|
	\| 0.4641 \| 0.6186 \| 18500 \| 0.7722 \| 0.7935 \| 0.7660 \| 0.7935 \| 0.7670 \|
	\| 0.4783 \| 0.6353 \| 19000 \| 0.7046 \| 0.7899 \| 0.8111 \| 0.7899 \| 0.7773 \|
	\| 0.4745 \| 0.6521 \| 19500 \| 0.7342 \| 0.7899 \| 0.8044 \| 0.7899 \| 0.7726 \|
	\| 0.4555 \| 0.6688 \| 20000 \| 0.7116 \| 0.7862 \| 0.7853 \| 0.7862 \| 0.7662 \|
	\| 0.4530 \| 0.6855 \| 20500 \| 0.7385 \| 0.7754 \| 0.7658 \| 0.7754 \| 0.7557 \|
	\| 0.4565 \| 0.7022 \| 21000 \| 0.7651 \| 0.7899 \| 0.8132 \| 0.7899 \| 0.7770 \|
	\| 0.4555 \| 0.7189 \| 21500 \| 0.7902 \| 0.7681 \| 0.7812 \| 0.7681 \| 0.7569 \|
	\| 0.4485 \| 0.7357 \| 22000 \| 0.7613 \| 0.7862 \| 0.7962 \| 0.7862 \| 0.7686 \|
	\| 0.4518 \| 0.7524 \| 22500 \| 0.7544 \| 0.7862 \| 0.7944 \| 0.7862 \| 0.7676 \|
	\| 0.4508 \| 0.7691 \| 23000 \| 0.7296 \| 0.8043 \| 0.8110 \| 0.8043 \| 0.7907 \|
	\| 0.4418 \| 0.7858 \| 23500 \| 0.7293 \| 0.8261 \| 0.8527 \| 0.8261 \| 0.8137 \|
	\| 0.4365 \| 0.8025 \| 24000 \| 0.7370 \| 0.8043 \| 0.8217 \| 0.8043 \| 0.7928 \|
	\| 0.4353 \| 0.8193 \| 24500 \| 0.7100 \| 0.8188 \| 0.8274 \| 0.8188 \| 0.8049 \|
	\| 0.4240 \| 0.8360 \| 25000 \| 0.7273 \| 0.7862 \| 0.7857 \| 0.7862 \| 0.7697 \|
	\| 0.4205 \| 0.8527 \| 25500 \| 0.7297 \| 0.8225 \| 0.8351 \| 0.8225 \| 0.8059 \|
	\| 0.4316 \| 0.8694 \| 26000 \| 0.7204 \| 0.8116 \| 0.8066 \| 0.8116 \| 0.7911 \|
	\| 0.4176 \| 0.8861 \| 26500 \| 0.7340 \| 0.8080 \| 0.8184 \| 0.8080 \| 0.7922 \|
	\| 0.4240 \| 0.9029 \| 27000 \| 0.7298 \| 0.8116 \| 0.8223 \| 0.8116 \| 0.7964 \|
	\| 0.4149 \| 0.9196 \| 27500 \| 0.7410 \| 0.8188 \| 0.8185 \| 0.8188 \| 0.8023 \|
	\| 0.4159 \| 0.9363 \| 28000 \| 0.7303 \| 0.8152 \| 0.8388 \| 0.8152 \| 0.8069 \|
	\| 0.4068 \| 0.9530 \| 28500 \| 0.7220 \| 0.8043 \| 0.8209 \| 0.8043 \| 0.7955 \|
	\| 0.4135 \| 0.9697 \| 29000 \| 0.7313 \| 0.8188 \| 0.8238 \| 0.8188 \| 0.8055 \|
	\| 0.4130 \| 0.9865 \| 29500 \| 0.7221 \| 0.8225 \| 0.8320 \| 0.8225 \| 0.8095 \|
	\| 0.4213 \| 1.0032 \| 30000 \| 0.7212 \| 0.8297 \| 0.8471 \| 0.8297 \| 0.8191 \|


	### Framework versions

	- Transformers 5.8.0
	- Pytorch 2.11.0+cu130
	- Datasets 4.8.5
	- Tokenizers 0.22.2

	---
	library_name: transformers
	license: apache-2.0
	base_model: google/t5-efficient-tiny
	tags:
	- generated_from_trainer
	metrics:
	- accuracy
	- precision
	- recall
	- f1
	model-index:
	- name: sunflower_language_classification_v1
	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. -->

	# sunflower_language_classification_v1

	This model is a fine-tuned version of [google/t5-efficient-tiny](https://huggingface.co/google/t5-efficient-tiny) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.7212
	- Accuracy: 0.8297
	- Precision: 0.8471
	- Recall: 0.8297
	- F1: 0.8191

	## 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: 0.001
	- train_batch_size: 64
	- eval_batch_size: 64
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_steps: 10
	- training_steps: 30000

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Precision \| Recall \| F1 \|
	\|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:---------:\|:------:\|:------:\|
	\| 2.3995 \| 0.0167 \| 500 \| 2.0015 \| 0.5145 \| 0.4412 \| 0.5145 \| 0.4517 \|
	\| 1.3282 \| 0.0334 \| 1000 \| 1.6467 \| 0.5688 \| 0.4908 \| 0.5688 \| 0.5080 \|
	\| 1.1086 \| 0.0502 \| 1500 \| 1.5051 \| 0.6304 \| 0.5784 \| 0.6304 \| 0.5766 \|
	\| 0.9882 \| 0.0669 \| 2000 \| 1.4518 \| 0.6268 \| 0.6374 \| 0.6268 \| 0.5891 \|
	\| 0.9187 \| 0.0836 \| 2500 \| 1.3470 \| 0.6522 \| 0.6245 \| 0.6522 \| 0.6093 \|
	\| 0.8546 \| 0.1003 \| 3000 \| 1.3747 \| 0.6159 \| 0.5871 \| 0.6159 \| 0.5760 \|
	\| 0.8214 \| 0.1170 \| 3500 \| 1.2708 \| 0.6703 \| 0.6316 \| 0.6703 \| 0.6323 \|
	\| 0.7843 \| 0.1338 \| 4000 \| 1.1659 \| 0.6848 \| 0.6639 \| 0.6848 \| 0.6461 \|
	\| 0.7470 \| 0.1505 \| 4500 \| 1.1969 \| 0.6848 \| 0.6534 \| 0.6848 \| 0.6491 \|
	\| 0.7299 \| 0.1672 \| 5000 \| 1.0592 \| 0.7101 \| 0.7030 \| 0.7101 \| 0.6748 \|
	\| 0.7041 \| 0.1839 \| 5500 \| 1.0536 \| 0.6848 \| 0.6728 \| 0.6848 \| 0.6534 \|
	\| 0.6755 \| 0.2006 \| 6000 \| 1.0265 \| 0.7138 \| 0.7298 \| 0.7138 \| 0.6852 \|
	\| 0.6683 \| 0.2174 \| 6500 \| 1.0049 \| 0.7428 \| 0.7403 \| 0.7428 \| 0.7089 \|
	\| 0.6573 \| 0.2341 \| 7000 \| 1.0702 \| 0.7029 \| 0.7052 \| 0.7029 \| 0.6764 \|
	\| 0.6372 \| 0.2508 \| 7500 \| 1.0260 \| 0.7210 \| 0.7143 \| 0.7210 \| 0.6998 \|
	\| 0.6173 \| 0.2675 \| 8000 \| 0.9654 \| 0.7428 \| 0.7492 \| 0.7428 \| 0.7141 \|
	\| 0.6009 \| 0.2842 \| 8500 \| 1.0185 \| 0.7464 \| 0.7504 \| 0.7464 \| 0.7167 \|
	\| 0.5924 \| 0.3010 \| 9000 \| 1.0028 \| 0.7283 \| 0.7652 \| 0.7283 \| 0.7052 \|
	\| 0.5916 \| 0.3177 \| 9500 \| 0.9581 \| 0.7174 \| 0.7217 \| 0.7174 \| 0.6893 \|
	\| 0.5806 \| 0.3344 \| 10000 \| 1.0011 \| 0.7355 \| 0.7618 \| 0.7355 \| 0.7149 \|
	\| 0.5672 \| 0.3511 \| 10500 \| 0.8978 \| 0.7572 \| 0.7429 \| 0.7572 \| 0.7307 \|
	\| 0.5580 \| 0.3678 \| 11000 \| 0.9525 \| 0.7210 \| 0.7308 \| 0.7210 \| 0.7013 \|
	\| 0.5520 \| 0.3846 \| 11500 \| 0.8647 \| 0.7645 \| 0.7695 \| 0.7645 \| 0.7391 \|
	\| 0.5552 \| 0.4013 \| 12000 \| 0.8977 \| 0.7536 \| 0.7698 \| 0.7536 \| 0.7358 \|
	\| 0.5341 \| 0.4180 \| 12500 \| 0.8526 \| 0.7536 \| 0.7625 \| 0.7536 \| 0.7305 \|
	\| 0.5284 \| 0.4347 \| 13000 \| 0.8496 \| 0.7464 \| 0.7310 \| 0.7464 \| 0.7166 \|
	\| 0.5322 \| 0.4514 \| 13500 \| 0.7672 \| 0.8007 \| 0.8006 \| 0.8007 \| 0.7827 \|
	\| 0.5229 \| 0.4681 \| 14000 \| 0.8253 \| 0.7754 \| 0.7698 \| 0.7754 \| 0.7515 \|
	\| 0.5007 \| 0.4849 \| 14500 \| 0.8496 \| 0.7826 \| 0.7649 \| 0.7826 \| 0.7547 \|
	\| 0.5109 \| 0.5016 \| 15000 \| 0.7700 \| 0.7754 \| 0.7767 \| 0.7754 \| 0.7518 \|
	\| 0.4989 \| 0.5183 \| 15500 \| 0.8338 \| 0.7645 \| 0.7741 \| 0.7645 \| 0.7419 \|
	\| 0.4991 \| 0.5350 \| 16000 \| 0.7927 \| 0.7754 \| 0.7928 \| 0.7754 \| 0.7625 \|
	\| 0.4977 \| 0.5517 \| 16500 \| 0.7859 \| 0.7790 \| 0.7670 \| 0.7790 \| 0.7551 \|
	\| 0.4854 \| 0.5685 \| 17000 \| 0.7915 \| 0.7862 \| 0.7907 \| 0.7862 \| 0.7630 \|
	\| 0.4826 \| 0.5852 \| 17500 \| 0.7628 \| 0.8043 \| 0.7964 \| 0.8043 \| 0.7846 \|
	\| 0.4765 \| 0.6019 \| 18000 \| 0.7632 \| 0.7971 \| 0.8008 \| 0.7971 \| 0.7791 \|
	\| 0.4641 \| 0.6186 \| 18500 \| 0.7722 \| 0.7935 \| 0.7660 \| 0.7935 \| 0.7670 \|
	\| 0.4783 \| 0.6353 \| 19000 \| 0.7046 \| 0.7899 \| 0.8111 \| 0.7899 \| 0.7773 \|
	\| 0.4745 \| 0.6521 \| 19500 \| 0.7342 \| 0.7899 \| 0.8044 \| 0.7899 \| 0.7726 \|
	\| 0.4555 \| 0.6688 \| 20000 \| 0.7116 \| 0.7862 \| 0.7853 \| 0.7862 \| 0.7662 \|
	\| 0.4530 \| 0.6855 \| 20500 \| 0.7385 \| 0.7754 \| 0.7658 \| 0.7754 \| 0.7557 \|
	\| 0.4565 \| 0.7022 \| 21000 \| 0.7651 \| 0.7899 \| 0.8132 \| 0.7899 \| 0.7770 \|
	\| 0.4555 \| 0.7189 \| 21500 \| 0.7902 \| 0.7681 \| 0.7812 \| 0.7681 \| 0.7569 \|
	\| 0.4485 \| 0.7357 \| 22000 \| 0.7613 \| 0.7862 \| 0.7962 \| 0.7862 \| 0.7686 \|
	\| 0.4518 \| 0.7524 \| 22500 \| 0.7544 \| 0.7862 \| 0.7944 \| 0.7862 \| 0.7676 \|
	\| 0.4508 \| 0.7691 \| 23000 \| 0.7296 \| 0.8043 \| 0.8110 \| 0.8043 \| 0.7907 \|
	\| 0.4418 \| 0.7858 \| 23500 \| 0.7293 \| 0.8261 \| 0.8527 \| 0.8261 \| 0.8137 \|
	\| 0.4365 \| 0.8025 \| 24000 \| 0.7370 \| 0.8043 \| 0.8217 \| 0.8043 \| 0.7928 \|
	\| 0.4353 \| 0.8193 \| 24500 \| 0.7100 \| 0.8188 \| 0.8274 \| 0.8188 \| 0.8049 \|
	\| 0.4240 \| 0.8360 \| 25000 \| 0.7273 \| 0.7862 \| 0.7857 \| 0.7862 \| 0.7697 \|
	\| 0.4205 \| 0.8527 \| 25500 \| 0.7297 \| 0.8225 \| 0.8351 \| 0.8225 \| 0.8059 \|
	\| 0.4316 \| 0.8694 \| 26000 \| 0.7204 \| 0.8116 \| 0.8066 \| 0.8116 \| 0.7911 \|
	\| 0.4176 \| 0.8861 \| 26500 \| 0.7340 \| 0.8080 \| 0.8184 \| 0.8080 \| 0.7922 \|
	\| 0.4240 \| 0.9029 \| 27000 \| 0.7298 \| 0.8116 \| 0.8223 \| 0.8116 \| 0.7964 \|
	\| 0.4149 \| 0.9196 \| 27500 \| 0.7410 \| 0.8188 \| 0.8185 \| 0.8188 \| 0.8023 \|
	\| 0.4159 \| 0.9363 \| 28000 \| 0.7303 \| 0.8152 \| 0.8388 \| 0.8152 \| 0.8069 \|
	\| 0.4068 \| 0.9530 \| 28500 \| 0.7220 \| 0.8043 \| 0.8209 \| 0.8043 \| 0.7955 \|
	\| 0.4135 \| 0.9697 \| 29000 \| 0.7313 \| 0.8188 \| 0.8238 \| 0.8188 \| 0.8055 \|
	\| 0.4130 \| 0.9865 \| 29500 \| 0.7221 \| 0.8225 \| 0.8320 \| 0.8225 \| 0.8095 \|
	\| 0.4213 \| 1.0032 \| 30000 \| 0.7212 \| 0.8297 \| 0.8471 \| 0.8297 \| 0.8191 \|


	### Framework versions

	- Transformers 5.8.0
	- Pytorch 2.11.0+cu130
	- Datasets 4.8.5
	- Tokenizers 0.22.2