LIM-0.5 / README.md

adasgaleus

End of training

036bf18 verified 4 months ago

preview code

raw

history blame contribute delete

No virus

6.89 kB

	---
	license: apache-2.0
	base_model: google-bert/bert-base-uncased
	tags:
	- generated_from_trainer
	metrics:
	- precision
	- recall
	- f1
	- accuracy
	model-index:
	- name: 20240402140914_big_aristotle
	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. -->

	# 20240402140914_big_aristotle

	This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.0293
	- Precision: 0.9731
	- Recall: 0.9711
	- F1: 0.9721
	- Accuracy: 0.9891

	## 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: 0.0005
	- train_batch_size: 32
	- eval_batch_size: 32
	- seed: 69
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 256
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_steps: 350
	- num_epochs: 5

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \|
	\|:-------------:\|:-----:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.0654 \| 0.09 \| 300 \| 0.0495 \| 0.9535 \| 0.9462 \| 0.9498 \| 0.9808 \|
	\| 0.0647 \| 0.18 \| 600 \| 0.0489 \| 0.9529 \| 0.9470 \| 0.9499 \| 0.9807 \|
	\| 0.0626 \| 0.26 \| 900 \| 0.0486 \| 0.9542 \| 0.9448 \| 0.9495 \| 0.9807 \|
	\| 0.0613 \| 0.35 \| 1200 \| 0.0460 \| 0.9544 \| 0.9501 \| 0.9522 \| 0.9815 \|
	\| 0.0623 \| 0.44 \| 1500 \| 0.0469 \| 0.9538 \| 0.9493 \| 0.9515 \| 0.9814 \|
	\| 0.0573 \| 0.53 \| 1800 \| 0.0455 \| 0.9552 \| 0.9488 \| 0.9520 \| 0.9816 \|
	\| 0.0569 \| 0.61 \| 2100 \| 0.0447 \| 0.9528 \| 0.9540 \| 0.9534 \| 0.9819 \|
	\| 0.0585 \| 0.7 \| 2400 \| 0.0464 \| 0.9566 \| 0.9468 \| 0.9516 \| 0.9815 \|
	\| 0.056 \| 0.79 \| 2700 \| 0.0452 \| 0.9555 \| 0.9517 \| 0.9536 \| 0.9822 \|
	\| 0.0564 \| 0.88 \| 3000 \| 0.0430 \| 0.9591 \| 0.9512 \| 0.9551 \| 0.9828 \|
	\| 0.0552 \| 0.96 \| 3300 \| 0.0433 \| 0.9548 \| 0.9532 \| 0.9540 \| 0.9825 \|
	\| 0.048 \| 1.05 \| 3600 \| 0.0444 \| 0.9579 \| 0.9529 \| 0.9554 \| 0.9828 \|
	\| 0.0483 \| 1.14 \| 3900 \| 0.0415 \| 0.9582 \| 0.9553 \| 0.9568 \| 0.9831 \|
	\| 0.0465 \| 1.23 \| 4200 \| 0.0424 \| 0.9622 \| 0.9495 \| 0.9558 \| 0.9831 \|
	\| 0.0465 \| 1.31 \| 4500 \| 0.0415 \| 0.9616 \| 0.9514 \| 0.9565 \| 0.9835 \|
	\| 0.0462 \| 1.4 \| 4800 \| 0.0407 \| 0.9588 \| 0.9534 \| 0.9561 \| 0.9835 \|
	\| 0.0467 \| 1.49 \| 5100 \| 0.0403 \| 0.9582 \| 0.9581 \| 0.9581 \| 0.9836 \|
	\| 0.0453 \| 1.58 \| 5400 \| 0.0405 \| 0.9636 \| 0.9513 \| 0.9574 \| 0.9839 \|
	\| 0.0446 \| 1.66 \| 5700 \| 0.0383 \| 0.9637 \| 0.9555 \| 0.9596 \| 0.9847 \|
	\| 0.0443 \| 1.75 \| 6000 \| 0.0382 \| 0.9596 \| 0.9572 \| 0.9584 \| 0.9844 \|
	\| 0.0432 \| 1.84 \| 6300 \| 0.0373 \| 0.9637 \| 0.9573 \| 0.9605 \| 0.9847 \|
	\| 0.0424 \| 1.93 \| 6600 \| 0.0368 \| 0.9674 \| 0.9516 \| 0.9594 \| 0.9850 \|
	\| 0.0364 \| 2.01 \| 6900 \| 0.0361 \| 0.9633 \| 0.9570 \| 0.9601 \| 0.9851 \|
	\| 0.0358 \| 2.1 \| 7200 \| 0.0366 \| 0.9618 \| 0.9613 \| 0.9615 \| 0.9853 \|
	\| 0.0359 \| 2.19 \| 7500 \| 0.0370 \| 0.9665 \| 0.9561 \| 0.9613 \| 0.9852 \|
	\| 0.036 \| 2.28 \| 7800 \| 0.0360 \| 0.9660 \| 0.9564 \| 0.9611 \| 0.9853 \|
	\| 0.0352 \| 2.36 \| 8100 \| 0.0355 \| 0.9658 \| 0.9602 \| 0.9630 \| 0.9856 \|
	\| 0.0354 \| 2.45 \| 8400 \| 0.0354 \| 0.9682 \| 0.9579 \| 0.9630 \| 0.9860 \|
	\| 0.0347 \| 2.54 \| 8700 \| 0.0347 \| 0.9694 \| 0.9566 \| 0.9630 \| 0.9861 \|
	\| 0.0347 \| 2.63 \| 9000 \| 0.0340 \| 0.9676 \| 0.9597 \| 0.9636 \| 0.9864 \|
	\| 0.0338 \| 2.71 \| 9300 \| 0.0327 \| 0.9682 \| 0.9626 \| 0.9654 \| 0.9867 \|
	\| 0.0338 \| 2.8 \| 9600 \| 0.0334 \| 0.9681 \| 0.9627 \| 0.9654 \| 0.9865 \|
	\| 0.033 \| 2.89 \| 9900 \| 0.0325 \| 0.9705 \| 0.9613 \| 0.9659 \| 0.9870 \|
	\| 0.0326 \| 2.98 \| 10200 \| 0.0331 \| 0.9686 \| 0.9640 \| 0.9663 \| 0.9870 \|
	\| 0.0264 \| 3.06 \| 10500 \| 0.0352 \| 0.9689 \| 0.9651 \| 0.9670 \| 0.9871 \|
	\| 0.0261 \| 3.15 \| 10800 \| 0.0329 \| 0.9698 \| 0.9633 \| 0.9666 \| 0.9871 \|
	\| 0.026 \| 3.24 \| 11100 \| 0.0328 \| 0.9672 \| 0.9662 \| 0.9667 \| 0.9872 \|
	\| 0.0261 \| 3.33 \| 11400 \| 0.0333 \| 0.9678 \| 0.9681 \| 0.9680 \| 0.9872 \|
	\| 0.0264 \| 3.41 \| 11700 \| 0.0326 \| 0.9689 \| 0.9676 \| 0.9682 \| 0.9875 \|
	\| 0.0258 \| 3.5 \| 12000 \| 0.0313 \| 0.9717 \| 0.9643 \| 0.9680 \| 0.9877 \|
	\| 0.0254 \| 3.59 \| 12300 \| 0.0307 \| 0.9691 \| 0.9675 \| 0.9683 \| 0.9880 \|
	\| 0.0249 \| 3.68 \| 12600 \| 0.0304 \| 0.9720 \| 0.9666 \| 0.9693 \| 0.9881 \|
	\| 0.025 \| 3.76 \| 12900 \| 0.0300 \| 0.9686 \| 0.9680 \| 0.9683 \| 0.9882 \|
	\| 0.0242 \| 3.85 \| 13200 \| 0.0297 \| 0.9682 \| 0.9682 \| 0.9682 \| 0.9881 \|
	\| 0.0246 \| 3.94 \| 13500 \| 0.0291 \| 0.9725 \| 0.9655 \| 0.9690 \| 0.9883 \|
	\| 0.0184 \| 4.03 \| 13800 \| 0.0320 \| 0.9712 \| 0.9678 \| 0.9695 \| 0.9882 \|
	\| 0.0186 \| 4.11 \| 14100 \| 0.0311 \| 0.9703 \| 0.9688 \| 0.9696 \| 0.9883 \|
	\| 0.0183 \| 4.2 \| 14400 \| 0.0319 \| 0.9718 \| 0.9696 \| 0.9707 \| 0.9886 \|
	\| 0.0181 \| 4.29 \| 14700 \| 0.0312 \| 0.9730 \| 0.9673 \| 0.9702 \| 0.9885 \|
	\| 0.0181 \| 4.38 \| 15000 \| 0.0308 \| 0.9694 \| 0.9698 \| 0.9696 \| 0.9885 \|
	\| 0.0178 \| 4.47 \| 15300 \| 0.0302 \| 0.9727 \| 0.9698 \| 0.9712 \| 0.9888 \|
	\| 0.0175 \| 4.55 \| 15600 \| 0.0300 \| 0.9729 \| 0.9705 \| 0.9717 \| 0.9889 \|
	\| 0.0171 \| 4.64 \| 15900 \| 0.0300 \| 0.9725 \| 0.9713 \| 0.9719 \| 0.9890 \|
	\| 0.017 \| 4.73 \| 16200 \| 0.0296 \| 0.9712 \| 0.9710 \| 0.9711 \| 0.9888 \|
	\| 0.017 \| 4.82 \| 16500 \| 0.0295 \| 0.9726 \| 0.9707 \| 0.9717 \| 0.9890 \|
	\| 0.0168 \| 4.9 \| 16800 \| 0.0297 \| 0.9730 \| 0.9711 \| 0.9721 \| 0.9891 \|
	\| 0.0166 \| 4.99 \| 17100 \| 0.0293 \| 0.9731 \| 0.9711 \| 0.9721 \| 0.9891 \|


	### Framework versions

	- Transformers 4.39.3
	- Pytorch 2.2.0a0+6a974be
	- Datasets 2.18.0
	- Tokenizers 0.15.2

	---
	license: apache-2.0
	base_model: google-bert/bert-base-uncased
	tags:
	- generated_from_trainer
	metrics:
	- precision
	- recall
	- f1
	- accuracy
	model-index:
	- name: 20240402140914_big_aristotle
	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. -->

	# 20240402140914_big_aristotle

	This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.0293
	- Precision: 0.9731
	- Recall: 0.9711
	- F1: 0.9721
	- Accuracy: 0.9891

	## 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: 0.0005
	- train_batch_size: 32
	- eval_batch_size: 32
	- seed: 69
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 256
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- lr_scheduler_warmup_steps: 350
	- num_epochs: 5

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \|
	\|:-------------:\|:-----:\|:-----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\|
	\| 0.0654 \| 0.09 \| 300 \| 0.0495 \| 0.9535 \| 0.9462 \| 0.9498 \| 0.9808 \|
	\| 0.0647 \| 0.18 \| 600 \| 0.0489 \| 0.9529 \| 0.9470 \| 0.9499 \| 0.9807 \|
	\| 0.0626 \| 0.26 \| 900 \| 0.0486 \| 0.9542 \| 0.9448 \| 0.9495 \| 0.9807 \|
	\| 0.0613 \| 0.35 \| 1200 \| 0.0460 \| 0.9544 \| 0.9501 \| 0.9522 \| 0.9815 \|
	\| 0.0623 \| 0.44 \| 1500 \| 0.0469 \| 0.9538 \| 0.9493 \| 0.9515 \| 0.9814 \|
	\| 0.0573 \| 0.53 \| 1800 \| 0.0455 \| 0.9552 \| 0.9488 \| 0.9520 \| 0.9816 \|
	\| 0.0569 \| 0.61 \| 2100 \| 0.0447 \| 0.9528 \| 0.9540 \| 0.9534 \| 0.9819 \|
	\| 0.0585 \| 0.7 \| 2400 \| 0.0464 \| 0.9566 \| 0.9468 \| 0.9516 \| 0.9815 \|
	\| 0.056 \| 0.79 \| 2700 \| 0.0452 \| 0.9555 \| 0.9517 \| 0.9536 \| 0.9822 \|
	\| 0.0564 \| 0.88 \| 3000 \| 0.0430 \| 0.9591 \| 0.9512 \| 0.9551 \| 0.9828 \|
	\| 0.0552 \| 0.96 \| 3300 \| 0.0433 \| 0.9548 \| 0.9532 \| 0.9540 \| 0.9825 \|
	\| 0.048 \| 1.05 \| 3600 \| 0.0444 \| 0.9579 \| 0.9529 \| 0.9554 \| 0.9828 \|
	\| 0.0483 \| 1.14 \| 3900 \| 0.0415 \| 0.9582 \| 0.9553 \| 0.9568 \| 0.9831 \|
	\| 0.0465 \| 1.23 \| 4200 \| 0.0424 \| 0.9622 \| 0.9495 \| 0.9558 \| 0.9831 \|
	\| 0.0465 \| 1.31 \| 4500 \| 0.0415 \| 0.9616 \| 0.9514 \| 0.9565 \| 0.9835 \|
	\| 0.0462 \| 1.4 \| 4800 \| 0.0407 \| 0.9588 \| 0.9534 \| 0.9561 \| 0.9835 \|
	\| 0.0467 \| 1.49 \| 5100 \| 0.0403 \| 0.9582 \| 0.9581 \| 0.9581 \| 0.9836 \|
	\| 0.0453 \| 1.58 \| 5400 \| 0.0405 \| 0.9636 \| 0.9513 \| 0.9574 \| 0.9839 \|
	\| 0.0446 \| 1.66 \| 5700 \| 0.0383 \| 0.9637 \| 0.9555 \| 0.9596 \| 0.9847 \|
	\| 0.0443 \| 1.75 \| 6000 \| 0.0382 \| 0.9596 \| 0.9572 \| 0.9584 \| 0.9844 \|
	\| 0.0432 \| 1.84 \| 6300 \| 0.0373 \| 0.9637 \| 0.9573 \| 0.9605 \| 0.9847 \|
	\| 0.0424 \| 1.93 \| 6600 \| 0.0368 \| 0.9674 \| 0.9516 \| 0.9594 \| 0.9850 \|
	\| 0.0364 \| 2.01 \| 6900 \| 0.0361 \| 0.9633 \| 0.9570 \| 0.9601 \| 0.9851 \|
	\| 0.0358 \| 2.1 \| 7200 \| 0.0366 \| 0.9618 \| 0.9613 \| 0.9615 \| 0.9853 \|
	\| 0.0359 \| 2.19 \| 7500 \| 0.0370 \| 0.9665 \| 0.9561 \| 0.9613 \| 0.9852 \|
	\| 0.036 \| 2.28 \| 7800 \| 0.0360 \| 0.9660 \| 0.9564 \| 0.9611 \| 0.9853 \|
	\| 0.0352 \| 2.36 \| 8100 \| 0.0355 \| 0.9658 \| 0.9602 \| 0.9630 \| 0.9856 \|
	\| 0.0354 \| 2.45 \| 8400 \| 0.0354 \| 0.9682 \| 0.9579 \| 0.9630 \| 0.9860 \|
	\| 0.0347 \| 2.54 \| 8700 \| 0.0347 \| 0.9694 \| 0.9566 \| 0.9630 \| 0.9861 \|
	\| 0.0347 \| 2.63 \| 9000 \| 0.0340 \| 0.9676 \| 0.9597 \| 0.9636 \| 0.9864 \|
	\| 0.0338 \| 2.71 \| 9300 \| 0.0327 \| 0.9682 \| 0.9626 \| 0.9654 \| 0.9867 \|
	\| 0.0338 \| 2.8 \| 9600 \| 0.0334 \| 0.9681 \| 0.9627 \| 0.9654 \| 0.9865 \|
	\| 0.033 \| 2.89 \| 9900 \| 0.0325 \| 0.9705 \| 0.9613 \| 0.9659 \| 0.9870 \|
	\| 0.0326 \| 2.98 \| 10200 \| 0.0331 \| 0.9686 \| 0.9640 \| 0.9663 \| 0.9870 \|
	\| 0.0264 \| 3.06 \| 10500 \| 0.0352 \| 0.9689 \| 0.9651 \| 0.9670 \| 0.9871 \|
	\| 0.0261 \| 3.15 \| 10800 \| 0.0329 \| 0.9698 \| 0.9633 \| 0.9666 \| 0.9871 \|
	\| 0.026 \| 3.24 \| 11100 \| 0.0328 \| 0.9672 \| 0.9662 \| 0.9667 \| 0.9872 \|
	\| 0.0261 \| 3.33 \| 11400 \| 0.0333 \| 0.9678 \| 0.9681 \| 0.9680 \| 0.9872 \|
	\| 0.0264 \| 3.41 \| 11700 \| 0.0326 \| 0.9689 \| 0.9676 \| 0.9682 \| 0.9875 \|
	\| 0.0258 \| 3.5 \| 12000 \| 0.0313 \| 0.9717 \| 0.9643 \| 0.9680 \| 0.9877 \|
	\| 0.0254 \| 3.59 \| 12300 \| 0.0307 \| 0.9691 \| 0.9675 \| 0.9683 \| 0.9880 \|
	\| 0.0249 \| 3.68 \| 12600 \| 0.0304 \| 0.9720 \| 0.9666 \| 0.9693 \| 0.9881 \|
	\| 0.025 \| 3.76 \| 12900 \| 0.0300 \| 0.9686 \| 0.9680 \| 0.9683 \| 0.9882 \|
	\| 0.0242 \| 3.85 \| 13200 \| 0.0297 \| 0.9682 \| 0.9682 \| 0.9682 \| 0.9881 \|
	\| 0.0246 \| 3.94 \| 13500 \| 0.0291 \| 0.9725 \| 0.9655 \| 0.9690 \| 0.9883 \|
	\| 0.0184 \| 4.03 \| 13800 \| 0.0320 \| 0.9712 \| 0.9678 \| 0.9695 \| 0.9882 \|
	\| 0.0186 \| 4.11 \| 14100 \| 0.0311 \| 0.9703 \| 0.9688 \| 0.9696 \| 0.9883 \|
	\| 0.0183 \| 4.2 \| 14400 \| 0.0319 \| 0.9718 \| 0.9696 \| 0.9707 \| 0.9886 \|
	\| 0.0181 \| 4.29 \| 14700 \| 0.0312 \| 0.9730 \| 0.9673 \| 0.9702 \| 0.9885 \|
	\| 0.0181 \| 4.38 \| 15000 \| 0.0308 \| 0.9694 \| 0.9698 \| 0.9696 \| 0.9885 \|
	\| 0.0178 \| 4.47 \| 15300 \| 0.0302 \| 0.9727 \| 0.9698 \| 0.9712 \| 0.9888 \|
	\| 0.0175 \| 4.55 \| 15600 \| 0.0300 \| 0.9729 \| 0.9705 \| 0.9717 \| 0.9889 \|
	\| 0.0171 \| 4.64 \| 15900 \| 0.0300 \| 0.9725 \| 0.9713 \| 0.9719 \| 0.9890 \|
	\| 0.017 \| 4.73 \| 16200 \| 0.0296 \| 0.9712 \| 0.9710 \| 0.9711 \| 0.9888 \|
	\| 0.017 \| 4.82 \| 16500 \| 0.0295 \| 0.9726 \| 0.9707 \| 0.9717 \| 0.9890 \|
	\| 0.0168 \| 4.9 \| 16800 \| 0.0297 \| 0.9730 \| 0.9711 \| 0.9721 \| 0.9891 \|
	\| 0.0166 \| 4.99 \| 17100 \| 0.0293 \| 0.9731 \| 0.9711 \| 0.9721 \| 0.9891 \|


	### Framework versions

	- Transformers 4.39.3
	- Pytorch 2.2.0a0+6a974be
	- Datasets 2.18.0
	- Tokenizers 0.15.2