|
--- |
|
license: mit |
|
base_model: prajjwal1/bert-tiny |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: Merged-MM-praj |
|
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. --> |
|
|
|
# Merged-MM-praj |
|
|
|
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5525 |
|
- Accuracy: 0.7777 |
|
- F1: 0.8749 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.0 | 50 | 0.6929 | 0.526 | 0.3813 | |
|
| No log | 0.0 | 100 | 0.6938 | 0.48 | 0.3125 | |
|
| No log | 0.01 | 150 | 0.6971 | 0.479 | 0.3103 | |
|
| No log | 0.01 | 200 | 0.6948 | 0.479 | 0.3103 | |
|
| No log | 0.01 | 250 | 0.6938 | 0.479 | 0.3103 | |
|
| No log | 0.01 | 300 | 0.6939 | 0.479 | 0.3103 | |
|
| No log | 0.01 | 350 | 0.6927 | 0.521 | 0.3587 | |
|
| No log | 0.02 | 400 | 0.6931 | 0.501 | 0.4988 | |
|
| No log | 0.02 | 450 | 0.6944 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.02 | 500 | 0.6954 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.02 | 550 | 0.6960 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.02 | 600 | 0.6934 | 0.486 | 0.3322 | |
|
| 0.6942 | 0.02 | 650 | 0.6970 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.03 | 700 | 0.6929 | 0.535 | 0.4767 | |
|
| 0.6942 | 0.03 | 750 | 0.6931 | 0.499 | 0.4609 | |
|
| 0.6942 | 0.03 | 800 | 0.6952 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.03 | 850 | 0.6933 | 0.48 | 0.3160 | |
|
| 0.6942 | 0.03 | 900 | 0.6979 | 0.479 | 0.3103 | |
|
| 0.6942 | 0.04 | 950 | 0.6940 | 0.479 | 0.3103 | |
|
| 0.6938 | 0.04 | 1000 | 0.6915 | 0.521 | 0.3569 | |
|
| 0.6938 | 0.04 | 1050 | 0.6942 | 0.479 | 0.3103 | |
|
| 0.6938 | 0.04 | 1100 | 0.6884 | 0.519 | 0.3630 | |
|
| 0.6938 | 0.04 | 1150 | 0.6849 | 0.596 | 0.5817 | |
|
| 0.6938 | 0.05 | 1200 | 0.6849 | 0.547 | 0.5131 | |
|
| 0.6938 | 0.05 | 1250 | 0.6771 | 0.568 | 0.5502 | |
|
| 0.6938 | 0.05 | 1300 | 0.6792 | 0.572 | 0.5558 | |
|
| 0.6938 | 0.05 | 1350 | 0.6889 | 0.55 | 0.5161 | |
|
| 0.6938 | 0.05 | 1400 | 0.6792 | 0.59 | 0.5828 | |
|
| 0.6938 | 0.06 | 1450 | 0.6729 | 0.602 | 0.5987 | |
|
| 0.6781 | 0.06 | 1500 | 0.6702 | 0.592 | 0.5822 | |
|
| 0.6781 | 0.06 | 1550 | 0.6711 | 0.578 | 0.5633 | |
|
| 0.6781 | 0.06 | 1600 | 0.6642 | 0.607 | 0.6024 | |
|
| 0.6781 | 0.06 | 1650 | 0.6624 | 0.592 | 0.5819 | |
|
| 0.6781 | 0.07 | 1700 | 0.6585 | 0.595 | 0.5883 | |
|
| 0.6781 | 0.07 | 1750 | 0.6543 | 0.584 | 0.5740 | |
|
| 0.6781 | 0.07 | 1800 | 0.6452 | 0.6 | 0.5926 | |
|
| 0.6781 | 0.07 | 1850 | 0.6355 | 0.615 | 0.6106 | |
|
| 0.6781 | 0.07 | 1900 | 0.6280 | 0.615 | 0.6090 | |
|
| 0.6781 | 0.07 | 1950 | 0.6209 | 0.621 | 0.6139 | |
|
| 0.6465 | 0.08 | 2000 | 0.6178 | 0.632 | 0.6247 | |
|
| 0.6465 | 0.08 | 2050 | 0.6133 | 0.641 | 0.6303 | |
|
| 0.6465 | 0.08 | 2100 | 0.6132 | 0.629 | 0.6218 | |
|
| 0.6465 | 0.08 | 2150 | 0.6155 | 0.63 | 0.6289 | |
|
| 0.6465 | 0.08 | 2200 | 0.5984 | 0.635 | 0.6322 | |
|
| 0.6465 | 0.09 | 2250 | 0.6065 | 0.633 | 0.6102 | |
|
| 0.6465 | 0.09 | 2300 | 0.5968 | 0.629 | 0.6063 | |
|
| 0.6465 | 0.09 | 2350 | 0.5871 | 0.649 | 0.6411 | |
|
| 0.6465 | 0.09 | 2400 | 0.5824 | 0.64 | 0.6218 | |
|
| 0.6465 | 0.09 | 2450 | 0.5812 | 0.643 | 0.6390 | |
|
| 0.6042 | 0.1 | 2500 | 0.5790 | 0.644 | 0.6355 | |
|
| 0.6042 | 0.1 | 2550 | 0.5744 | 0.654 | 0.6507 | |
|
| 0.6042 | 0.1 | 2600 | 0.5679 | 0.641 | 0.6292 | |
|
| 0.6042 | 0.1 | 2650 | 0.5707 | 0.644 | 0.6311 | |
|
| 0.6042 | 0.1 | 2700 | 0.5707 | 0.652 | 0.6439 | |
|
| 0.6042 | 0.11 | 2750 | 0.5680 | 0.661 | 0.6569 | |
|
| 0.6042 | 0.11 | 2800 | 0.5592 | 0.67 | 0.6684 | |
|
| 0.6042 | 0.11 | 2850 | 0.5557 | 0.678 | 0.6758 | |
|
| 0.6042 | 0.11 | 2900 | 0.5579 | 0.671 | 0.6690 | |
|
| 0.6042 | 0.11 | 2950 | 0.5490 | 0.692 | 0.6909 | |
|
| 0.5834 | 0.11 | 3000 | 0.5474 | 0.688 | 0.6858 | |
|
| 0.5834 | 0.12 | 3050 | 0.5447 | 0.696 | 0.6902 | |
|
| 0.5834 | 0.12 | 3100 | 0.5456 | 0.699 | 0.6985 | |
|
| 0.5834 | 0.12 | 3150 | 0.5592 | 0.675 | 0.6628 | |
|
| 0.5834 | 0.12 | 3200 | 0.5442 | 0.69 | 0.6856 | |
|
| 0.5834 | 0.12 | 3250 | 0.5424 | 0.698 | 0.6974 | |
|
| 0.5834 | 0.13 | 3300 | 0.5464 | 0.691 | 0.6907 | |
|
| 0.5834 | 0.13 | 3350 | 0.5433 | 0.693 | 0.6922 | |
|
| 0.5834 | 0.13 | 3400 | 0.5400 | 0.746 | 0.7461 | |
|
| 0.5834 | 0.13 | 3450 | 0.5406 | 0.712 | 0.7091 | |
|
| 0.5551 | 0.13 | 3500 | 0.5367 | 0.738 | 0.7376 | |
|
| 0.5551 | 0.14 | 3550 | 0.5354 | 0.713 | 0.7091 | |
|
| 0.5551 | 0.14 | 3600 | 0.5377 | 0.74 | 0.7400 | |
|
| 0.5551 | 0.14 | 3650 | 0.5342 | 0.751 | 0.7506 | |
|
| 0.5551 | 0.14 | 3700 | 0.5386 | 0.701 | 0.6992 | |
|
| 0.5551 | 0.14 | 3750 | 0.5395 | 0.737 | 0.7368 | |
|
| 0.5551 | 0.15 | 3800 | 0.5333 | 0.733 | 0.7330 | |
|
| 0.5551 | 0.15 | 3850 | 0.5245 | 0.737 | 0.7371 | |
|
| 0.5551 | 0.15 | 3900 | 0.5236 | 0.745 | 0.7451 | |
|
| 0.5551 | 0.15 | 3950 | 0.5149 | 0.741 | 0.7400 | |
|
| 0.5508 | 0.15 | 4000 | 0.5208 | 0.743 | 0.7422 | |
|
| 0.5508 | 0.16 | 4050 | 0.5109 | 0.744 | 0.7440 | |
|
| 0.5508 | 0.16 | 4100 | 0.5179 | 0.742 | 0.7398 | |
|
| 0.5508 | 0.16 | 4150 | 0.5133 | 0.75 | 0.7499 | |
|
| 0.5508 | 0.16 | 4200 | 0.5110 | 0.744 | 0.7416 | |
|
| 0.5508 | 0.16 | 4250 | 0.5133 | 0.749 | 0.7476 | |
|
| 0.5508 | 0.16 | 4300 | 0.5075 | 0.743 | 0.7410 | |
|
| 0.5508 | 0.17 | 4350 | 0.5108 | 0.755 | 0.7544 | |
|
| 0.5508 | 0.17 | 4400 | 0.5051 | 0.747 | 0.7465 | |
|
| 0.5508 | 0.17 | 4450 | 0.5064 | 0.746 | 0.7455 | |
|
| 0.5362 | 0.17 | 4500 | 0.5030 | 0.744 | 0.7441 | |
|
| 0.5362 | 0.17 | 4550 | 0.5043 | 0.748 | 0.7476 | |
|
| 0.5362 | 0.18 | 4600 | 0.5010 | 0.753 | 0.7531 | |
|
| 0.5362 | 0.18 | 4650 | 0.4988 | 0.762 | 0.7616 | |
|
| 0.5362 | 0.18 | 4700 | 0.4999 | 0.755 | 0.7548 | |
|
| 0.5362 | 0.18 | 4750 | 0.5159 | 0.754 | 0.7529 | |
|
| 0.5362 | 0.18 | 4800 | 0.4924 | 0.764 | 0.7639 | |
|
| 0.5362 | 0.19 | 4850 | 0.4935 | 0.755 | 0.7549 | |
|
| 0.5362 | 0.19 | 4900 | 0.4874 | 0.76 | 0.7601 | |
|
| 0.5362 | 0.19 | 4950 | 0.4859 | 0.759 | 0.7591 | |
|
| 0.5226 | 0.19 | 5000 | 0.4901 | 0.761 | 0.7610 | |
|
| 0.5226 | 0.19 | 5050 | 0.4740 | 0.779 | 0.7790 | |
|
| 0.5226 | 0.2 | 5100 | 0.4799 | 0.783 | 0.7831 | |
|
| 0.5226 | 0.2 | 5150 | 0.4833 | 0.771 | 0.7698 | |
|
| 0.5226 | 0.2 | 5200 | 0.4879 | 0.759 | 0.7561 | |
|
| 0.5226 | 0.2 | 5250 | 0.4812 | 0.772 | 0.7719 | |
|
| 0.5226 | 0.2 | 5300 | 0.4825 | 0.772 | 0.7715 | |
|
| 0.5226 | 0.2 | 5350 | 0.4791 | 0.775 | 0.7744 | |
|
| 0.5226 | 0.21 | 5400 | 0.4749 | 0.773 | 0.7729 | |
|
| 0.5226 | 0.21 | 5450 | 0.4691 | 0.782 | 0.7811 | |
|
| 0.5055 | 0.21 | 5500 | 0.4752 | 0.78 | 0.7791 | |
|
| 0.5055 | 0.21 | 5550 | 0.4621 | 0.766 | 0.7645 | |
|
| 0.5055 | 0.21 | 5600 | 0.4628 | 0.779 | 0.7790 | |
|
| 0.5055 | 0.22 | 5650 | 0.4543 | 0.776 | 0.7760 | |
|
| 0.5055 | 0.22 | 5700 | 0.4548 | 0.786 | 0.7861 | |
|
| 0.5055 | 0.22 | 5750 | 0.4578 | 0.777 | 0.7763 | |
|
| 0.5055 | 0.22 | 5800 | 0.4684 | 0.778 | 0.7780 | |
|
| 0.5055 | 0.22 | 5850 | 0.4626 | 0.775 | 0.7751 | |
|
| 0.5055 | 0.23 | 5900 | 0.4714 | 0.785 | 0.7850 | |
|
| 0.5055 | 0.23 | 5950 | 0.4514 | 0.79 | 0.7896 | |
|
| 0.4985 | 0.23 | 6000 | 0.4541 | 0.773 | 0.7731 | |
|
| 0.4985 | 0.23 | 6050 | 0.4587 | 0.788 | 0.7876 | |
|
| 0.4985 | 0.23 | 6100 | 0.4523 | 0.787 | 0.7867 | |
|
| 0.4985 | 0.24 | 6150 | 0.4441 | 0.787 | 0.7870 | |
|
| 0.4985 | 0.24 | 6200 | 0.4529 | 0.784 | 0.7841 | |
|
| 0.4985 | 0.24 | 6250 | 0.4512 | 0.784 | 0.7840 | |
|
| 0.4985 | 0.24 | 6300 | 0.4545 | 0.777 | 0.7757 | |
|
| 0.4985 | 0.24 | 6350 | 0.4399 | 0.788 | 0.7874 | |
|
| 0.4985 | 0.25 | 6400 | 0.4478 | 0.794 | 0.7939 | |
|
| 0.4985 | 0.25 | 6450 | 0.4495 | 0.793 | 0.7930 | |
|
| 0.4937 | 0.25 | 6500 | 0.4454 | 0.792 | 0.7913 | |
|
| 0.4937 | 0.25 | 6550 | 0.4438 | 0.795 | 0.7950 | |
|
| 0.4937 | 0.25 | 6600 | 0.4476 | 0.795 | 0.7948 | |
|
| 0.4937 | 0.25 | 6650 | 0.4448 | 0.794 | 0.7939 | |
|
| 0.4937 | 0.26 | 6700 | 0.4472 | 0.791 | 0.7911 | |
|
| 0.4937 | 0.26 | 6750 | 0.4431 | 0.793 | 0.7924 | |
|
| 0.4937 | 0.26 | 6800 | 0.4434 | 0.796 | 0.7958 | |
|
| 0.4937 | 0.26 | 6850 | 0.4340 | 0.802 | 0.802 | |
|
| 0.4937 | 0.26 | 6900 | 0.4502 | 0.786 | 0.7848 | |
|
| 0.4937 | 0.27 | 6950 | 0.4349 | 0.797 | 0.7964 | |
|
| 0.4826 | 0.27 | 7000 | 0.4348 | 0.79 | 0.7894 | |
|
| 0.4826 | 0.27 | 7050 | 0.4321 | 0.788 | 0.7875 | |
|
| 0.4826 | 0.27 | 7100 | 0.4300 | 0.787 | 0.7868 | |
|
| 0.4826 | 0.27 | 7150 | 0.4346 | 0.78 | 0.7779 | |
|
| 0.4826 | 0.28 | 7200 | 0.4246 | 0.802 | 0.8020 | |
|
| 0.4826 | 0.28 | 7250 | 0.4273 | 0.793 | 0.7930 | |
|
| 0.4826 | 0.28 | 7300 | 0.4346 | 0.79 | 0.7894 | |
|
| 0.4826 | 0.28 | 7350 | 0.4358 | 0.789 | 0.7887 | |
|
| 0.4826 | 0.28 | 7400 | 0.4368 | 0.788 | 0.7871 | |
|
| 0.4826 | 0.29 | 7450 | 0.4426 | 0.784 | 0.7841 | |
|
| 0.4756 | 0.29 | 7500 | 0.4312 | 0.802 | 0.8019 | |
|
| 0.4756 | 0.29 | 7550 | 0.4303 | 0.795 | 0.7944 | |
|
| 0.4756 | 0.29 | 7600 | 0.4391 | 0.792 | 0.7916 | |
|
| 0.4756 | 0.29 | 7650 | 0.4325 | 0.793 | 0.7922 | |
|
| 0.4756 | 0.29 | 7700 | 0.4283 | 0.793 | 0.7920 | |
|
| 0.4756 | 0.3 | 7750 | 0.4271 | 0.799 | 0.7991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
