|
--- |
|
license: mit |
|
base_model: prajjwal1/bert-tiny |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: MM03 |
|
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. --> |
|
|
|
# MM03 |
|
|
|
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3682 |
|
- Accuracy: 0.85 |
|
- F1: 0.9189 |
|
|
|
## 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: 5e-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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.0 | 50 | 0.6923 | 0.53 | 0.3672 | |
|
| No log | 0.01 | 100 | 0.6938 | 0.47 | 0.3005 | |
|
| No log | 0.01 | 150 | 0.6914 | 0.53 | 0.3672 | |
|
| No log | 0.01 | 200 | 0.6934 | 0.45 | 0.3486 | |
|
| No log | 0.02 | 250 | 0.6900 | 0.53 | 0.3672 | |
|
| No log | 0.02 | 300 | 0.6910 | 0.53 | 0.3672 | |
|
| No log | 0.03 | 350 | 0.6910 | 0.57 | 0.5387 | |
|
| No log | 0.03 | 400 | 0.6898 | 0.53 | 0.3672 | |
|
| No log | 0.03 | 450 | 0.6943 | 0.47 | 0.3005 | |
|
| 0.6943 | 0.04 | 500 | 0.7011 | 0.47 | 0.3005 | |
|
| 0.6943 | 0.04 | 550 | 0.6920 | 0.56 | 0.56 | |
|
| 0.6943 | 0.04 | 600 | 0.6917 | 0.59 | 0.5765 | |
|
| 0.6943 | 0.05 | 650 | 0.6883 | 0.56 | 0.5252 | |
|
| 0.6943 | 0.05 | 700 | 0.6938 | 0.49 | 0.4896 | |
|
| 0.6943 | 0.06 | 750 | 0.6903 | 0.54 | 0.4655 | |
|
| 0.6943 | 0.06 | 800 | 0.6923 | 0.47 | 0.4686 | |
|
| 0.6943 | 0.06 | 850 | 0.6904 | 0.5 | 0.4992 | |
|
| 0.6943 | 0.07 | 900 | 0.6835 | 0.6 | 0.5684 | |
|
| 0.6943 | 0.07 | 950 | 0.6912 | 0.43 | 0.3752 | |
|
| 0.6881 | 0.07 | 1000 | 0.6634 | 0.61 | 0.5974 | |
|
| 0.6881 | 0.08 | 1050 | 0.6575 | 0.6 | 0.5935 | |
|
| 0.6881 | 0.08 | 1100 | 0.6431 | 0.68 | 0.6803 | |
|
| 0.6881 | 0.08 | 1150 | 0.6386 | 0.67 | 0.6691 | |
|
| 0.6881 | 0.09 | 1200 | 0.6290 | 0.63 | 0.6279 | |
|
| 0.6881 | 0.09 | 1250 | 0.6355 | 0.66 | 0.66 | |
|
| 0.6881 | 0.1 | 1300 | 0.6592 | 0.61 | 0.6078 | |
|
| 0.6881 | 0.1 | 1350 | 0.6443 | 0.66 | 0.6595 | |
|
| 0.6881 | 0.1 | 1400 | 0.6520 | 0.62 | 0.6194 | |
|
| 0.6881 | 0.11 | 1450 | 0.6636 | 0.58 | 0.5680 | |
|
| 0.6621 | 0.11 | 1500 | 0.6508 | 0.59 | 0.5844 | |
|
| 0.6621 | 0.11 | 1550 | 0.6373 | 0.61 | 0.6097 | |
|
| 0.6621 | 0.12 | 1600 | 0.6372 | 0.63 | 0.6280 | |
|
| 0.6621 | 0.12 | 1650 | 0.6499 | 0.6 | 0.5912 | |
|
| 0.6621 | 0.12 | 1700 | 0.6501 | 0.61 | 0.6047 | |
|
| 0.6621 | 0.13 | 1750 | 0.6390 | 0.62 | 0.6139 | |
|
| 0.6621 | 0.13 | 1800 | 0.6358 | 0.62 | 0.6139 | |
|
| 0.6621 | 0.14 | 1850 | 0.6245 | 0.65 | 0.6468 | |
|
| 0.6621 | 0.14 | 1900 | 0.6207 | 0.66 | 0.6575 | |
|
| 0.6621 | 0.14 | 1950 | 0.6185 | 0.69 | 0.6898 | |
|
| 0.6317 | 0.15 | 2000 | 0.6366 | 0.62 | 0.6139 | |
|
| 0.6317 | 0.15 | 2050 | 0.6155 | 0.64 | 0.6374 | |
|
| 0.6317 | 0.15 | 2100 | 0.6062 | 0.69 | 0.6902 | |
|
| 0.6317 | 0.16 | 2150 | 0.6040 | 0.66 | 0.6575 | |
|
| 0.6317 | 0.16 | 2200 | 0.5912 | 0.73 | 0.7298 | |
|
| 0.6317 | 0.17 | 2250 | 0.5861 | 0.72 | 0.7195 | |
|
| 0.6317 | 0.17 | 2300 | 0.5732 | 0.73 | 0.7302 | |
|
| 0.6317 | 0.17 | 2350 | 0.5695 | 0.74 | 0.7402 | |
|
| 0.6317 | 0.18 | 2400 | 0.5514 | 0.74 | 0.74 | |
|
| 0.6317 | 0.18 | 2450 | 0.5468 | 0.74 | 0.74 | |
|
| 0.6194 | 0.18 | 2500 | 0.5528 | 0.71 | 0.7101 | |
|
| 0.6194 | 0.19 | 2550 | 0.5562 | 0.68 | 0.6803 | |
|
| 0.6194 | 0.19 | 2600 | 0.5624 | 0.69 | 0.6903 | |
|
| 0.6194 | 0.19 | 2650 | 0.5505 | 0.72 | 0.72 | |
|
| 0.6194 | 0.2 | 2700 | 0.5429 | 0.74 | 0.7389 | |
|
| 0.6194 | 0.2 | 2750 | 0.5576 | 0.68 | 0.6803 | |
|
| 0.6194 | 0.21 | 2800 | 0.5424 | 0.71 | 0.7098 | |
|
| 0.6194 | 0.21 | 2850 | 0.5194 | 0.76 | 0.7590 | |
|
| 0.6194 | 0.21 | 2900 | 0.5321 | 0.75 | 0.7493 | |
|
| 0.6194 | 0.22 | 2950 | 0.5306 | 0.75 | 0.7493 | |
|
| 0.596 | 0.22 | 3000 | 0.5366 | 0.75 | 0.7477 | |
|
| 0.596 | 0.22 | 3050 | 0.5124 | 0.77 | 0.7679 | |
|
| 0.596 | 0.23 | 3100 | 0.5152 | 0.75 | 0.7465 | |
|
| 0.596 | 0.23 | 3150 | 0.5302 | 0.76 | 0.7573 | |
|
| 0.596 | 0.23 | 3200 | 0.5289 | 0.76 | 0.7582 | |
|
| 0.596 | 0.24 | 3250 | 0.5111 | 0.76 | 0.7573 | |
|
| 0.596 | 0.24 | 3300 | 0.5204 | 0.75 | 0.7477 | |
|
| 0.596 | 0.25 | 3350 | 0.5145 | 0.75 | 0.7477 | |
|
| 0.596 | 0.25 | 3400 | 0.5139 | 0.76 | 0.7561 | |
|
| 0.596 | 0.25 | 3450 | 0.4971 | 0.76 | 0.7561 | |
|
| 0.5746 | 0.26 | 3500 | 0.5048 | 0.74 | 0.7381 | |
|
| 0.5746 | 0.26 | 3550 | 0.5224 | 0.76 | 0.7590 | |
|
| 0.5746 | 0.26 | 3600 | 0.5077 | 0.76 | 0.76 | |
|
| 0.5746 | 0.27 | 3650 | 0.4803 | 0.79 | 0.7899 | |
|
| 0.5746 | 0.27 | 3700 | 0.4753 | 0.78 | 0.7802 | |
|
| 0.5746 | 0.28 | 3750 | 0.4684 | 0.79 | 0.7901 | |
|
| 0.5746 | 0.28 | 3800 | 0.4853 | 0.76 | 0.76 | |
|
| 0.5746 | 0.28 | 3850 | 0.5012 | 0.76 | 0.7602 | |
|
| 0.5746 | 0.29 | 3900 | 0.4905 | 0.77 | 0.7698 | |
|
| 0.5746 | 0.29 | 3950 | 0.4731 | 0.79 | 0.7899 | |
|
| 0.5246 | 0.29 | 4000 | 0.4616 | 0.8 | 0.7992 | |
|
| 0.5246 | 0.3 | 4050 | 0.4875 | 0.79 | 0.7902 | |
|
| 0.5246 | 0.3 | 4100 | 0.4560 | 0.78 | 0.7791 | |
|
| 0.5246 | 0.3 | 4150 | 0.4696 | 0.77 | 0.7694 | |
|
| 0.5246 | 0.31 | 4200 | 0.4457 | 0.78 | 0.7802 | |
|
| 0.5246 | 0.31 | 4250 | 0.4743 | 0.76 | 0.7596 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
