|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: flan_t5_small_ledgar |
|
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. --> |
|
|
|
# flan_t5_small_ledgar |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5534 |
|
- Accuracy: 0.8525 |
|
- F1 Macro: 0.7680 |
|
- F1 Micro: 0.8525 |
|
|
|
## 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: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.1741 | 0.11 | 100 | 1.6958 | 0.6204 | 0.3397 | 0.6204 | |
|
| 1.2325 | 0.21 | 200 | 1.0701 | 0.7302 | 0.5340 | 0.7302 | |
|
| 0.9558 | 0.32 | 300 | 0.8877 | 0.7713 | 0.6186 | 0.7713 | |
|
| 0.8635 | 0.43 | 400 | 0.8029 | 0.788 | 0.6469 | 0.788 | |
|
| 0.8667 | 0.53 | 500 | 0.7517 | 0.8035 | 0.6794 | 0.8035 | |
|
| 0.7975 | 0.64 | 600 | 0.7280 | 0.8031 | 0.6852 | 0.8031 | |
|
| 0.7511 | 0.75 | 700 | 0.7209 | 0.8124 | 0.6907 | 0.8124 | |
|
| 0.7683 | 0.85 | 800 | 0.6883 | 0.811 | 0.6968 | 0.811 | |
|
| 0.6874 | 0.96 | 900 | 0.6764 | 0.8137 | 0.7147 | 0.8137 | |
|
| 0.6042 | 1.07 | 1000 | 0.6628 | 0.8236 | 0.7097 | 0.8236 | |
|
| 0.6397 | 1.17 | 1100 | 0.6546 | 0.8233 | 0.7171 | 0.8233 | |
|
| 0.6584 | 1.28 | 1200 | 0.6371 | 0.831 | 0.7400 | 0.831 | |
|
| 0.5718 | 1.39 | 1300 | 0.6346 | 0.8295 | 0.7350 | 0.8295 | |
|
| 0.5012 | 1.49 | 1400 | 0.6176 | 0.8343 | 0.7446 | 0.8343 | |
|
| 0.5843 | 1.6 | 1500 | 0.6214 | 0.8331 | 0.7376 | 0.8331 | |
|
| 0.6021 | 1.71 | 1600 | 0.6024 | 0.8395 | 0.7455 | 0.8395 | |
|
| 0.5538 | 1.81 | 1700 | 0.5964 | 0.843 | 0.7516 | 0.843 | |
|
| 0.5391 | 1.92 | 1800 | 0.5835 | 0.8431 | 0.7590 | 0.8431 | |
|
| 0.4632 | 2.03 | 1900 | 0.5845 | 0.842 | 0.7432 | 0.842 | |
|
| 0.4581 | 2.13 | 2000 | 0.5832 | 0.8451 | 0.7575 | 0.8451 | |
|
| 0.4806 | 2.24 | 2100 | 0.5749 | 0.8444 | 0.7639 | 0.8444 | |
|
| 0.4438 | 2.35 | 2200 | 0.5704 | 0.85 | 0.7642 | 0.85 | |
|
| 0.4379 | 2.45 | 2300 | 0.5667 | 0.8486 | 0.7598 | 0.8486 | |
|
| 0.4342 | 2.56 | 2400 | 0.5614 | 0.8503 | 0.7642 | 0.8503 | |
|
| 0.4197 | 2.67 | 2500 | 0.5605 | 0.8527 | 0.7684 | 0.8527 | |
|
| 0.4417 | 2.77 | 2600 | 0.5568 | 0.8505 | 0.7652 | 0.8505 | |
|
| 0.4401 | 2.88 | 2700 | 0.5542 | 0.8529 | 0.7685 | 0.8529 | |
|
| 0.4666 | 2.99 | 2800 | 0.5534 | 0.8525 | 0.7680 | 0.8525 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
