|
--- |
|
license: mit |
|
base_model: VietAI/vit5-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: T5_fine_tune |
|
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. --> |
|
|
|
# T5_fine_tune |
|
|
|
This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0439 |
|
- Score: 42.2142 |
|
- Counts: [2084, 1925, 1770, 1616] |
|
- Totals: [2111, 1964, 1817, 1670] |
|
- Precisions: [98.72098531501658, 98.0142566191446, 97.41331865712714, 96.76646706586827] |
|
- Bp: 0.4320 |
|
- Sys Len: 2111 |
|
- Ref Len: 3883 |
|
|
|
## 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: 2e-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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Score | Counts | Totals | Precisions | Bp | Sys Len | Ref Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------------------:|:------------------------:|:----------------------------------------------------------------------------:|:------:|:-------:|:-------:| |
|
| No log | 1.0 | 71 | 0.3049 | 34.8561 | [1920, 1622, 1384, 1161] | [2160, 2013, 1866, 1719] | [88.88888888888889, 80.57625434674615, 74.16934619506966, 67.53926701570681] | 0.4504 | 2160 | 3883 | |
|
| No log | 2.0 | 142 | 0.2064 | 37.7340 | [1984, 1738, 1528, 1321] | [2150, 2003, 1856, 1709] | [92.27906976744185, 86.76984523215177, 82.32758620689656, 77.29666471620831] | 0.4466 | 2150 | 3883 | |
|
| No log | 3.0 | 213 | 0.1438 | 39.7849 | [2029, 1813, 1629, 1452] | [2141, 1994, 1847, 1700] | [94.76879962634283, 90.92276830491474, 88.19707634001082, 85.41176470588235] | 0.4432 | 2141 | 3883 | |
|
| No log | 4.0 | 284 | 0.1157 | 40.8740 | [2050, 1864, 1693, 1524] | [2128, 1981, 1834, 1687] | [96.33458646616542, 94.09389197375063, 92.31188658669575, 90.33787788974512] | 0.4384 | 2128 | 3883 | |
|
| No log | 5.0 | 355 | 0.0860 | 41.2231 | [2066, 1889, 1722, 1559] | [2108, 1961, 1814, 1667] | [98.00759013282732, 96.32840387557368, 94.92833517089305, 93.52129574085183] | 0.4308 | 2108 | 3883 | |
|
| No log | 6.0 | 426 | 0.0727 | 41.5588 | [2068, 1897, 1738, 1583] | [2110, 1963, 1816, 1669] | [98.00947867298578, 96.63779928680592, 95.70484581497797, 94.84721390053924] | 0.4316 | 2110 | 3883 | |
|
| No log | 7.0 | 497 | 0.0564 | 41.9034 | [2076, 1914, 1759, 1607] | [2105, 1958, 1811, 1664] | [98.62232779097387, 97.75280898876404, 97.12865819988956, 96.57451923076923] | 0.4297 | 2105 | 3883 | |
|
| 0.3736 | 8.0 | 568 | 0.0497 | 42.1238 | [2080, 1919, 1763, 1608] | [2115, 1968, 1821, 1674] | [98.3451536643026, 97.51016260162602, 96.81493684788578, 96.05734767025089] | 0.4335 | 2115 | 3883 | |
|
| 0.3736 | 9.0 | 639 | 0.0449 | 42.2673 | [2084, 1927, 1774, 1621] | [2110, 1963, 1816, 1669] | [98.76777251184834, 98.16607233825776, 97.68722466960352, 97.12402636309167] | 0.4316 | 2110 | 3883 | |
|
| 0.3736 | 10.0 | 710 | 0.0439 | 42.2142 | [2084, 1925, 1770, 1616] | [2111, 1964, 1817, 1670] | [98.72098531501658, 98.0142566191446, 97.41331865712714, 96.76646706586827] | 0.4320 | 2111 | 3883 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.0 |
|
|
