|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-base_sst2_dense_epochs-8 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: glue |
|
type: glue |
|
config: sst2 |
|
split: validation |
|
args: sst2 |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9231651376146789 |
|
--- |
|
|
|
<!-- 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-base_sst2_dense_epochs-8 |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2179 |
|
- Accuracy: 0.9232 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 64 |
|
- seed: 0 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 20 |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6384 | 0.02 | 50 | 0.6360 | 0.7064 | |
|
| 0.3416 | 0.05 | 100 | 0.2955 | 0.8922 | |
|
| 0.29 | 0.07 | 150 | 0.2512 | 0.9094 | |
|
| 0.2371 | 0.1 | 200 | 0.2511 | 0.9106 | |
|
| 0.2059 | 0.12 | 250 | 0.2379 | 0.9174 | |
|
| 0.2617 | 0.14 | 300 | 0.2299 | 0.9174 | |
|
| 0.2266 | 0.17 | 350 | 0.2190 | 0.9243 | |
|
| 0.2288 | 0.19 | 400 | 0.2292 | 0.9255 | |
|
| 0.2385 | 0.21 | 450 | 0.2263 | 0.9232 | |
|
| 0.161 | 0.24 | 500 | 0.2368 | 0.9243 | |
|
| 0.158 | 0.26 | 550 | 0.2411 | 0.9174 | |
|
| 0.2469 | 0.29 | 600 | 0.2381 | 0.9209 | |
|
| 0.2417 | 0.31 | 650 | 0.2349 | 0.9163 | |
|
| 0.1614 | 0.33 | 700 | 0.2251 | 0.9174 | |
|
| 0.2764 | 0.36 | 750 | 0.2129 | 0.9266 | |
|
| 0.1499 | 0.38 | 800 | 0.2248 | 0.9197 | |
|
| 0.1376 | 0.4 | 850 | 0.2285 | 0.9232 | |
|
| 0.1875 | 0.43 | 900 | 0.2324 | 0.9312 | |
|
| 0.1819 | 0.45 | 950 | 0.2302 | 0.9220 | |
|
| 0.2373 | 0.48 | 1000 | 0.2179 | 0.9232 | |
|
| 0.0956 | 0.5 | 1050 | 0.2077 | 0.9278 | |
|
| 0.2396 | 0.52 | 1100 | 0.3249 | 0.9266 | |
|
| 0.2543 | 0.55 | 1150 | 0.4440 | 0.9243 | |
|
| 0.0942 | 0.57 | 1200 | 0.1982 | 0.9312 | |
|
| 0.1296 | 0.59 | 1250 | 0.4270 | 0.9335 | |
|
| 0.1618 | 0.62 | 1300 | 0.1893 | 0.9392 | |
|
| 0.1902 | 0.64 | 1350 | 0.1911 | 0.9381 | |
|
| 0.1234 | 0.67 | 1400 | 0.1903 | 0.9346 | |
|
| 0.1369 | 0.69 | 1450 | 0.4157 | 0.9335 | |
|
| 0.1149 | 0.71 | 1500 | 0.4121 | 0.9323 | |
|
| 0.1501 | 0.74 | 1550 | 0.6343 | 0.9358 | |
|
| 0.1679 | 0.76 | 1600 | 0.5294 | 0.9323 | |
|
| 0.1462 | 0.78 | 1650 | 0.4037 | 0.9392 | |
|
| 0.2111 | 0.81 | 1700 | 0.4094 | 0.9323 | |
|
| 0.0902 | 0.83 | 1750 | 0.4094 | 0.9346 | |
|
| 0.1185 | 0.86 | 1800 | 0.4059 | 0.9323 | |
|
| 0.1602 | 0.88 | 1850 | 0.2946 | 0.9323 | |
|
| 0.1212 | 0.9 | 1900 | 0.3037 | 0.9312 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.14.1 |
|
|
