|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- massive |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: hs768-nh16-nl8_custom |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: massive |
|
type: massive |
|
config: en-US |
|
split: validation |
|
args: en-US |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6254203093476799 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# hs768-nh16-nl8_custom |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the massive dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4879 |
|
- Accuracy: 0.6254 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 3.6661 | 0.35 | 500 | 2.8486 | 0.2991 | |
|
| 2.1334 | 0.69 | 1000 | 1.5131 | 0.6188 | |
|
| 1.5765 | 1.04 | 1500 | 1.4220 | 0.6434 | |
|
| 1.43 | 1.39 | 2000 | 1.5366 | 0.5839 | |
|
| 1.6168 | 1.74 | 2500 | 1.4929 | 0.5878 | |
|
| 1.5878 | 2.08 | 3000 | 1.8057 | 0.5957 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.0 |
|
|
