|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: source-type-model |
|
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. --> |
|
|
|
# source-type-model |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7162 |
|
- F1: 0.4315 |
|
|
|
## 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: 5 |
|
- eval_batch_size: 5 |
|
- seed: 42 |
|
- 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 | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| No log | 0.12 | 100 | 1.3490 | 0.0956 | |
|
| No log | 0.25 | 200 | 1.4751 | 0.0956 | |
|
| No log | 0.37 | 300 | 0.9687 | 0.2427 | |
|
| No log | 0.49 | 400 | 1.0625 | 0.1891 | |
|
| 1.2336 | 0.62 | 500 | 1.0954 | 0.1949 | |
|
| 1.2336 | 0.74 | 600 | 0.9969 | 0.3080 | |
|
| 1.2336 | 0.86 | 700 | 0.9171 | 0.3175 | |
|
| 1.2336 | 0.99 | 800 | 0.9600 | 0.3136 | |
|
| 1.2336 | 1.11 | 900 | 0.9637 | 0.3161 | |
|
| 1.0269 | 1.23 | 1000 | 0.9592 | 0.3257 | |
|
| 1.0269 | 1.35 | 1100 | 0.9117 | 0.3342 | |
|
| 1.0269 | 1.48 | 1200 | 0.8891 | 0.3205 | |
|
| 1.0269 | 1.6 | 1300 | 0.8136 | 0.3375 | |
|
| 1.0269 | 1.72 | 1400 | 0.9676 | 0.3300 | |
|
| 0.8592 | 1.85 | 1500 | 0.8778 | 0.3316 | |
|
| 0.8592 | 1.97 | 1600 | 0.8407 | 0.3379 | |
|
| 0.8592 | 2.09 | 1700 | 0.8409 | 0.3369 | |
|
| 0.8592 | 2.22 | 1800 | 0.8818 | 0.3343 | |
|
| 0.8592 | 2.34 | 1900 | 0.9259 | 0.3386 | |
|
| 0.7521 | 2.46 | 2000 | 0.9419 | 0.3380 | |
|
| 0.7521 | 2.59 | 2100 | 0.8050 | 0.3474 | |
|
| 0.7521 | 2.71 | 2200 | 0.7773 | 0.4053 | |
|
| 0.7521 | 2.83 | 2300 | 0.7114 | 0.4337 | |
|
| 0.7521 | 2.96 | 2400 | 0.7162 | 0.4315 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
