|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: contradictions_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. --> |
|
|
|
# contradictions_model |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0973 |
|
- Accuracy: 0.3490 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.1191 | 0.07 | 100 | 1.1001 | 0.3177 | |
|
| 1.1041 | 0.15 | 200 | 1.0959 | 0.3490 | |
|
| 1.1081 | 0.22 | 300 | 1.0927 | 0.3993 | |
|
| 1.1031 | 0.29 | 400 | 1.1143 | 0.3350 | |
|
| 1.0855 | 0.37 | 500 | 1.0973 | 0.3490 | |
|
| 1.0788 | 0.44 | 600 | 1.1068 | 0.3490 | |
|
| 1.1029 | 0.51 | 700 | 1.0978 | 0.3490 | |
|
| 1.1018 | 0.59 | 800 | 1.1049 | 0.3020 | |
|
| 1.0983 | 0.66 | 900 | 1.1168 | 0.3267 | |
|
| 1.1094 | 0.73 | 1000 | 1.1011 | 0.3020 | |
|
| 1.0866 | 0.81 | 1100 | 1.1168 | 0.3020 | |
|
| 1.1286 | 0.88 | 1200 | 1.1051 | 0.3020 | |
|
| 1.1128 | 0.95 | 1300 | 1.1016 | 0.3490 | |
|
| 1.1194 | 1.03 | 1400 | 1.0978 | 0.3490 | |
|
| 1.0899 | 1.1 | 1500 | 1.1028 | 0.3490 | |
|
| 1.0948 | 1.17 | 1600 | 1.0976 | 0.3490 | |
|
| 1.1061 | 1.25 | 1700 | 1.0975 | 0.3490 | |
|
| 1.0964 | 1.32 | 1800 | 1.1016 | 0.3020 | |
|
| 1.1117 | 1.39 | 1900 | 1.0989 | 0.3490 | |
|
| 1.1053 | 1.47 | 2000 | 1.1013 | 0.3020 | |
|
| 1.0966 | 1.54 | 2100 | 1.0979 | 0.3490 | |
|
| 1.1037 | 1.61 | 2200 | 1.1007 | 0.3490 | |
|
| 1.1102 | 1.69 | 2300 | 1.0984 | 0.3490 | |
|
| 1.1029 | 1.76 | 2400 | 1.0979 | 0.3490 | |
|
| 1.095 | 1.83 | 2500 | 1.0975 | 0.3490 | |
|
| 1.0942 | 1.91 | 2600 | 1.0973 | 0.3490 | |
|
| 1.0962 | 1.98 | 2700 | 1.0973 | 0.3490 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
