|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: aces-roberta-10 |
|
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. --> |
|
|
|
# aces-roberta-10 |
|
|
|
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6188 |
|
- Precision: 0.8040 |
|
- Recall: 0.8198 |
|
- F1: 0.8097 |
|
- Accuracy: 0.8198 |
|
- F1 Who: 0.7939 |
|
- F1 What: 0.7929 |
|
- F1 Where: 0.7769 |
|
- F1 How: 0.8905 |
|
|
|
## 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: 1e-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 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | F1 Who | F1 What | F1 Where | F1 How | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:------:|:-------:|:--------:|:------:| |
|
| 1.6596 | 0.15 | 20 | 1.2172 | 0.5510 | 0.6640 | 0.5906 | 0.6640 | 0.0 | 0.6409 | 0.3258 | 0.7719 | |
|
| 1.0566 | 0.31 | 40 | 0.9097 | 0.6534 | 0.7087 | 0.6590 | 0.7087 | 0.3855 | 0.7020 | 0.5620 | 0.8086 | |
|
| 0.8056 | 0.46 | 60 | 0.7640 | 0.7092 | 0.7570 | 0.7196 | 0.7570 | 0.6857 | 0.7709 | 0.6696 | 0.8114 | |
|
| 0.6996 | 0.61 | 80 | 0.6706 | 0.7601 | 0.7931 | 0.7687 | 0.7931 | 0.8103 | 0.7743 | 0.7471 | 0.8499 | |
|
| 0.6346 | 0.76 | 100 | 0.6471 | 0.7763 | 0.8032 | 0.7852 | 0.8032 | 0.7874 | 0.7813 | 0.7490 | 0.8665 | |
|
| 0.523 | 0.92 | 120 | 0.6635 | 0.7872 | 0.8061 | 0.7865 | 0.8061 | 0.8244 | 0.7718 | 0.7692 | 0.8771 | |
|
| 0.5324 | 1.07 | 140 | 0.6162 | 0.8045 | 0.8212 | 0.8110 | 0.8212 | 0.8197 | 0.8008 | 0.8033 | 0.8852 | |
|
| 0.4734 | 1.22 | 160 | 0.6147 | 0.7935 | 0.8097 | 0.7978 | 0.8097 | 0.7939 | 0.7861 | 0.7698 | 0.8911 | |
|
| 0.5111 | 1.37 | 180 | 0.6142 | 0.8022 | 0.8154 | 0.8051 | 0.8154 | 0.8244 | 0.8047 | 0.768 | 0.8909 | |
|
| 0.4416 | 1.53 | 200 | 0.6204 | 0.8006 | 0.8190 | 0.8079 | 0.8190 | 0.8271 | 0.7984 | 0.7773 | 0.8886 | |
|
| 0.5249 | 1.68 | 220 | 0.6239 | 0.7907 | 0.8133 | 0.8006 | 0.8133 | 0.8182 | 0.7969 | 0.7739 | 0.8776 | |
|
| 0.4599 | 1.83 | 240 | 0.6458 | 0.7989 | 0.8082 | 0.7967 | 0.8082 | 0.8244 | 0.7953 | 0.7751 | 0.8853 | |
|
| 0.4979 | 1.98 | 260 | 0.6390 | 0.8071 | 0.8183 | 0.8051 | 0.8183 | 0.7869 | 0.8000 | 0.7583 | 0.8871 | |
|
| 0.393 | 2.14 | 280 | 0.6348 | 0.7994 | 0.8125 | 0.8021 | 0.8125 | 0.8271 | 0.7904 | 0.7653 | 0.8812 | |
|
| 0.4079 | 2.29 | 300 | 0.6227 | 0.8002 | 0.8140 | 0.8040 | 0.8140 | 0.8182 | 0.7908 | 0.7668 | 0.8784 | |
|
| 0.3731 | 2.44 | 320 | 0.6319 | 0.7887 | 0.8075 | 0.7965 | 0.8075 | 0.8030 | 0.7814 | 0.7692 | 0.8702 | |
|
| 0.3987 | 2.6 | 340 | 0.6171 | 0.7922 | 0.8140 | 0.8015 | 0.8140 | 0.7907 | 0.7813 | 0.7968 | 0.8759 | |
|
| 0.3865 | 2.75 | 360 | 0.6161 | 0.7968 | 0.8118 | 0.8032 | 0.8118 | 0.7846 | 0.7824 | 0.7692 | 0.8851 | |
|
| 0.4222 | 2.9 | 380 | 0.6137 | 0.7955 | 0.8140 | 0.8033 | 0.8140 | 0.8060 | 0.7897 | 0.7874 | 0.8746 | |
|
| 0.4164 | 3.05 | 400 | 0.6016 | 0.8017 | 0.8176 | 0.8079 | 0.8176 | 0.7846 | 0.7954 | 0.7843 | 0.8832 | |
|
| 0.3505 | 3.21 | 420 | 0.6239 | 0.7912 | 0.8075 | 0.7949 | 0.8075 | 0.7846 | 0.7930 | 0.7786 | 0.8556 | |
|
| 0.3834 | 3.36 | 440 | 0.6038 | 0.8022 | 0.8169 | 0.8082 | 0.8169 | 0.7907 | 0.7976 | 0.7757 | 0.8835 | |
|
| 0.3139 | 3.51 | 460 | 0.6068 | 0.7978 | 0.8161 | 0.8052 | 0.8161 | 0.7970 | 0.7904 | 0.7846 | 0.8870 | |
|
| 0.3679 | 3.66 | 480 | 0.6070 | 0.8026 | 0.8183 | 0.8063 | 0.8183 | 0.7907 | 0.7953 | 0.7799 | 0.8835 | |
|
| 0.3387 | 3.82 | 500 | 0.6059 | 0.8025 | 0.8205 | 0.8094 | 0.8205 | 0.7879 | 0.7977 | 0.7937 | 0.8879 | |
|
| 0.3208 | 3.97 | 520 | 0.6064 | 0.8015 | 0.8183 | 0.8082 | 0.8183 | 0.7970 | 0.7900 | 0.7782 | 0.8854 | |
|
| 0.3008 | 4.12 | 540 | 0.6088 | 0.8020 | 0.8205 | 0.8107 | 0.8205 | 0.7970 | 0.7946 | 0.7813 | 0.8883 | |
|
| 0.3014 | 4.27 | 560 | 0.6093 | 0.8032 | 0.8212 | 0.8114 | 0.8212 | 0.8120 | 0.7961 | 0.7813 | 0.8867 | |
|
| 0.3486 | 4.43 | 580 | 0.6112 | 0.8042 | 0.8205 | 0.8107 | 0.8205 | 0.7939 | 0.7961 | 0.7829 | 0.8873 | |
|
| 0.2793 | 4.58 | 600 | 0.6156 | 0.8047 | 0.8183 | 0.8088 | 0.8183 | 0.7846 | 0.7945 | 0.7769 | 0.8905 | |
|
| 0.2943 | 4.73 | 620 | 0.6170 | 0.8044 | 0.8212 | 0.8107 | 0.8212 | 0.7846 | 0.7992 | 0.7843 | 0.8895 | |
|
| 0.3314 | 4.89 | 640 | 0.6188 | 0.8040 | 0.8198 | 0.8097 | 0.8198 | 0.7939 | 0.7929 | 0.7769 | 0.8905 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
