<!-- 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. -->
scenario-kd-from-post-finetune-silver-div-2-data-indolem_sentiment-model-haryoaw
This model is a fine-tuned version of haryoaw/scenario-normal-finetune-clf-data-indolem_sentiment-model-xlm-roberta-base on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 5.1475
- Accuracy: 0.8496
- F1: 0.7541
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6969
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.88 | 100 | 4.9395 | 0.8070 | 0.6578 |
| No log | 1.75 | 200 | 3.9351 | 0.8471 | 0.7469 |
| No log | 2.63 | 300 | 6.0878 | 0.8221 | 0.7361 |
| No log | 3.51 | 400 | 4.0921 | 0.8596 | 0.7522 |
| 3.7224 | 4.39 | 500 | 5.4792 | 0.8396 | 0.7333 |
| 3.7224 | 5.26 | 600 | 4.6363 | 0.8321 | 0.7074 |
| 3.7224 | 6.14 | 700 | 4.7179 | 0.8596 | 0.7431 |
| 3.7224 | 7.02 | 800 | 5.1069 | 0.8421 | 0.7549 |
| 3.7224 | 7.89 | 900 | 4.8423 | 0.8647 | 0.7857 |
| 1.1576 | 8.77 | 1000 | 4.3909 | 0.8697 | 0.7739 |
| 1.1576 | 9.65 | 1100 | 4.2645 | 0.8747 | 0.7788 |
| 1.1576 | 10.53 | 1200 | 4.6230 | 0.8672 | 0.7985 |
| 1.1576 | 11.4 | 1300 | 4.6784 | 0.8596 | 0.7941 |
| 1.1576 | 12.28 | 1400 | 4.5404 | 0.8747 | 0.7934 |
| 0.7484 | 13.16 | 1500 | 4.3058 | 0.8672 | 0.7905 |
| 0.7484 | 14.04 | 1600 | 4.2340 | 0.8421 | 0.7296 |
| 0.7484 | 14.91 | 1700 | 4.6968 | 0.8471 | 0.7189 |
| 0.7484 | 15.79 | 1800 | 5.2276 | 0.8421 | 0.6927 |
| 0.7484 | 16.67 | 1900 | 4.5916 | 0.8246 | 0.7131 |
| 0.434 | 17.54 | 2000 | 4.6032 | 0.8421 | 0.7200 |
| 0.434 | 18.42 | 2100 | 4.8115 | 0.8571 | 0.7421 |
| 0.434 | 19.3 | 2200 | 5.7001 | 0.8271 | 0.7677 |
| 0.434 | 20.18 | 2300 | 5.9914 | 0.8321 | 0.7509 |
| 0.434 | 21.05 | 2400 | 4.8685 | 0.8371 | 0.7032 |
| 0.3701 | 21.93 | 2500 | 5.1582 | 0.8521 | 0.7668 |
| 0.3701 | 22.81 | 2600 | 4.4940 | 0.8647 | 0.7805 |
| 0.3701 | 23.68 | 2700 | 5.1475 | 0.8496 | 0.7541 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
