<!-- 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_weight_copy_before_finetune-data-indolem_sentiment-model-xlmr_base_trained
This model is a fine-tuned version of xlm-roberta-base on the indolem_sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 4.5241
- Accuracy: 0.8772
- F1: 0.7742
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 | 7.9127 | 0.7143 | 0.6481 |
| No log | 1.75 | 200 | 4.6741 | 0.8070 | 0.7050 |
| No log | 2.63 | 300 | 7.8636 | 0.7444 | 0.6909 |
| No log | 3.51 | 400 | 6.0981 | 0.7995 | 0.7386 |
| 5.2315 | 4.39 | 500 | 5.4394 | 0.8371 | 0.7547 |
| 5.2315 | 5.26 | 600 | 5.2403 | 0.8471 | 0.7510 |
| 5.2315 | 6.14 | 700 | 5.2631 | 0.8446 | 0.6961 |
| 5.2315 | 7.02 | 800 | 4.4937 | 0.8446 | 0.7500 |
| 5.2315 | 7.89 | 900 | 5.3924 | 0.8271 | 0.7473 |
| 1.5489 | 8.77 | 1000 | 4.8344 | 0.8496 | 0.7619 |
| 1.5489 | 9.65 | 1100 | 4.9316 | 0.8596 | 0.7431 |
| 1.5489 | 10.53 | 1200 | 4.5991 | 0.8471 | 0.7382 |
| 1.5489 | 11.4 | 1300 | 4.9883 | 0.8622 | 0.7860 |
| 1.5489 | 12.28 | 1400 | 4.9270 | 0.8396 | 0.7630 |
| 0.7153 | 13.16 | 1500 | 5.3685 | 0.8421 | 0.7042 |
| 0.7153 | 14.04 | 1600 | 5.0460 | 0.8496 | 0.7778 |
| 0.7153 | 14.91 | 1700 | 4.9382 | 0.8521 | 0.7839 |
| 0.7153 | 15.79 | 1800 | 4.6305 | 0.8622 | 0.7489 |
| 0.7153 | 16.67 | 1900 | 4.3493 | 0.8622 | 0.7773 |
| 0.5099 | 17.54 | 2000 | 5.6297 | 0.8446 | 0.7754 |
| 0.5099 | 18.42 | 2100 | 5.8916 | 0.8346 | 0.6916 |
| 0.5099 | 19.3 | 2200 | 4.4486 | 0.8546 | 0.7500 |
| 0.5099 | 20.18 | 2300 | 4.0523 | 0.8697 | 0.7833 |
| 0.5099 | 21.05 | 2400 | 5.7238 | 0.8496 | 0.7196 |
| 0.4105 | 21.93 | 2500 | 4.5255 | 0.8647 | 0.7568 |
| 0.4105 | 22.81 | 2600 | 4.6293 | 0.8571 | 0.7467 |
| 0.4105 | 23.68 | 2700 | 4.6967 | 0.8546 | 0.7734 |
| 0.4105 | 24.56 | 2800 | 4.5241 | 0.8772 | 0.7742 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
