generated_from_trainer

<!-- 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-no_kd_weight_copy-data-indolem_sentiment-model-xlm-roberta-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:

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:

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 0.88 100 0.6818 0.6466 0.6137
No log 1.75 200 0.4083 0.8045 0.675
No log 2.63 300 0.4782 0.7870 0.7018
No log 3.51 400 0.4200 0.8120 0.6377
0.342 4.39 500 0.4516 0.8346 0.7203
0.342 5.26 600 0.8387 0.8396 0.7037
0.342 6.14 700 0.6095 0.8647 0.7589
0.342 7.02 800 0.6555 0.8596 0.7667
0.342 7.89 900 0.7089 0.8421 0.7709
0.1124 8.77 1000 0.8602 0.8396 0.7288
0.1124 9.65 1100 0.7809 0.8496 0.7794
0.1124 10.53 1200 0.9068 0.8571 0.7865
0.1124 11.4 1300 0.8547 0.8546 0.7315
0.1124 12.28 1400 0.8175 0.8546 0.7521
0.0382 13.16 1500 1.1699 0.8396 0.7037
0.0382 14.04 1600 0.8574 0.8271 0.7137
0.0382 14.91 1700 0.8383 0.8346 0.7676
0.0382 15.79 1800 0.6734 0.8421 0.7014
0.0382 16.67 1900 0.9742 0.8471 0.7798
0.0322 17.54 2000 0.9638 0.8546 0.7698
0.0322 18.42 2100 0.8489 0.8672 0.7764
0.0322 19.3 2200 1.1684 0.8471 0.7749
0.0322 20.18 2300 0.9654 0.8521 0.7592
0.0322 21.05 2400 1.1021 0.8371 0.6890
0.0272 21.93 2500 0.7941 0.8747 0.7917
0.0272 22.81 2600 1.0242 0.8571 0.7692
0.0272 23.68 2700 1.0652 0.8471 0.7359
0.0272 24.56 2800 0.8950 0.8446 0.7281
0.0272 25.44 2900 1.0617 0.8296 0.6852
0.0227 26.32 3000 1.2601 0.8371 0.6766
0.0227 27.19 3100 1.1990 0.8622 0.7556
0.0227 28.07 3200 0.9990 0.8321 0.7433
0.0227 28.95 3300 1.0540 0.8571 0.7765
0.0227 29.82 3400 1.2783 0.8446 0.7232
0.0147 30.7 3500 1.1020 0.8571 0.7816
0.0147 31.58 3600 1.0771 0.8571 0.7349
0.0147 32.46 3700 0.9544 0.8672 0.7725
0.0147 33.33 3800 0.9524 0.8371 0.7005
0.0147 34.21 3900 0.8062 0.8296 0.7344
0.0275 35.09 4000 1.1793 0.8321 0.6854

Framework versions