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-kd_weight_copy-data-smsa-model-xlmr_base_trained

This model is a fine-tuned version of haryoaw/scenario-normal-finetune-clf-data-smsa-model-xlm-roberta-base on the smsa 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 0.29 100 1.6376 0.8762 0.8366
No log 0.58 200 0.9254 0.9016 0.8676
No log 0.87 300 1.1149 0.9056 0.8673
No log 1.16 400 0.9098 0.9127 0.8603
1.156 1.45 500 0.8235 0.9143 0.8710
1.156 1.74 600 0.7765 0.9087 0.8638
1.156 2.03 700 0.7826 0.9040 0.8611
1.156 2.33 800 0.8526 0.9151 0.8755
1.156 2.62 900 0.7667 0.9103 0.8766
0.5493 2.91 1000 0.9115 0.9024 0.8615
0.5493 3.2 1100 0.7453 0.9063 0.8651
0.5493 3.49 1200 0.6839 0.9167 0.8789
0.5493 3.78 1300 0.5967 0.9119 0.8714
0.5493 4.07 1400 0.6695 0.9167 0.8714
0.4097 4.36 1500 0.6204 0.9159 0.8779
0.4097 4.65 1600 0.5870 0.9246 0.8896
0.4097 4.94 1700 0.7656 0.9167 0.8812
0.4097 5.23 1800 0.9198 0.9111 0.8785
0.4097 5.52 1900 0.6545 0.9111 0.8713
0.3397 5.81 2000 0.6778 0.9095 0.8788
0.3397 6.1 2100 0.5985 0.9087 0.8656
0.3397 6.4 2200 0.6263 0.9087 0.8704
0.3397 6.69 2300 0.6875 0.9032 0.8543
0.3397 6.98 2400 0.5157 0.9111 0.8724
0.2927 7.27 2500 0.5375 0.9111 0.8687
0.2927 7.56 2600 0.5682 0.9143 0.8809
0.2927 7.85 2700 0.5866 0.9151 0.8789
0.2927 8.14 2800 0.5692 0.9159 0.8741
0.2927 8.43 2900 0.5413 0.9183 0.8824
0.259 8.72 3000 0.6369 0.9127 0.8790
0.259 9.01 3100 0.6281 0.9063 0.8692

Framework versions