scenario-KD-PO-MSV-D2_data-massive005_all_1_1_beta

This model is a fine-tuned version of haryoaw/scenario-TCR-data-AmazonScience-massive-all_1.1-model-xlm-roberta-base on the massive dataset. It achieves the following results on the evaluation set:

• Loss: 1.5983
• Accuracy: 0.8130
• F1: 0.7610

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: 4444
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.4073	5.45	5000	1.8787	0.7975	0.7417
0.317	10.89	10000	1.7264	0.8060	0.7498
0.2627	16.34	15000	1.6736	0.8085	0.7497
0.2409	21.79	20000	1.6215	0.8111	0.7588
0.2234	27.23	25000	1.5983	0.8130	0.7610

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3