scenario-KD-SCR-MSV-D2_data-massive005_all_1_1_delta

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the massive dataset. It achieves the following results on the evaluation set:

• Loss: 6.0463
• Accuracy: 0.5165
• F1: 0.4528

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: 1254
• 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
3.0677	5.45	5000	6.1102	0.4241	0.3184
1.3686	10.89	10000	6.4998	0.4722	0.3921
0.9452	16.34	15000	6.3958	0.4890	0.4247
0.7489	21.79	20000	6.3230	0.5006	0.4409
0.6528	27.23	25000	6.0463	0.5165	0.4528

Framework versions

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