TAM-10epoch-BertMul

This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1285
• Accuracy: 0.4340

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: 2e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	8	1.1051	0.2264
No log	2.0	16	1.0816	0.5094
No log	3.0	24	1.0964	0.6415
No log	4.0	32	1.1052	0.4151
No log	5.0	40	1.0832	0.4340
No log	6.0	48	1.0855	0.4151
No log	7.0	56	1.1034	0.4528
No log	8.0	64	1.1136	0.4340
No log	9.0	72	1.1246	0.4340
No log	10.0	80	1.1285	0.4340

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 1.13.1
• Datasets 2.14.5
• Tokenizers 0.14.1