laptop_sentence_classfication_wangChanBERTa

This model is a fine-tuned version of airesearch/wangchanberta-base-att-spm-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2752
• Accuracy: 0.9

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	25	0.6130	0.7077
No log	2.0	50	0.4832	0.7769
No log	3.0	75	0.4457	0.8154
No log	4.0	100	0.4696	0.7692
No log	5.0	125	0.4378	0.8077
No log	6.0	150	0.4698	0.8077
No log	7.0	175	0.3654	0.8615
No log	8.0	200	0.3795	0.8615
No log	9.0	225	0.4212	0.8692
No log	10.0	250	0.4153	0.8538
No log	11.0	275	0.3723	0.8692
No log	12.0	300	0.3590	0.8538
No log	13.0	325	0.2553	0.9077
No log	14.0	350	0.2713	0.9
No log	15.0	375	0.2699	0.9077
No log	16.0	400	0.2563	0.9154
No log	17.0	425	0.2536	0.9231
No log	18.0	450	0.2529	0.9154
No log	19.0	475	0.2743	0.9
0.3025	20.0	500	0.2752	0.9

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3