BERT_test_graident_accumulation_test4

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

• Loss: 1.1752
• Accuracy: 0.5781

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	116	1.0083	0.5586
No log	1.99	232	1.0274	0.5913
No log	2.99	348	1.1752	0.5781

Framework versions

• Transformers 4.36.0
• Pytorch 2.1.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0