sentance_split_by_time_gpt_concate_2

This model is a fine-tuned version of OFA-Sys/chinese-clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.8914
• Accuracy: 0.0782

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: 1e-05
• train_batch_size: 25
• eval_batch_size: 20
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 200
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 60.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0864	5.9928	1866	2.9935	0.0803
1.9035	11.9855	3732	3.1629	0.0863
1.779	17.9783	5598	3.2064	0.0870
1.7158	23.9711	7464	3.4417	0.0854
1.6832	29.9639	9330	3.4988	0.0845
1.6554	35.9566	11196	3.5538	0.0833
1.6498	41.9494	13062	3.6819	0.0819
1.6335	47.9422	14928	3.7696	0.0809
1.6339	53.9350	16794	3.8098	0.0799
1.6264	59.9277	18660	3.8914	0.0789

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1