hoa1b4_finetuned_kc_June27th_1

This model is a fine-tuned version of vlsp-2023-vllm/hoa-1b4 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3124

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 1
• 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
0.971	1.0	788	0.7533
0.6048	2.0	1576	0.5293
0.4194	3.0	2364	0.4284
0.3238	4.0	3152	0.3751
0.2651	5.0	3940	0.3464
0.2247	6.0	4728	0.3325
0.195	7.0	5516	0.3200
0.1722	8.0	6304	0.3175
0.1555	9.0	7092	0.3132
0.1434	10.0	7880	0.3124

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.3.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1