ROE_Patent_Breeze7B_20250124_Type2

This model is a fine-tuned version of MediaTek-Research/Breeze-7B-Instruct-v1_0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0886

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2674	1.0	13	1.2818
1.1968	2.0	26	1.2237
1.109	3.0	39	1.1783
1.0705	4.0	52	1.1455
1.0496	5.0	65	1.1257
0.9968	6.0	78	1.1108
0.9967	7.0	91	1.0996
0.9594	8.0	104	1.0953
0.9665	9.0	117	1.0904
0.9773	10.0	130	1.0887
0.9705	11.0	143	1.0930
0.9705	11.0808	144	1.0886

Framework versions

• PEFT 0.14.1.dev0
• Transformers 4.48.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0