ROE_Patent_Breeze7B_V2

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: 1.0290

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 18
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2509	0.9697	12	1.2524
1.1785	1.9394	24	1.1963
1.0903	2.9899	37	1.1486
1.0958	3.9596	49	1.1173
1.0397	4.9293	61	1.0942
0.9761	5.9798	74	1.0738
0.9634	6.9495	86	1.0573
0.9075	8.0	99	1.0463
0.9133	8.9697	111	1.0375
0.8696	9.9394	123	1.0337
0.8935	10.9899	136	1.0294
0.8618	11.9596	148	1.0261
0.826	12.9293	160	1.0235
0.8184	13.9798	173	1.0226
0.7991	14.9495	185	1.0289
0.7906	16.0	198	1.0220
0.7722	16.9697	210	1.0245
0.7722	17.4545	216	1.0290

Framework versions

• PEFT 0.13.3.dev0
• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1