Lora_LED_sum_approach

This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.5646
• Rouge1: 0.4521
• Rouge2: 0.2422
• Rougel: 0.3904
• Rougelsum: 0.3905
• Gen Len: 29.4
• Bleu: 0.1533
• Precisions: 0.2152
• Brevity Penalty: 0.8831
• Length Ratio: 0.8894
• Translation Length: 1086.0
• Reference Length: 1221.0
• Precision: 0.9043
• Recall: 0.9002
• F1: 0.9021
• Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

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: 0.001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• 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: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length	Precision	Recall	F1	Hashcode
8.0757	1.0	7	7.6798	0.3128	0.1085	0.253	0.2533	32.0	0.0733	0.1062	1.0	1.0663	1302.0	1221.0	0.8685	0.8728	0.8706	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
6.5609	2.0	14	5.7642	0.4165	0.2088	0.3627	0.3626	30.64	0.1358	0.1742	1.0	1.036	1265.0	1221.0	0.8922	0.8861	0.889	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
4.9145	3.0	21	4.4340	0.4234	0.2265	0.3669	0.3685	25.84	0.1246	0.2092	0.765	0.7887	963.0	1221.0	0.9057	0.894	0.8996	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
4.0682	4.0	28	3.9241	0.4454	0.2452	0.3952	0.3971	27.26	0.1446	0.2209	0.8115	0.8272	1010.0	1221.0	0.9059	0.8983	0.9019	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.6834	5.0	35	3.7361	0.4521	0.237	0.3828	0.3837	27.58	0.1433	0.2137	0.8327	0.8452	1032.0	1221.0	0.9031	0.8973	0.9	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.5042	6.0	42	3.6285	0.4567	0.247	0.3901	0.3908	27.86	0.1451	0.2184	0.8336	0.846	1033.0	1221.0	0.9067	0.9003	0.9033	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.4173	7.0	49	3.5881	0.4458	0.2389	0.3839	0.3852	27.16	0.1439	0.2226	0.7929	0.8116	991.0	1221.0	0.9056	0.8973	0.9013	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.3572	8.0	56	3.5698	0.4514	0.2331	0.3836	0.3862	29.12	0.147	0.2081	0.884	0.8903	1087.0	1221.0	0.9026	0.8994	0.9009	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.3165	9.0	63	3.5700	0.4592	0.2422	0.3954	0.3957	29.28	0.1502	0.2113	0.8922	0.8976	1096.0	1221.0	0.9056	0.9012	0.9033	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
3.3094	10.0	70	3.5646	0.4521	0.2422	0.3904	0.3905	29.4	0.1533	0.2152	0.8831	0.8894	1086.0	1221.0	0.9043	0.9002	0.9021	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

Framework versions

• PEFT 0.15.2
• Transformers 4.53.1
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1