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: 3.3340
• Rouge1: 0.4569
• Rouge2: 0.2272
• Rougel: 0.3918
• Rougelsum: 0.3927
• Gen Len: 20.82
• Bleu: 0.1112
• Precisions: 0.2401
• Brevity Penalty: 0.5852
• Length Ratio: 0.6511
• Translation Length: 795.0
• Reference Length: 1221.0
• Precision: 0.9098
• Recall: 0.8906
• F1: 0.9
• Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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
• mixed_precision_training: Native AMP

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
No log	1.0	7	7.6476	0.348	0.1355	0.2757	0.274	21.0	0.0602	0.1436	0.6232	0.679	829.0	1221.0	0.8935	0.8759	0.8845	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	2.0	14	6.4676	0.4218	0.2049	0.3597	0.3592	20.94	0.1008	0.2063	0.6419	0.6929	846.0	1221.0	0.9027	0.8839	0.8932	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	3.0	21	5.0145	0.4189	0.2067	0.362	0.3612	20.5	0.0945	0.2152	0.5919	0.656	801.0	1221.0	0.9087	0.8846	0.8964	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	4.0	28	4.2719	0.44	0.2299	0.3791	0.3778	20.48	0.1052	0.2337	0.5852	0.6511	795.0	1221.0	0.9087	0.8882	0.8982	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	5.0	35	3.9222	0.4538	0.238	0.3919	0.3917	20.7	0.1062	0.2404	0.5795	0.647	790.0	1221.0	0.9126	0.891	0.9016	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	6.0	42	3.6730	0.4582	0.2266	0.3926	0.3922	20.82	0.1093	0.236	0.5908	0.6552	800.0	1221.0	0.9099	0.8895	0.8995	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	7.0	49	3.5177	0.4639	0.2385	0.4037	0.4033	20.76	0.117	0.2484	0.5863	0.6519	796.0	1221.0	0.9101	0.8901	0.8999	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	8.0	56	3.4234	0.4564	0.2345	0.398	0.3978	20.72	0.1148	0.247	0.5806	0.6478	791.0	1221.0	0.9094	0.8891	0.899	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	9.0	63	3.3645	0.4518	0.2273	0.3912	0.3913	20.82	0.1111	0.2376	0.5886	0.6536	798.0	1221.0	0.9087	0.8899	0.8991	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
No log	10.0	70	3.3340	0.4569	0.2272	0.3918	0.3927	20.82	0.1112	0.2401	0.5852	0.6511	795.0	1221.0	0.9098	0.8906	0.9	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1