summary_about_me

This model is a fine-tuned version of d0rj/rut5-base-summ on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9918
• Rouge1: 0.9677
• Rouge2: 0.8966
• Rougel: 0.9677
• Rougelsum: 0.9677
• Gen Len: 79.0

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: 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: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	50	1.3458	0.0	0.0	0.0	0.0	20.0
No log	2.0	100	1.3283	0.0	0.0	0.0	0.0	20.0
No log	3.0	150	1.3000	0.0	0.0	0.0	0.0	17.0
No log	4.0	200	1.2688	0.0	0.0	0.0	0.0	17.0
No log	5.0	250	1.2354	0.0	0.0	0.0	0.0	17.0
No log	6.0	300	1.2041	0.0	0.0	0.0	0.0	20.0
No log	7.0	350	1.1791	0.0	0.0	0.0	0.0	10.0
No log	8.0	400	1.1403	0.0	0.0	0.0	0.0	17.0
No log	9.0	450	1.1153	0.0	0.0	0.0	0.0	17.0
2.0999	10.0	500	1.0938	0.0	0.0	0.0	0.0	17.0
2.0999	11.0	550	1.0813	0.0	0.0	0.0	0.0	17.0
2.0999	12.0	600	1.0607	0.1176	0.0	0.1176	0.1176	35.0
2.0999	13.0	650	1.0508	0.9333	0.8571	0.9333	0.9333	44.0
2.0999	14.0	700	1.0386	0.9333	0.8571	0.9333	0.9333	44.0
2.0999	15.0	750	1.0293	0.9333	0.8571	0.9333	0.9333	44.0
2.0999	16.0	800	1.0210	0.9333	0.8571	0.9333	0.9333	44.0
2.0999	17.0	850	1.0151	0.9333	0.8571	0.9333	0.9333	44.0
2.0999	18.0	900	1.0084	0.0	0.0	0.0	0.0	10.0
2.0999	19.0	950	1.0039	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	20.0	1000	0.9999	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	21.0	1050	0.9963	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	22.0	1100	0.9943	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	23.0	1150	0.9932	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	24.0	1200	0.9925	0.9677	0.8966	0.9677	0.9677	79.0
1.8806	25.0	1250	0.9918	0.9677	0.8966	0.9677	0.9677	79.0

Framework versions

• PEFT 0.11.1
• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1