README.md

metadata

base_model: weny22/sum_model_t5_saved
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: extract_long_text_unbalanced_smaller_6
    results: []

extract_long_text_unbalanced_smaller_6

Use this , this is for the small unbalanced dataset with extracted text.

This model is a fine-tuned version of weny22/sum_model_t5_saved on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4469
• Rouge1: 0.202
• Rouge2: 0.0715
• Rougel: 0.1621
• Rougelsum: 0.1621
• Gen Len: 18.9807

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: 0.002
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	72	2.4359	0.1821	0.0587	0.1461	0.1461	18.9967
No log	2.0	144	2.3350	0.1934	0.0625	0.1529	0.1532	19.0
No log	3.0	216	2.2535	0.1907	0.0618	0.1515	0.1516	18.9947
No log	4.0	288	2.2242	0.1915	0.0619	0.1515	0.1517	18.9913
No log	5.0	360	2.2027	0.196	0.0646	0.1544	0.1545	18.9973
No log	6.0	432	2.2339	0.1894	0.0619	0.1501	0.1502	18.9967
2.7907	7.0	504	2.1934	0.1949	0.0649	0.155	0.155	18.9847
2.7907	8.0	576	2.2615	0.1976	0.0669	0.1574	0.1575	18.982
2.7907	9.0	648	2.2664	0.2033	0.0726	0.1623	0.1622	18.9827
2.7907	10.0	720	2.2514	0.2025	0.0713	0.1609	0.161	18.984
2.7907	11.0	792	2.2772	0.1982	0.071	0.1591	0.1591	18.9847
2.7907	12.0	864	2.3114	0.2056	0.0731	0.1635	0.1637	18.9753
2.7907	13.0	936	2.3120	0.2011	0.071	0.1602	0.1602	18.9867
1.8632	14.0	1008	2.3276	0.2044	0.0733	0.1636	0.1638	18.9687
1.8632	15.0	1080	2.3733	0.201	0.072	0.161	0.1611	18.9847
1.8632	16.0	1152	2.3852	0.2021	0.0719	0.1627	0.1627	18.9773
1.8632	17.0	1224	2.4101	0.1999	0.0705	0.1608	0.1608	18.9787
1.8632	18.0	1296	2.4123	0.1999	0.0709	0.1604	0.1605	18.9833
1.8632	19.0	1368	2.4414	0.2	0.0704	0.1605	0.1604	18.9753
1.8632	20.0	1440	2.4469	0.202	0.0715	0.1621	0.1621	18.9807

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2