automation-flanT5-summarize

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3180

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: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
4.6737	1.0	100	4.2136
2.2672	2.0	200	1.2099
0.7158	3.0	300	0.5136
0.3763	4.0	400	0.4204
0.34	5.0	500	0.3903
0.444	6.0	600	0.3730
0.3021	7.0	700	0.3643
0.2925	8.0	800	0.3539
0.2655	9.0	900	0.3486
0.2291	10.0	1000	0.3434
0.2638	11.0	1100	0.3420
0.3179	12.0	1200	0.3342
0.2649	13.0	1300	0.3322
0.2329	14.0	1400	0.3298
0.205	15.0	1500	0.3275
0.238	16.0	1600	0.3248
0.324	17.0	1700	0.3231
0.2491	18.0	1800	0.3214
0.2297	19.0	1900	0.3202
0.2335	20.0	2000	0.3185
0.1737	21.0	2100	0.3190
0.1962	22.0	2200	0.3180
0.2303	23.0	2300	0.3185
0.2434	24.0	2400	0.3180

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1