t5-small-text-simplification_1e4_adafactor

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

• Loss: 0.4541

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: 0.0001
• train_batch_size: 256
• eval_batch_size: 256
• 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
0.8842	1.0	582	0.4651
0.5737	2.0	1164	0.4611
0.5559	3.0	1746	0.4585
0.548	4.0	2328	0.4573
0.541	5.0	2910	0.4565
0.5349	6.0	3492	0.4564
0.5257	7.0	4074	0.4552
0.5223	8.0	4656	0.4558
0.5185	9.0	5238	0.4550
0.5145	10.0	5820	0.4544
0.5166	11.0	6402	0.4551
0.5104	12.0	6984	0.4546
0.5089	13.0	7566	0.4547
0.5054	14.0	8148	0.4544
0.5047	15.0	8730	0.4544
0.5043	16.0	9312	0.4537
0.5021	17.0	9894	0.4539
0.5034	18.0	10476	0.4539
0.5008	19.0	11058	0.4541
0.5003	20.0	11640	0.4541

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3