owanr/ghc-google-t5-v1_1-large-intra_model-sorted-model_annots_str

ghc-google-t5-v1_1-large-intra_model-sorted

This model is a fine-tuned version of google/t5-v1_1-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2695

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss
15.9581	1.0	345	15.6856
10.8736	2.0	690	11.4385
10.3765	3.0	1035	10.8459
3.15	4.0	1380	2.7128
0.2927	5.0	1725	0.2377
0.3245	6.0	2070	0.2290
0.3004	7.0	2415	0.2255
0.2514	8.0	2760	0.2242
0.2371	9.0	3105	0.2189
0.2359	10.0	3450	0.2122
0.2501	11.0	3795	0.2092
0.2344	12.0	4140	0.2053
0.2419	13.0	4485	0.2090
0.2542	14.0	4830	0.2080
0.227	15.0	5175	0.2079
0.2213	16.0	5520	0.2055
0.2104	17.0	5865	0.2066

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1