ghc-google-t5-v1_1-large-intra_model-frequency-human_annots_str

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: 0.2524

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
2.5958	1.0	345	2.2751
1.9688	2.0	690	2.0758
1.8217	3.0	1035	1.8429
0.0765	4.0	1380	0.0461
0.0683	5.0	1725	0.0501
0.0545	6.0	2070	0.0452
0.0515	7.0	2415	0.0417
0.044	8.0	2760	0.0387
0.0464	9.0	3105	0.0375
0.0449	10.0	3450	0.0416
0.0383	11.0	3795	0.0343
0.0484	12.0	4140	0.0334
0.0411	13.0	4485	0.0329
0.0412	14.0	4830	0.0327
0.0416	15.0	5175	0.0324
0.0409	16.0	5520	0.0328
0.0368	17.0	5865	0.0319
0.039	18.0	6210	0.0315
0.0352	19.0	6555	0.0311
0.0339	20.0	6900	0.0309
0.0391	21.0	7245	0.0322
0.0375	22.0	7590	0.0303
0.036	23.0	7935	0.0304
0.0322	24.0	8280	0.0302
0.0289	25.0	8625	0.0297
0.0296	26.0	8970	0.0300
0.0327	27.0	9315	0.0302
0.0331	28.0	9660	0.0300

Framework versions

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