ghc-google-t5-v1_1-large-intra_model-frequency-model_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: nan

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: 16
• eval_batch_size: 16
• 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
6.0859	1.0	689	6.1514
5.0336	2.0	1378	5.3269
0.2999	3.0	2067	0.2688
0.2743	4.0	2756	0.2625
0.2938	5.0	3445	0.2641
0.2575	6.0	4134	0.2568
0.2648	7.0	4823	0.2530
0.2687	8.0	5512	0.2512
0.2444	9.0	6201	0.2498
0.2562	10.0	6890	0.2489
0.2606	11.0	7579	0.2467
0.2592	12.0	8268	0.2466
0.2316	13.0	8957	0.2470
0.2544	14.0	9646	0.2454
0.2644	15.0	10335	0.2449
0.2505	16.0	11024	0.2449
0.2485	17.0	11713	0.2449
0.2312	18.0	12402	0.2449

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.6.1
• Tokenizers 0.14.1