mt5-base-finetuned-mt5-base-poem4Final

This model is a fine-tuned version of google/mt5-base on an unknown 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: 2e-05
• 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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	121	nan
No log	2.0	242	nan
No log	3.0	363	nan
No log	4.0	484	nan
0.0	5.0	605	nan
0.0	6.0	726	nan
0.0	7.0	847	nan
0.0	8.0	968	nan
0.0	9.0	1089	nan
0.0	10.0	1210	nan
0.0	11.0	1331	nan
0.0	12.0	1452	nan
0.0	13.0	1573	nan
0.0	14.0	1694	nan
0.0	15.0	1815	nan
0.0	16.0	1936	nan
0.0	17.0	2057	nan
0.0	18.0	2178	nan
0.0	19.0	2299	nan
0.0	20.0	2420	nan

Framework versions

• Transformers 4.41.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1