Sentiment-google-t5-v1_1-large-inter_model-shuffle-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: 128
• eval_batch_size: 128
• 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
19.9569	1.0	44	24.5425
17.0234	2.0	88	15.4055
11.6683	3.0	132	9.5059
8.8616	4.0	176	8.7957
8.2698	5.0	220	8.6316
8.1875	6.0	264	8.5314
7.99	7.0	308	8.4160
7.8585	8.0	352	8.2126
7.5473	9.0	396	7.7908
7.1869	10.0	440	7.4343
7.0103	11.0	484	7.2743
6.9522	12.0	528	7.1678
6.8309	13.0	572	7.0572
1.2882	14.0	616	1.0288
1.0846	15.0	660	1.0039
1.072	16.0	704	0.9993
1.0704	17.0	748	0.9972
1.0643	18.0	792	0.9962
1.0574	19.0	836	0.9945
1.0485	20.0	880	0.9926
1.0436	21.0	924	0.9924
1.0587	22.0	968	0.9950
1.0569	23.0	1012	0.9906
1.0393	24.0	1056	0.9922
1.0438	25.0	1100	0.9931
1.0579	26.0	1144	0.9880
1.0194	27.0	1188	0.9909
1.0475	28.0	1232	0.9906
1.0494	29.0	1276	0.9887

Framework versions

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