Sentiment-google-t5-v1_1-large-inter_model-sorted-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: 2.4023

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
21.0529	1.0	44	22.8438
19.8705	2.0	88	18.5102
15.6787	3.0	132	12.3789
12.2348	4.0	176	11.0309
10.1559	5.0	220	10.6052
9.7633	6.0	264	10.3095
9.6742	7.0	308	10.2322
9.5533	8.0	352	10.1060
9.1403	9.0	396	9.6300
8.592	10.0	440	9.1220
8.4005	11.0	484	8.8250
8.2765	12.0	528	8.6542
7.9206	13.0	572	8.5108
1.7776	14.0	616	0.9630
0.9247	15.0	660	0.8549
0.9119	16.0	704	0.8479
0.9041	17.0	748	0.8443
0.9051	18.0	792	0.8442
0.8938	19.0	836	0.8585
0.8868	20.0	880	0.8510
0.8859	21.0	924	0.8462
0.8982	22.0	968	0.8460
0.8848	23.0	1012	0.8481

Framework versions

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