Sentiment-google-t5-v1_1-large-intra_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: 5.1523

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
21.4519	1.0	44	23.5551
18.9968	2.0	88	14.8263
14.9431	3.0	132	12.4969
12.6115	4.0	176	11.0088
10.6403	5.0	220	10.5915
9.9328	6.0	264	10.3356
9.7009	7.0	308	10.2266
9.6314	8.0	352	10.0653
9.0124	9.0	396	9.4660
8.5964	10.0	440	8.9690
8.2786	11.0	484	8.7360
8.1874	12.0	528	8.5747
7.731	13.0	572	8.2712
1.0229	14.0	616	0.8619
0.9062	15.0	660	0.8607
0.9159	16.0	704	0.8539
0.9008	17.0	748	0.8525
0.8876	18.0	792	0.8460
0.8877	19.0	836	0.8504
0.8792	20.0	880	0.8484
0.8778	21.0	924	0.8492

Framework versions

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