Sentiment-google-t5-v1_1-large-inter_model-shuffle-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: 1.3838

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
20.9707	1.0	44	24.0812
19.1584	2.0	88	19.1069
14.7114	3.0	132	12.0456
11.3751	4.0	176	10.9758
10.1468	5.0	220	10.7621
10.0067	6.0	264	10.6808
10.0007	7.0	308	10.5435
9.7079	8.0	352	10.1514
9.182	9.0	396	9.5931
8.7756	10.0	440	9.2557
8.6941	11.0	484	9.0992
8.6156	12.0	528	8.9849
8.1186	13.0	572	8.7739
1.4193	14.0	616	1.3089
1.3333	15.0	660	1.3014
1.3499	16.0	704	1.3009
1.3384	17.0	748	1.2995
1.332	18.0	792	1.2958
1.3226	19.0	836	1.3095
1.318	20.0	880	1.3012
1.3192	21.0	924	1.2978

Framework versions

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