Sentiment-google-t5-v1_1-large-intra_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: 7.5234

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
21.0865	1.0	44	23.6328
19.3373	2.0	88	17.3411
14.3861	3.0	132	11.9747
11.4823	4.0	176	10.9355
10.5154	5.0	220	10.7808
10.1482	6.0	264	10.7065
10.0319	7.0	308	10.5792
9.8259	8.0	352	10.2032
9.1712	9.0	396	9.5730
8.8567	10.0	440	9.2184
8.626	11.0	484	9.0661
8.5469	12.0	528	8.9471
6.3996	13.0	572	1.5474
1.3785	14.0	616	1.3062
1.3229	15.0	660	1.2992
1.3309	16.0	704	1.3052
1.3341	17.0	748	1.2961
1.3281	18.0	792	1.2946
1.3219	19.0	836	1.3034
1.3185	20.0	880	1.2989
1.3184	21.0	924	1.2985

Framework versions

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