Sentiment-google-t5-v1_1-large-inter_model-dataset-frequency-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: 0.7983

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
20.1785	1.0	44	24.2987
16.7918	2.0	88	13.0112
10.2722	3.0	132	9.1399
8.7351	4.0	176	8.7771
8.1648	5.0	220	8.6202
8.1662	6.0	264	8.5136
8.0042	7.0	308	8.3971
7.8946	8.0	352	8.1025
7.4059	9.0	396	7.6197
7.1363	10.0	440	7.3350
6.9292	11.0	484	7.1825
6.8455	12.0	528	7.0740
6.5296	13.0	572	6.9423
0.9019	14.0	616	0.6900
0.7584	15.0	660	0.6856
0.7245	16.0	704	0.6713
0.7189	17.0	748	0.6693
0.7258	18.0	792	0.6675
0.7222	19.0	836	0.6668
0.7112	20.0	880	0.6680
0.7125	21.0	924	0.6645
0.7038	22.0	968	0.6664
0.719	23.0	1012	0.6638
0.7022	24.0	1056	0.6621
0.6961	25.0	1100	0.6653
0.709	26.0	1144	0.6653
0.6969	27.0	1188	0.6633
0.7109	28.0	1232	0.6604
0.6965	29.0	1276	0.6617
0.7015	30.0	1320	0.6617
0.7098	31.0	1364	0.6609
0.6951	32.0	1408	0.6613
0.6881	33.0	1452	0.6631

Framework versions

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