Sentiment-google-t5-v1_1-large-inter_model-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: 1.2148

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
19.9179	1.0	44	23.0110
15.7039	2.0	88	11.5544
10.0821	3.0	132	9.0299
8.6626	4.0	176	8.7380
8.0831	5.0	220	8.5723
8.0781	6.0	264	8.4705
7.9258	7.0	308	8.3030
7.7266	8.0	352	7.8865
7.2525	9.0	396	7.4655
7.0455	10.0	440	7.2241
6.852	11.0	484	7.0989
6.7656	12.0	528	6.9915
0.9781	13.0	572	0.7604
0.8277	14.0	616	0.7302
0.8107	15.0	660	0.7269
0.7979	16.0	704	0.7203
0.787	17.0	748	0.7190
0.784	18.0	792	0.7176
0.7723	19.0	836	0.7162
0.7689	20.0	880	0.7157
0.7627	21.0	924	0.7137
0.7691	22.0	968	0.7156
0.7728	23.0	1012	0.7139
0.7586	24.0	1056	0.7136
0.7508	25.0	1100	0.7130
0.7754	26.0	1144	0.7096
0.7449	27.0	1188	0.7117
0.769	28.0	1232	0.7073
0.7562	29.0	1276	0.7081
0.7597	30.0	1320	0.7111
0.7649	31.0	1364	0.7072
0.7449	32.0	1408	0.7113
0.7431	33.0	1452	0.7103
0.7448	34.0	1496	0.7066
0.7409	35.0	1540	0.7056
0.7438	36.0	1584	0.7072
0.7545	37.0	1628	0.7041
0.7519	38.0	1672	0.7060
0.7546	39.0	1716	0.7042
0.7585	40.0	1760	0.7031
0.7491	41.0	1804	0.7074
0.7421	42.0	1848	0.7058
0.7471	43.0	1892	0.7108
0.758	44.0	1936	0.7041
0.7291	45.0	1980	0.7049

Framework versions

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