Sentiment-google-t5-v1_1-large-inter_model-sorted-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: nan

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
20.5922	1.0	44	24.6172
16.3048	2.0	88	12.1742
11.2971	3.0	132	10.1133
9.1562	4.0	176	8.7959
8.2587	5.0	220	8.5608
8.1239	6.0	264	8.4644
7.9281	7.0	308	8.3953
7.9676	8.0	352	8.2317
7.5012	9.0	396	7.7257
7.1769	10.0	440	7.3715
6.9303	11.0	484	7.1975
6.8629	12.0	528	7.0684
6.6057	13.0	572	6.9544
0.9049	14.0	616	0.6979
0.7327	15.0	660	0.6557
0.712	16.0	704	0.6521
0.7003	17.0	748	0.6520
0.7145	18.0	792	0.6503
0.6983	19.0	836	0.6504
0.6943	20.0	880	0.6481
0.6912	21.0	924	0.6479
0.6945	22.0	968	0.6467
0.6929	23.0	1012	0.6493
0.6902	24.0	1056	0.6479
0.6853	25.0	1100	0.6444
0.6881	26.0	1144	0.6438
0.6774	27.0	1188	0.6462
0.6921	28.0	1232	0.6456
0.6852	29.0	1276	0.6450
0.6763	30.0	1320	0.6448
0.6858	31.0	1364	0.6433
0.6789	32.0	1408	0.6450
0.6819	33.0	1452	0.6457
0.6804	34.0	1496	0.6458
0.6713	35.0	1540	0.6450
0.6781	36.0	1584	0.6437

Framework versions

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