Sentiment-google-t5-v1_1-large-intra_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: 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
19.7788	1.0	44	23.9563
15.9283	2.0	88	11.8553
10.0222	3.0	132	9.4991
8.9528	4.0	176	9.0638
8.4671	5.0	220	8.7748
8.189	6.0	264	8.6661
8.2203	7.0	308	8.5367
7.9303	8.0	352	8.1591
7.5313	9.0	396	7.7616
7.3476	10.0	440	7.4948
7.1959	11.0	484	7.3478
6.9493	12.0	528	7.2555
6.8091	13.0	572	7.1311
0.9281	14.0	616	0.6867
0.7487	15.0	660	0.6683
0.7383	16.0	704	0.6678
0.7336	17.0	748	0.6632
0.7256	18.0	792	0.6566
0.7344	19.0	836	0.6584
0.7237	20.0	880	0.6619
0.7204	21.0	924	0.6619
0.7088	22.0	968	0.6566
0.7017	23.0	1012	0.6556
0.7136	24.0	1056	0.6566
0.7078	25.0	1100	0.6582
0.7165	26.0	1144	0.6557
0.706	27.0	1188	0.6559
0.7146	28.0	1232	0.6537
0.7138	29.0	1276	0.6546
0.706	30.0	1320	0.6559
0.7067	31.0	1364	0.6567
0.7137	32.0	1408	0.6599
0.7	33.0	1452	0.6550

Framework versions

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