metadata

license: apache-2.0
base_model: google/t5-v1_1-large
tags:
  - generated_from_trainer
model-index:
  - name: Sentiment-google-t5-v1_1-large-inter_model-shuffle-model_annots_str
    results: []

Sentiment-google-t5-v1_1-large-inter_model-shuffle-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
19.9297	1.0	44	24.0270
17.8061	2.0	88	15.7129
12.1985	3.0	132	9.5557
9.3551	4.0	176	8.8485
8.3343	5.0	220	8.6630
8.1976	6.0	264	8.5339
8.0013	7.0	308	8.4201
7.8655	8.0	352	8.2116
7.4859	9.0	396	7.6870
7.122	10.0	440	7.3664
6.9723	11.0	484	7.2356
6.9118	12.0	528	7.1352
6.7457	13.0	572	6.9906
1.1378	14.0	616	1.0087
1.082	15.0	660	1.0024
1.0727	16.0	704	1.0054
1.0694	17.0	748	0.9990
1.0636	18.0	792	0.9929
1.053	19.0	836	0.9968
1.0486	20.0	880	0.9923
1.0446	21.0	924	0.9907
1.0551	22.0	968	0.9910
1.0583	23.0	1012	0.9896
1.0463	24.0	1056	0.9915
1.049	25.0	1100	0.9883
1.0603	26.0	1144	0.9879
1.0221	27.0	1188	0.9890
1.0526	28.0	1232	0.9904
1.0529	29.0	1276	0.9857
1.0373	30.0	1320	0.9888
1.0604	31.0	1364	0.9878
1.0393	32.0	1408	0.9872

Framework versions

Transformers 4.34.0
Pytorch 2.1.0+cu121
Datasets 2.14.5
Tokenizers 0.14.1