Sentiment-google-t5-v1_1-large-intra_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: 1.6025

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
20.2785	1.0	44	24.1630
16.5089	2.0	88	12.6240
12.1856	3.0	132	9.5483
9.6054	4.0	176	9.1792
8.6106	5.0	220	8.9367
8.4152	6.0	264	8.7252
8.3046	7.0	308	8.5101
7.8895	8.0	352	8.1848
7.7099	9.0	396	7.7711
7.3027	10.0	440	7.4309
7.1553	11.0	484	7.2568
6.9202	12.0	528	7.1566
6.8527	13.0	572	7.0624
6.5631	14.0	616	6.8983
1.0138	15.0	660	0.7973
0.8985	16.0	704	0.7822
0.8793	17.0	748	0.7791
0.8737	18.0	792	0.7799
0.8562	19.0	836	0.7812
0.8563	20.0	880	0.7742
0.8498	21.0	924	0.7738
0.8316	22.0	968	0.7683
0.8281	23.0	1012	0.7688
0.8314	24.0	1056	0.7732
0.8161	25.0	1100	0.7660
0.8273	26.0	1144	0.7634
0.8314	27.0	1188	0.7622
0.828	28.0	1232	0.7625
0.8161	29.0	1276	0.7605
0.812	30.0	1320	0.7602
0.8126	31.0	1364	0.7580
0.8021	32.0	1408	0.7649
0.7973	33.0	1452	0.7588
0.8076	34.0	1496	0.7569
0.819	35.0	1540	0.7559
0.8069	36.0	1584	0.7540
0.8042	37.0	1628	0.7546
0.8054	38.0	1672	0.7579
0.8049	39.0	1716	0.7584

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.6.1
• Tokenizers 0.14.1