Alex034/t5-small-indosum-summary-freeze

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.4247
• Validation Loss: 0.4257
• Train Rouge1: 15.5146
• Train Rouge2: 12.1652
• Train Rougel: 15.3050
• Train Rougelsum: 15.4247
• Train Gen Len: 19.0
• Epoch: 9

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
0.8254	0.5594	15.3909	12.0820	15.1891	15.2970	19.0	0
0.5704	0.5171	15.4204	12.1125	15.2075	15.3336	19.0	1
0.5255	0.4929	15.4384	12.1022	15.2197	15.3470	19.0	2
0.4987	0.4774	15.4411	12.0879	15.2188	15.3411	19.0	3
0.4792	0.4588	15.5215	12.1445	15.2984	15.4176	19.0	4
0.4648	0.4503	15.4935	12.1268	15.2796	15.4024	19.0	5
0.4520	0.4428	15.4938	12.1341	15.2847	15.4083	19.0	6
0.4420	0.4371	15.5749	12.2126	15.3567	15.4759	19.0	7
0.4326	0.4331	15.4931	12.1602	15.2872	15.4079	19.0	8
0.4247	0.4257	15.5146	12.1652	15.3050	15.4247	19.0	9

Framework versions

• Transformers 4.35.0
• TensorFlow 2.13.0
• Datasets 2.15.0
• Tokenizers 0.14.1