summarizing_lit_only

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.4906
• Rouge1: 0.1089
• Rouge2: 0.0191
• Rougel: 0.0871
• Rougelsum: 0.0874
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 72
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	19	4.3297	0.1055	0.0162	0.0847	0.0847	19.0
No log	2.0	38	3.8465	0.1108	0.0168	0.0886	0.0887	19.0
No log	3.0	57	3.6785	0.1083	0.0156	0.0853	0.0854	19.0
No log	4.0	76	3.5973	0.1029	0.0141	0.083	0.0829	19.0
No log	5.0	95	3.5518	0.1083	0.0174	0.0876	0.0878	19.0
No log	6.0	114	3.5261	0.1089	0.0178	0.0882	0.0886	19.0
No log	7.0	133	3.5093	0.1093	0.0178	0.0875	0.0879	19.0
No log	8.0	152	3.4986	0.1104	0.0187	0.088	0.0884	19.0
No log	9.0	171	3.4926	0.1093	0.0187	0.0875	0.0876	19.0
No log	10.0	190	3.4906	0.1089	0.0191	0.0871	0.0874	19.0

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3