results_t5base

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

• Loss: 0.3046
• Rouge1: 0.9199
• Rouge2: 0.8588
• Rougel: 0.9042
• Gen Len: 231.4427

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
0.3681	0.8969	200	0.3763	0.9035	0.8333	0.8852	231.2202
0.4231	1.7937	400	0.3336	0.9103	0.8424	0.8934	231.4427
0.3816	2.6906	600	0.3185	0.9132	0.8481	0.8968	231.4427
0.2074	3.5874	800	0.3097	0.9155	0.8514	0.8997	231.4427
0.3367	4.4843	1000	0.3086	0.9169	0.8528	0.9006	231.4427
0.2748	5.3812	1200	0.3060	0.9179	0.8549	0.9019	231.4427
0.2609	6.2780	1400	0.3038	0.919	0.8564	0.903	231.4427
0.2362	7.1749	1600	0.3049	0.9194	0.8573	0.9033	231.4427
0.206	8.0717	1800	0.3049	0.9198	0.8589	0.9042	231.4427
0.1963	8.9686	2000	0.3038	0.9202	0.8589	0.9044	231.4427
0.2273	9.8655	2200	0.3046	0.9199	0.8588	0.9042	231.4427

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0