results-t5base-of-concluding_statements

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

• Loss: 0.3235
• Rouge1: 0.4154
• Rouge2: 0.1527
• Rougel: 0.3348
• Gen Len: 60.3511

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
0.3584	0.4950	200	0.3740	0.4033	0.1406	0.3201	59.3288
0.3465	0.9901	400	0.3346	0.4122	0.1494	0.3303	60.3201
0.3157	1.4851	600	0.3281	0.4152	0.1525	0.3338	60.3498
0.3352	1.9802	800	0.3254	0.4155	0.153	0.3354	60.3511
0.338	2.4752	1000	0.3242	0.4152	0.1523	0.3344	60.3511
0.3181	2.9703	1200	0.3235	0.4154	0.1527	0.3348	60.3511

Framework versions

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