ExerciseLog

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

• Loss: 8.8515
• Rouge1: 0.2517
• Rouge2: 0.0519
• Rougel: 0.2511
• Rougelsum: 0.2531
• Gen Len: 13.4286

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: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	2	12.0165	0.1562	0.0	0.1562	0.158	12.2857
No log	2.0	4	11.5390	0.1966	0.0	0.1962	0.195	12.8571
No log	3.0	6	11.0965	0.1966	0.0	0.1962	0.195	12.8571
No log	4.0	8	10.7200	0.1833	0.0	0.1837	0.1833	13.7143
No log	5.0	10	10.3922	0.1833	0.0	0.1837	0.1833	13.7143
No log	6.0	12	10.0939	0.2439	0.0519	0.2449	0.2465	14.0
No log	7.0	14	9.8265	0.2439	0.0519	0.2449	0.2465	14.0
No log	8.0	16	9.5947	0.2439	0.0519	0.2449	0.2465	14.0
No log	9.0	18	9.4007	0.2439	0.0519	0.2449	0.2465	14.0
No log	10.0	20	9.2348	0.2439	0.0519	0.2449	0.2465	14.0
No log	11.0	22	9.1026	0.2517	0.0519	0.2511	0.2531	13.4286
No log	12.0	24	8.9968	0.2517	0.0519	0.2511	0.2531	13.4286
No log	13.0	26	8.9197	0.2517	0.0519	0.2511	0.2531	13.4286
No log	14.0	28	8.8720	0.2517	0.0519	0.2511	0.2531	13.4286
No log	15.0	30	8.8515	0.2517	0.0519	0.2511	0.2531	13.4286

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1