awesome_asqp_model_combined

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

• Loss: 0.2330
• Precision: 0.8343
• Recall: 0.5782
• F1: 0.683

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	263	0.2542	0.6011	0.4297	0.5012
0.3656	2.0	526	0.2148	0.6762	0.4673	0.5527
0.3656	3.0	789	0.1841	0.7486	0.5188	0.6129
0.0925	4.0	1052	0.1815	0.8057	0.5584	0.6596
0.0925	5.0	1315	0.1926	0.8012	0.5505	0.6526
0.0459	6.0	1578	0.1855	0.8091	0.5624	0.6636
0.0459	7.0	1841	0.1753	0.8127	0.5584	0.662
0.0314	8.0	2104	0.2178	0.8161	0.5624	0.6659
0.0314	9.0	2367	0.2206	0.8218	0.5663	0.6706
0.0161	10.0	2630	0.2098	0.8305	0.5723	0.6776
0.0161	11.0	2893	0.2096	0.8257	0.5723	0.676
0.0101	12.0	3156	0.2165	0.8386	0.5762	0.6831
0.0101	13.0	3419	0.2168	0.8252	0.5703	0.6745
0.0082	14.0	3682	0.2290	0.8252	0.5703	0.6745
0.0082	15.0	3945	0.2240	0.8329	0.5723	0.6784
0.0041	16.0	4208	0.2335	0.8333	0.5743	0.68
0.0041	17.0	4471	0.2355	0.8314	0.5762	0.6807
0.0023	18.0	4734	0.2308	0.8343	0.5782	0.683
0.0023	19.0	4997	0.2306	0.8314	0.5762	0.6807
0.0015	20.0	5260	0.2330	0.8343	0.5782	0.683

Framework versions

• Transformers 4.39.1
• Pytorch 2.7.0+cu118
• Datasets 2.12.0
• Tokenizers 0.15.2