mono_self_amh

This model is a fine-tuned version of castorini/afriteva_v2_base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0401
• Accuracy: {'accuracy': 0.21588385158087275}

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: 64
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.3329	1.1655	500	1.7980	{'accuracy': 0.1844460412856023}
1.831	2.3310	1000	1.5109	{'accuracy': 0.19700483407368696}
1.5538	3.4965	1500	1.3840	{'accuracy': 0.20110399790958974}
1.409	4.6620	2000	1.2974	{'accuracy': 0.20477854716488111}
1.3144	5.8275	2500	1.2348	{'accuracy': 0.2073588973085968}
1.2412	6.9930	3000	1.1953	{'accuracy': 0.2086000783903841}
1.1535	8.1585	3500	1.1696	{'accuracy': 0.2093349882414424}
1.1184	9.3240	4000	1.1589	{'accuracy': 0.21016788607264175}
1.0845	10.4895	4500	1.1263	{'accuracy': 0.21158871178468774}
1.0656	11.6550	5000	1.1136	{'accuracy': 0.21162137444473478}
1.0409	12.8205	5500	1.1089	{'accuracy': 0.2121276456754638}
1.0193	13.9860	6000	1.1017	{'accuracy': 0.21263391690619285}
0.9882	15.1515	6500	1.0911	{'accuracy': 0.2130748628168278}
0.9713	16.3170	7000	1.0774	{'accuracy': 0.21389142931800365}
0.9578	17.4825	7500	1.0679	{'accuracy': 0.213744447347792}
0.9462	18.6480	8000	1.0619	{'accuracy': 0.21447935719885028}
0.937	19.8135	8500	1.0629	{'accuracy': 0.21477332113927358}
0.9259	20.9790	9000	1.0580	{'accuracy': 0.21457734517899138}
0.9075	22.1445	9500	1.0550	{'accuracy': 0.21505095374967337}
0.9032	23.3100	10000	1.0549	{'accuracy': 0.21513261039979095}
0.894	24.4755	10500	1.0494	{'accuracy': 0.21568787562059055}
0.8849	25.6410	11000	1.0435	{'accuracy': 0.21554089365037887}
0.8825	26.8065	11500	1.0481	{'accuracy': 0.21575320094068462}
0.8758	27.9720	12000	1.0400	{'accuracy': 0.21568787562059055}
0.8672	29.1375	12500	1.0401	{'accuracy': 0.21588385158087275}

Framework versions

• PEFT 0.7.1
• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.15.0
• Tokenizers 0.19.1