mono_self_tig

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: 1.2721
• Accuracy: {'accuracy': 0.14912528216704288}

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
4.9645	2.3810	100	2.6627	{'accuracy': 0.11526523702031603}
2.5095	4.7619	200	1.6713	{'accuracy': 0.13896726862302483}
1.9139	7.1429	300	1.5532	{'accuracy': 0.14207110609480814}
1.775	9.5238	400	1.4973	{'accuracy': 0.14235327313769752}
1.7046	11.9048	500	1.4564	{'accuracy': 0.1433408577878104}
1.6074	14.2857	600	1.4001	{'accuracy': 0.14418735891647855}
1.5531	16.6667	700	1.3427	{'accuracy': 0.14672686230248308}
1.4773	19.0476	800	1.3227	{'accuracy': 0.14771444695259595}
1.4325	21.4286	900	1.3025	{'accuracy': 0.1488431151241535}
1.4142	23.8095	1000	1.2946	{'accuracy': 0.14813769751693}
1.392	26.1905	1100	1.2749	{'accuracy': 0.1488431151241535}
1.3836	28.5714	1200	1.2721	{'accuracy': 0.14912528216704288}

Framework versions

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