nci-scorer-multitask

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1511

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: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.3145	100	0.2901
No log	0.6289	200	0.2231
No log	0.9434	300	0.1861
No log	1.2579	400	0.1721
0.239	1.5723	500	0.1709
0.239	1.8868	600	0.1727
0.239	2.2013	700	0.1549
0.239	2.5157	800	0.1491
0.239	2.8302	900	0.1453
0.1452	3.1447	1000	0.1482
0.1452	3.4591	1100	0.1490
0.1452	3.7736	1200	0.1462

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1