test_TwoWayLoss_25K_bs64_P4_N1

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

• Loss: 8.8668
• Accuracy: 0.5430
• Precision: 0.0114
• Recall: 0.5359
• F1: 0.0224
• Hamming: 0.4570

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Hamming
8.9097	0.0	5	8.8974	0.5287	0.0107	0.5189	0.0210	0.4713
8.1387	0.0	10	8.8668	0.5430	0.0114	0.5359	0.0224	0.4570

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.7.1
• Tokenizers 0.14.1