distilroberta-fast-surgical

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

• Loss: 0.0299
• Accuracy: 0.9876
• F1: 0.9876

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: 8e-06
• train_batch_size: 64
• 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_steps: 0.1
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.1681	200	0.2195	0.8762	0.8746
No log	0.3361	400	0.0636	0.9704	0.9704
0.2821	0.5042	600	0.0600	0.9654	0.9653
0.2821	0.6723	800	0.0596	0.9655	0.9655
0.0404	0.8403	1000	0.1019	0.9456	0.9455
0.0404	1.0084	1200	0.0560	0.9734	0.9734
0.0404	1.1765	1400	0.0366	0.9842	0.9842
0.0253	1.3445	1600	0.0312	0.9875	0.9875
0.0253	1.5126	1800	0.0298	0.9878	0.9878
0.0201	1.6807	2000	0.0649	0.9682	0.9682
0.0201	1.8487	2200	0.0625	0.9697	0.9697

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2