biotech-sentiment-A

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

• Loss: 1.2457
• F1 Macro: 0.3986
• F1 Weighted: 0.5267
• F1 Neg: 0.2606
• F1 Neu: 0.7043
• F1 Pos: 0.2310

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 15
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Macro	F1 Weighted	F1 Neg	F1 Neu	F1 Pos
2.1937	1.0	99	1.1141	0.2786	0.4753	0.0878	0.7480	0.0
2.1524	2.0	198	1.0896	0.2894	0.4880	0.0702	0.7635	0.0345
2.0200	3.0	297	1.0944	0.3613	0.5090	0.1587	0.7144	0.2109
1.7418	4.0	396	1.1543	0.3909	0.5025	0.2984	0.6570	0.2171
1.3048	5.0	495	1.2334	0.3903	0.5119	0.2806	0.6802	0.2102
0.9555	6.0	594	1.3307	0.3970	0.5295	0.2839	0.7129	0.1942
0.9129	7.0	693	1.3240	0.3823	0.5179	0.2214	0.7062	0.2194
0.8084	8.0	792	1.3073	0.4076	0.5224	0.2431	0.6824	0.2972
0.7931	9.0	891	1.2647	0.3940	0.5154	0.2763	0.6836	0.2222
0.7278	10.0	990	1.2731	0.4029	0.5291	0.2810	0.7040	0.2237
0.7109	11.0	1089	1.2543	0.3929	0.5169	0.2692	0.6888	0.2208
0.6961	12.0	1188	1.2447	0.4033	0.5298	0.2576	0.7054	0.2468
0.6989	13.0	1287	1.2457	0.3986	0.5267	0.2606	0.7043	0.2310

Framework versions

• Transformers 5.3.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.2
• Tokenizers 0.22.2