finetuned-endpoints_classif_test-4_13_1246

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

• Loss: 0.4666
• F1: 0.8717
• Accuracy: 0.8667
• Precision: 0.9019
• Recall: 0.8667

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: 5e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy	Precision	Recall
2.0932	1.0	13	1.8419	0.3116	0.3667	0.3823	0.3667
1.683	2.0	26	1.5969	0.3338	0.4	0.4632	0.4
1.3516	3.0	39	1.3390	0.5505	0.5667	0.6117	0.5667
1.0476	4.0	52	1.0331	0.6773	0.7	0.7741	0.7
0.6697	5.0	65	0.8544	0.7635	0.7667	0.8483	0.7667
0.417	6.0	78	0.5855	0.8068	0.8	0.8722	0.8
0.2449	7.0	91	0.5300	0.8409	0.8333	0.89	0.8333
0.1387	8.0	104	0.5291	0.8717	0.8667	0.9019	0.8667
0.0898	9.0	117	0.4517	0.8717	0.8667	0.9019	0.8667
0.0605	10.0	130	0.4855	0.8717	0.8667	0.9019	0.8667
0.0474	11.0	143	0.4727	0.8717	0.8667	0.9019	0.8667
0.0436	12.0	156	0.4666	0.8717	0.8667	0.9019	0.8667

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3