intent_trading

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1741
• Accuracy: 0.9548

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	227	1.5904	0.7689
No log	2.0	454	1.0086	0.8670
1.6528	3.0	681	0.6706	0.9055
1.6528	4.0	908	0.4376	0.9518
0.6124	5.0	1135	0.2966	0.9551
0.6124	6.0	1362	0.2373	0.9504
0.2536	7.0	1589	0.1967	0.9537
0.2536	8.0	1816	0.1666	0.9565
0.1476	9.0	2043	0.1642	0.9543
0.1476	10.0	2270	0.1570	0.9551
0.1476	11.0	2497	0.1500	0.9543
0.1067	12.0	2724	0.1469	0.9548
0.1067	13.0	2951	0.1458	0.9557
0.0817	14.0	3178	0.1409	0.9540
0.0817	15.0	3405	0.1426	0.9595
0.0709	16.0	3632	0.1418	0.9540
0.0709	17.0	3859	0.1416	0.9557
0.0631	18.0	4086	0.1373	0.9581
0.0631	19.0	4313	0.1458	0.9559
0.0557	20.0	4540	0.1391	0.9559
0.0557	21.0	4767	0.1526	0.9518
0.0557	22.0	4994	0.1511	0.9529
0.0495	23.0	5221	0.1578	0.9526
0.0495	24.0	5448	0.1360	0.9568
0.0443	25.0	5675	0.1451	0.9565
0.0443	26.0	5902	0.1477	0.9562
0.0419	27.0	6129	0.1624	0.9540
0.0419	28.0	6356	0.1659	0.9537
0.0371	29.0	6583	0.1607	0.9548
0.0371	30.0	6810	0.1638	0.9543
0.035	31.0	7037	0.1655	0.9529
0.035	32.0	7264	0.1662	0.9562
0.035	33.0	7491	0.1702	0.9532
0.033	34.0	7718	0.1662	0.9562
0.033	35.0	7945	0.1667	0.9532
0.0309	36.0	8172	0.1794	0.9554
0.0309	37.0	8399	0.1756	0.9546
0.0292	38.0	8626	0.1722	0.9559
0.0292	39.0	8853	0.1706	0.9559
0.0281	40.0	9080	0.1741	0.9548

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.19.1