product_title_encoder-product

This model is a fine-tuned version of sfuller14/product_title_encoder on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5623

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: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	109	6.3979
No log	2.0	218	5.5030
No log	3.0	327	4.9871
6.0477	4.0	436	4.6591
6.0477	5.0	545	4.4086
6.0477	6.0	654	4.2139
6.0477	7.0	763	4.0430
4.4808	8.0	872	3.9297
4.4808	9.0	981	3.8503
4.4808	10.0	1090	3.7207
4.4808	11.0	1199	3.6599
3.9736	12.0	1308	3.5738
3.9736	13.0	1417	3.5111
3.9736	14.0	1526	3.4656
3.9736	15.0	1635	3.4296
3.6934	16.0	1744	3.3670
3.6934	17.0	1853	3.3428
3.6934	18.0	1962	3.2965
3.6934	19.0	2071	3.2606
3.5021	20.0	2180	3.2121
3.5021	21.0	2289	3.1882
3.5021	22.0	2398	3.1584
3.5021	23.0	2507	3.1498
3.3712	24.0	2616	3.1109
3.3712	25.0	2725	3.0827
3.3712	26.0	2834	3.0578
3.3712	27.0	2943	3.0819
3.2644	28.0	3052	3.0450
3.2644	29.0	3161	2.9785
3.2644	30.0	3270	2.9864
3.2644	31.0	3379	2.9808
3.1738	32.0	3488	2.9380
3.1738	33.0	3597	2.9328
3.1738	34.0	3706	2.9362
3.1738	35.0	3815	2.8941
3.0957	36.0	3924	2.8929
3.0957	37.0	4033	2.8685
3.0957	38.0	4142	2.8574
3.0957	39.0	4251	2.8395
3.0363	40.0	4360	2.8484
3.0363	41.0	4469	2.8052
3.0363	42.0	4578	2.8013
3.0363	43.0	4687	2.8127
2.9823	44.0	4796	2.7729
2.9823	45.0	4905	2.7911
2.9823	46.0	5014	2.7684
2.9823	47.0	5123	2.7790
2.9399	48.0	5232	2.7390
2.9399	49.0	5341	2.7378
2.9399	50.0	5450	2.7385
2.9399	51.0	5559	2.7039
2.9012	52.0	5668	2.6999
2.9012	53.0	5777	2.7039
2.9012	54.0	5886	2.6759
2.9012	55.0	5995	2.7022
2.8656	56.0	6104	2.6945
2.8656	57.0	6213	2.7010
2.8656	58.0	6322	2.6958
2.8656	59.0	6431	2.6952
2.8356	60.0	6540	2.6516
2.8356	61.0	6649	2.6553
2.8356	62.0	6758	2.6495
2.8356	63.0	6867	2.6643
2.8152	64.0	6976	2.6281
2.8152	65.0	7085	2.6341
2.8152	66.0	7194	2.6686
2.8152	67.0	7303	2.6327
2.7915	68.0	7412	2.6366
2.7915	69.0	7521	2.6128
2.7915	70.0	7630	2.6259
2.7915	71.0	7739	2.6307
2.7726	72.0	7848	2.6111
2.7726	73.0	7957	2.6427
2.7726	74.0	8066	2.5772
2.7726	75.0	8175	2.5984
2.7524	76.0	8284	2.5796
2.7524	77.0	8393	2.6209
2.7524	78.0	8502	2.5897
2.7524	79.0	8611	2.5966
2.7455	80.0	8720	2.5836
2.7455	81.0	8829	2.5877
2.7455	82.0	8938	2.5855
2.7455	83.0	9047	2.5869
2.731	84.0	9156	2.5656
2.731	85.0	9265	2.5663
2.731	86.0	9374	2.5568
2.731	87.0	9483	2.5749
2.723	88.0	9592	2.5823
2.723	89.0	9701	2.5743
2.723	90.0	9810	2.5679
2.723	91.0	9919	2.5561
2.7136	92.0	10028	2.5768
2.7136	93.0	10137	2.5697
2.7136	94.0	10246	2.5489
2.7136	95.0	10355	2.5846
2.7088	96.0	10464	2.5686
2.7088	97.0	10573	2.5712
2.7088	98.0	10682	2.5691
2.7088	99.0	10791	2.5900
2.7075	100.0	10900	2.5617

Framework versions

• Transformers 4.40.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1