Modelpublic

suraj2dsai/business-news-generator_with_lora

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face

1likes13downloads

Model Card

business-news-generatorwithlora

This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 2.9387

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: 0.0005
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: cosine
—num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0267	100	3.4433
3.4968	0.0533	200	3.3315
3.4968	0.08	300	3.2736
3.2813	0.1067	400	3.2348
3.2813	0.1333	500	3.2063
3.1403	0.16	600	3.1827
3.1403	0.1867	700	3.1660
3.1403	0.2133	800	3.1481
3.1403	0.24	900	3.1337
3.0689	0.2667	1000	3.1186
3.0689	0.2933	1100	3.1089
3.096	0.32	1200	3.1015
3.096	0.3467	1300	3.0889
3.0381	0.3733	1400	3.0811
3.0381	0.4	1500	3.0747
2.9869	0.4267	1600	3.0651
2.9869	0.4533	1700	3.0584
3.0096	0.48	1800	3.0539
3.0096	0.5067	1900	3.0451
2.9873	0.5333	2000	3.0419
2.9873	0.56	2100	3.0331
3.0418	0.5867	2200	3.0295
3.0418	0.6133	2300	3.0241
3.0136	0.64	2400	3.0200
3.0136	0.6667	2500	3.0148
2.9712	0.6933	2600	3.0115
2.9712	0.72	2700	3.0060
2.977	0.7467	2800	3.0017
2.977	0.7733	2900	2.9983
2.9404	0.8	3000	2.9953
2.9404	0.8267	3100	2.9923
2.9519	0.8533	3200	2.9875
2.9519	0.88	3300	2.9879
2.9498	0.9067	3400	2.9817
2.9498	0.9333	3500	2.9791
2.9433	0.96	3600	2.9775
2.9433	0.9867	3700	2.9738
2.9084	1.0133	3800	2.9719
2.9084	1.04	3900	2.9696
2.8999	1.0667	4000	2.9674
2.8999	1.0933	4100	2.9652
2.897	1.12	4200	2.9637
2.897	1.1467	4300	2.9620
2.8921	1.1733	4400	2.9602
2.8921	1.2	4500	2.9582
2.8803	1.2267	4600	2.9576
2.8803	1.2533	4700	2.9554
2.8813	1.28	4800	2.9529
2.8813	1.3067	4900	2.9524
2.8777	1.3333	5000	2.9515
2.8777	1.3600	5100	2.9492
2.8778	1.3867	5200	2.9494
2.8778	1.4133	5300	2.9474
2.8516	1.44	5400	2.9461
2.8516	1.4667	5500	2.9457
2.8767	1.4933	5600	2.9444
2.8767	1.52	5700	2.9444
2.882	1.5467	5800	2.9437
2.882	1.5733	5900	2.9426
2.8682	1.6	6000	2.9418
2.8682	1.6267	6100	2.9410
2.8519	1.6533	6200	2.9408
2.8519	1.6800	6300	2.9405
2.859	1.7067	6400	2.9403
2.859	1.7333	6500	2.9397
2.948	1.76	6600	2.9394
2.948	1.7867	6700	2.9391
2.8633	1.8133	6800	2.9390
2.8633	1.8400	6900	2.9388
2.8889	1.8667	7000	2.9388
2.8889	1.8933	7100	2.9387
2.857	1.92	7200	2.9387
2.857	1.9467	7300	2.9387
2.8578	1.9733	7400	2.9387
2.8578	2.0	7500	2.9387

Framework versions

—PEFT 0.18.0
—Transformers 4.57.3
—Pytorch 2.9.0+cu126
—Datasets 4.0.0
—Tokenizers 0.22.1