distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1492
• Accuracy: {'accuracy': 0.897}

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	63	0.2880	{'accuracy': 0.877}
No log	2.0	126	0.3310	{'accuracy': 0.88}
No log	3.0	189	0.3370	{'accuracy': 0.89}
No log	4.0	252	0.4173	{'accuracy': 0.888}
No log	5.0	315	0.4930	{'accuracy': 0.891}
No log	6.0	378	0.6000	{'accuracy': 0.881}
No log	7.0	441	0.6323	{'accuracy': 0.887}
0.1522	8.0	504	0.7372	{'accuracy': 0.885}
0.1522	9.0	567	0.8241	{'accuracy': 0.886}
0.1522	10.0	630	0.8152	{'accuracy': 0.889}
0.1522	11.0	693	0.8553	{'accuracy': 0.888}
0.1522	12.0	756	0.8635	{'accuracy': 0.89}
0.1522	13.0	819	0.9230	{'accuracy': 0.886}
0.1522	14.0	882	0.8972	{'accuracy': 0.883}
0.1522	15.0	945	1.0292	{'accuracy': 0.88}
0.0132	16.0	1008	1.0075	{'accuracy': 0.887}
0.0132	17.0	1071	0.9745	{'accuracy': 0.896}
0.0132	18.0	1134	0.9919	{'accuracy': 0.897}
0.0132	19.0	1197	1.0695	{'accuracy': 0.892}
0.0132	20.0	1260	1.0988	{'accuracy': 0.897}
0.0132	21.0	1323	1.0215	{'accuracy': 0.895}
0.0132	22.0	1386	1.0229	{'accuracy': 0.897}
0.0132	23.0	1449	1.0720	{'accuracy': 0.896}
0.0137	24.0	1512	1.0708	{'accuracy': 0.893}
0.0137	25.0	1575	1.0941	{'accuracy': 0.894}
0.0137	26.0	1638	1.2022	{'accuracy': 0.884}
0.0137	27.0	1701	1.2134	{'accuracy': 0.885}
0.0137	28.0	1764	1.1918	{'accuracy': 0.89}
0.0137	29.0	1827	1.2061	{'accuracy': 0.886}
0.0137	30.0	1890	1.2831	{'accuracy': 0.885}
0.0137	31.0	1953	1.3249	{'accuracy': 0.89}
0.0033	32.0	2016	1.2590	{'accuracy': 0.891}
0.0033	33.0	2079	1.1984	{'accuracy': 0.892}
0.0033	34.0	2142	1.1320	{'accuracy': 0.888}
0.0033	35.0	2205	1.2169	{'accuracy': 0.888}
0.0033	36.0	2268	1.1492	{'accuracy': 0.892}
0.0033	37.0	2331	1.1455	{'accuracy': 0.892}
0.0033	38.0	2394	1.1809	{'accuracy': 0.892}
0.0033	39.0	2457	1.2245	{'accuracy': 0.894}
0.0035	40.0	2520	1.1411	{'accuracy': 0.891}
0.0035	41.0	2583	1.1350	{'accuracy': 0.892}
0.0035	42.0	2646	1.1506	{'accuracy': 0.89}
0.0035	43.0	2709	1.1809	{'accuracy': 0.895}
0.0035	44.0	2772	1.1559	{'accuracy': 0.896}
0.0035	45.0	2835	1.1722	{'accuracy': 0.894}
0.0035	46.0	2898	1.1432	{'accuracy': 0.899}
0.0035	47.0	2961	1.1541	{'accuracy': 0.897}
0.0009	48.0	3024	1.1480	{'accuracy': 0.897}
0.0009	49.0	3087	1.1491	{'accuracy': 0.897}
0.0009	50.0	3150	1.1492	{'accuracy': 0.897}

Framework versions

• PEFT 0.16.0
• Transformers 4.53.1
• Pytorch 2.7.1+cu128
• Datasets 3.6.0
• Tokenizers 0.21.2