MikeGreen2710/street_alley_classification

training_with_callbacks

This model is a fine-tuned version of MikeGreen2710/mlm_listing_1.79 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3694
• F1: 0.9412

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: 24
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.3883	1.0	140	0.2135	0.9032
0.196	2.0	280	0.2403	0.9028
0.1268	3.0	420	0.2044	0.9251
0.0797	4.0	560	0.2866	0.9245
0.0506	5.0	700	0.3358	0.9232
0.0283	6.0	840	0.3247	0.9349
0.0219	7.0	980	0.3160	0.9355
0.0173	8.0	1120	0.3366	0.9384
0.0112	9.0	1260	0.3360	0.9409
0.0147	10.0	1400	0.3523	0.9384
0.0087	11.0	1540	0.3694	0.9412
0.0075	12.0	1680	0.3761	0.9381
0.0041	13.0	1820	0.4205	0.9323
0.0059	14.0	1960	0.4012	0.9409
0.0058	15.0	2100	0.4717	0.9269
0.0027	16.0	2240	0.4644	0.9325
0.0033	17.0	2380	0.4491	0.9353
0.0011	18.0	2520	0.4494	0.9353
0.0025	19.0	2660	0.4440	0.9381
0.0012	20.0	2800	0.4482	0.9381

Framework versions

• Transformers 4.41.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1