afx-grouping-model

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0154
• Accuracy: 1.0

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	6	0.9060	0.7674
No log	2.0	12	0.7408	0.7674
No log	3.0	18	0.6209	0.8023
No log	4.0	24	0.5090	0.8023
No log	5.0	30	0.4159	0.8488
No log	6.0	36	0.3407	0.8837
No log	7.0	42	0.2719	0.9535
No log	8.0	48	0.2218	0.9535
No log	9.0	54	0.1801	0.9535
No log	10.0	60	0.1476	0.9535
No log	11.0	66	0.1164	0.9767
No log	12.0	72	0.0937	0.9884
No log	13.0	78	0.0723	1.0
No log	14.0	84	0.0604	1.0
No log	15.0	90	0.0485	1.0
No log	16.0	96	0.0395	1.0
No log	17.0	102	0.0339	1.0
No log	18.0	108	0.0307	1.0
No log	19.0	114	0.0262	1.0
No log	20.0	120	0.0240	1.0
No log	21.0	126	0.0215	1.0
No log	22.0	132	0.0200	1.0
No log	23.0	138	0.0189	1.0
No log	24.0	144	0.0178	1.0
No log	25.0	150	0.0170	1.0
No log	26.0	156	0.0164	1.0
No log	27.0	162	0.0160	1.0
No log	28.0	168	0.0157	1.0
No log	29.0	174	0.0155	1.0
No log	30.0	180	0.0154	1.0

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1
• Datasets 2.14.5
• Tokenizers 0.13.3