distilbert-q-classifier-3

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: 0.3192
• Accuracy: 0.9238
• Precision Weighted: 0.9240
• Recall Weighted: 0.9238
• F1 Weighted: 0.9239
• Precision Macro: 0.9240
• Recall Macro: 0.9241
• F1 Macro: 0.9240

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Weighted	Recall Weighted	F1 Weighted	Precision Macro	Recall Macro	F1 Macro
No log	1.0	68	0.4096	0.8558	0.8587	0.8558	0.8567	0.8588	0.8561	0.8569
No log	2.0	136	0.3029	0.8963	0.8959	0.8963	0.8959	0.8965	0.8964	0.8962
No log	3.0	204	0.2803	0.8914	0.8935	0.8914	0.8898	0.8942	0.8911	0.8900
No log	4.0	272	0.2651	0.9109	0.9132	0.9109	0.9114	0.9135	0.9105	0.9113
No log	5.0	340	0.2840	0.9222	0.9247	0.9222	0.9226	0.9241	0.9231	0.9228
No log	6.0	408	0.2939	0.9254	0.9253	0.9254	0.9253	0.9252	0.9258	0.9254
No log	7.0	476	0.3011	0.9238	0.9242	0.9238	0.9239	0.9241	0.9242	0.9241
0.2181	8.0	544	0.3170	0.9190	0.9199	0.9190	0.9192	0.9201	0.9186	0.9191
0.2181	9.0	612	0.3135	0.9222	0.9224	0.9222	0.9223	0.9225	0.9220	0.9223
0.2181	10.0	680	0.3192	0.9238	0.9240	0.9238	0.9239	0.9240	0.9241	0.9240

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1