file_classifier_v2

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

• Loss: 0.7582
• Accuracy: 0.8294

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	85	3.0707	0.3147
No log	2.0	170	2.4689	0.4794
No log	3.0	255	2.0578	0.5559
No log	4.0	340	1.7652	0.5882
No log	5.0	425	1.5310	0.6382
2.2135	6.0	510	1.3034	0.7382
2.2135	7.0	595	1.1321	0.7235
2.2135	8.0	680	0.9992	0.7441
2.2135	9.0	765	0.9234	0.7824
2.2135	10.0	850	0.8456	0.7529
2.2135	11.0	935	0.7754	0.7824
0.6588	12.0	1020	0.7846	0.7794
0.6588	13.0	1105	0.7418	0.7941
0.6588	14.0	1190	0.7061	0.7941
0.6588	15.0	1275	0.7279	0.8029
0.6588	16.0	1360	0.6775	0.8118
0.6588	17.0	1445	0.7537	0.7882
0.1766	18.0	1530	0.7194	0.8059
0.1766	19.0	1615	0.7150	0.7971
0.1766	20.0	1700	0.7456	0.8147
0.1766	21.0	1785	0.7581	0.8029
0.1766	22.0	1870	0.7447	0.8265
0.1766	23.0	1955	0.7407	0.8353
0.0515	24.0	2040	0.7541	0.8324
0.0515	25.0	2125	0.7601	0.8235
0.0515	26.0	2210	0.7582	0.8206
0.0515	27.0	2295	0.7613	0.8265
0.0515	28.0	2380	0.7588	0.8294
0.0515	29.0	2465	0.7541	0.8294
0.026	30.0	2550	0.7582	0.8294

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1