ec_classfication_0502_distilbert_base_uncased

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: 0.9120
• F1: 0.8222

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	59	0.6145	0.5753
No log	2.0	118	0.5000	0.7619
No log	3.0	177	0.5990	0.7
No log	4.0	236	0.5030	0.8235
No log	5.0	295	0.6379	0.8478
No log	6.0	354	0.6739	0.8478
No log	7.0	413	0.7597	0.8090
No log	8.0	472	0.7854	0.8222
0.1878	9.0	531	0.8594	0.8222
0.1878	10.0	590	0.8947	0.8090
0.1878	11.0	649	0.9086	0.8222
0.1878	12.0	708	0.9130	0.8222
0.1878	13.0	767	0.9070	0.8222
0.1878	14.0	826	0.9117	0.8222
0.1878	15.0	885	0.9120	0.8222

Framework versions

• Transformers 4.27.3
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.2