distilbert_nbx_all_l

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: 0.4794

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.27	1.0	1949	0.3553
0.4705	2.0	3898	0.3125
0.2474	3.0	5847	0.3118
0.2003	4.0	7796	0.3311
0.0115	5.0	9745	0.3643
0.1731	6.0	11694	0.3928
0.0423	7.0	13643	0.4096
0.0052	8.0	15592	0.4430
0.0001	9.0	17541	0.4746
0.0001	10.0	19490	0.4794

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.19.2
• Tokenizers 0.15.0