distilbert-v0

This model is a fine-tuned version of distilbert/distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.4249
• Precision: 0.0860
• Recall: 0.0883
• F1: 0.0792
• Accuracy: 0.1013

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: 4
• eval_batch_size: 4
• 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	Precision	Recall	F1	Accuracy
No log	1.0	29	2.3644	0.0657	0.0917	0.0241	0.1193
No log	2.0	58	2.3651	0.0979	0.0925	0.0338	0.1195
No log	3.0	87	2.3686	0.0742	0.0923	0.0498	0.1148
No log	4.0	116	2.3718	0.0904	0.0918	0.0619	0.1132
No log	5.0	145	2.3800	0.0893	0.0913	0.0758	0.1082
No log	6.0	174	2.3946	0.0873	0.0915	0.0772	0.1070
No log	7.0	203	2.4064	0.0864	0.0897	0.0780	0.1043
No log	8.0	232	2.4165	0.0872	0.0888	0.0798	0.1019
No log	9.0	261	2.4233	0.0860	0.0885	0.0778	0.1024
No log	10.0	290	2.4249	0.0860	0.0883	0.0792	0.1013

Framework versions

• Transformers 4.36.1
• Pytorch 2.2.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0