README.md

metadata

license: mit
base_model: xlnet-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlnet-case-25
    results: []

xlnet-case-25

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

• Loss: 0.5796
• Precision: 0.9156
• Recall: 0.9067
• F1: 0.9103
• Accuracy: 0.9067

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: 224
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	44	0.3254	0.8710	0.8533	0.8494	0.8533
No log	2.0	88	0.2517	0.8653	0.8933	0.8768	0.8933
No log	3.0	132	0.2558	0.8497	0.8933	0.8690	0.8933
No log	4.0	176	0.3633	0.8782	0.8933	0.8803	0.8933
No log	5.0	220	0.3514	0.8978	0.9067	0.9008	0.9067
No log	6.0	264	0.4314	0.8922	0.8933	0.8927	0.8933
No log	7.0	308	0.5872	0.9079	0.8733	0.8869	0.8733
No log	8.0	352	0.4349	0.9081	0.9067	0.9073	0.9067
No log	9.0	396	0.4632	0.9188	0.9133	0.9156	0.9133
No log	10.0	440	0.4815	0.9156	0.9133	0.9143	0.9133
No log	11.0	484	0.4972	0.9156	0.9133	0.9143	0.9133
0.0831	12.0	528	0.5025	0.9317	0.92	0.9240	0.92
0.0831	13.0	572	0.5105	0.9156	0.9133	0.9143	0.9133
0.0831	14.0	616	0.5225	0.9156	0.9133	0.9143	0.9133
0.0831	15.0	660	0.6110	0.9036	0.88	0.8892	0.88
0.0831	16.0	704	0.5772	0.9156	0.9067	0.9103	0.9067
0.0831	17.0	748	0.5688	0.9156	0.9067	0.9103	0.9067
0.0831	18.0	792	0.5698	0.9156	0.9067	0.9103	0.9067
0.0831	19.0	836	0.5712	0.9156	0.9067	0.9103	0.9067
0.0831	20.0	880	0.5770	0.9156	0.9067	0.9103	0.9067
0.0831	21.0	924	0.5826	0.9156	0.9067	0.9103	0.9067
0.0831	22.0	968	0.5803	0.9156	0.9067	0.9103	0.9067
0.0001	23.0	1012	0.5788	0.9156	0.9067	0.9103	0.9067
0.0001	24.0	1056	0.5795	0.9156	0.9067	0.9103	0.9067
0.0001	25.0	1100	0.5796	0.9156	0.9067	0.9103	0.9067

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0