README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: patentClassfication2
    results: []

patentClassfication2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5108
• Accuracy: 0.7492
• F1: 0.7710
• Precision: 0.7025
• Recall: 0.8543

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: 2.329139e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 18
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 478
• num_epochs: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5264	1.0	1110	0.5108	0.7492	0.7710	0.7025	0.8543
0.4405	2.0	2220	0.5624	0.7463	0.7295	0.7710	0.6923
0.2972	3.0	3330	0.7480	0.7394	0.7224	0.7629	0.6859
0.1733	4.0	4440	0.7975	0.7328	0.7316	0.7266	0.7367
0.1242	5.0	5550	1.3035	0.7314	0.7396	0.7101	0.7716
0.0866	6.0	6660	1.6628	0.7272	0.7110	0.7464	0.6788
0.0493	7.0	7770	1.7728	0.7321	0.7285	0.7297	0.7274
0.0313	8.0	8880	2.0279	0.7383	0.7325	0.7402	0.7249
0.0187	9.0	9990	2.1956	0.7375	0.7445	0.7173	0.7739
0.0148	10.0	11100	2.2491	0.7355	0.7366	0.7256	0.7479
0.0129	11.0	12210	2.2694	0.7350	0.7378	0.7220	0.7543

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.0
• Datasets 2.14.4
• Tokenizers 0.13.3