README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - accuracy
  - f1
model-index:
  - name: electricidad-base-ft-diagTrast
    results: []

electricidad-base-ft-diagTrast

This model is a fine-tuned version of mrm8488/electricidad-base-discriminator on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2111
• Precision: 0.9653
• Recall: 0.9627
• Accuracy: 0.9627
• F1: 0.9622

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: 8
• eval_batch_size: 16
• 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	Accuracy	F1
No log	1.0	150	0.9281	0.7399	0.6567	0.6567	0.5989
No log	2.0	300	0.4736	0.8680	0.8582	0.8582	0.8581
No log	3.0	450	0.2584	0.9215	0.9104	0.9104	0.9110
0.6826	4.0	600	0.3336	0.9190	0.9104	0.9104	0.9036
0.6826	5.0	750	0.2194	0.9458	0.9403	0.9403	0.9398
0.6826	6.0	900	0.1984	0.9451	0.9403	0.9403	0.9397
0.0262	7.0	1050	0.2012	0.9582	0.9552	0.9552	0.9552
0.0262	8.0	1200	0.2272	0.9366	0.9328	0.9328	0.9319
0.0262	9.0	1350	0.2111	0.9653	0.9627	0.9627	0.9622
0.0044	10.0	1500	0.2156	0.9587	0.9552	0.9552	0.9543

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3