README.md

metadata

license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: EVALutionRelationTrain-5
    results: []

EVALutionRelationTrain-5

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

• Loss: 0.6933
• Accuracy: 0.5
• Precision: 0.5
• Recall: 1.0
• F1: 0.6667

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
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	0.35	100	0.7119	0.5	0.0	0.0	0.0
No log	0.71	200	0.7123	0.5	0.5	1.0	0.6667
No log	1.06	300	0.6936	0.5	0.5	1.0	0.6667
No log	1.42	400	0.6933	0.5	0.5	1.0	0.6667
0.6993	1.77	500	0.6945	0.5	0.0	0.0	0.0
0.6993	2.13	600	0.6948	0.5	0.0	0.0	0.0
0.6993	2.48	700	0.6999	0.5	0.5	1.0	0.6667
0.6993	2.84	800	0.6943	0.5	0.0	0.0	0.0
0.6993	3.19	900	0.6951	0.5	0.5	1.0	0.6667
0.698	3.55	1000	0.6945	0.5	0.0	0.0	0.0
0.698	3.9	1100	0.6956	0.5	0.0	0.0	0.0
0.698	4.26	1200	0.6933	0.5	0.5	1.0	0.6667
0.698	4.61	1300	0.6941	0.5	0.5	1.0	0.6667
0.698	4.96	1400	0.6934	0.5	0.0	0.0	0.0
0.6964	5.32	1500	0.6933	0.5	0.0	0.0	0.0
0.6964	5.67	1600	0.6943	0.5	0.0	0.0	0.0
0.6964	6.03	1700	0.6946	0.5	0.0	0.0	0.0
0.6964	6.38	1800	0.6932	0.5	0.0	0.0	0.0
0.6964	6.74	1900	0.6952	0.5	0.0	0.0	0.0
0.6952	7.09	2000	0.6934	0.5	0.5	1.0	0.6667
0.6952	7.45	2100	0.6935	0.5	0.5	1.0	0.6667
0.6952	7.8	2200	0.6933	0.5	0.5	1.0	0.6667

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1