README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: sentic-singletTextWcBerta-Fold1
    results: []

sentic-singletTextWcBerta-Fold1

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

• Loss: 0.5627
• Accuracy: 0.7510
• Precision: 0.7401
• Recall: 0.7510
• F1 Score: 0.7431

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Score
No log	1.0	60	0.6901	0.7040	0.7917	0.7040	0.5827
0.501	2.0	120	0.5192	0.7354	0.7138	0.7354	0.6994
0.501	3.0	180	0.5411	0.7270	0.7045	0.7270	0.7048
0.4839	4.0	240	0.8009	0.7029	0.6429	0.7029	0.5822
0.4849	5.0	300	0.5294	0.7374	0.7163	0.7374	0.7066
0.4849	6.0	360	0.5430	0.7301	0.7109	0.7301	0.7132
0.4684	7.0	420	0.5570	0.7312	0.7104	0.7312	0.7110
0.4684	8.0	480	0.5740	0.7416	0.7258	0.7416	0.7006
0.4182	9.0	540	0.6109	0.7458	0.7328	0.7458	0.7054
0.4052	10.0	600	0.5607	0.7490	0.7357	0.7490	0.7383
0.4052	11.0	660	0.5974	0.7510	0.7369	0.7510	0.7182
0.3884	12.0	720	0.5715	0.7333	0.7423	0.7333	0.7370
0.3884	13.0	780	0.5603	0.7552	0.7463	0.7552	0.7492
0.364	14.0	840	0.5610	0.7573	0.7511	0.7573	0.7535
0.3564	15.0	900	0.5627	0.7510	0.7401	0.7510	0.7431

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1