metadata
library_name: peft
tags:
- generated_from_trainer
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
metrics:
- accuracy
- precision
- recall
model-index:
- name: twitter-roberta-base-sentiment-latest-biden-stance-1
results: []
twitter-roberta-base-sentiment-latest-biden-stance-1
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4037
- Accuracy: {'accuracy': 0.5688073394495413}
- Precision: {'precision': 0.5540838852097131}
- Recall: {'recall': 0.6640211640211641}
- F1 Score: {'f1': 0.6040914560770156}
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- 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 | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 0.4339 | 1.0 | 3600 | 0.4173 | {'accuracy': 0.8925} | {'precision': 0.857630979498861} | {'recall': 0.94125} | {'f1': 0.8974970202622169} |
| 0.3848 | 2.0 | 7200 | 0.5757 | {'accuracy': 0.854375} | {'precision': 0.9341500765696784} | {'recall': 0.7625} | {'f1': 0.8396421197522368} |
| 0.4094 | 3.0 | 10800 | 0.3543 | {'accuracy': 0.904375} | {'precision': 0.8655367231638418} | {'recall': 0.9575} | {'f1': 0.9091988130563798} |
| 0.3937 | 4.0 | 14400 | 0.2576 | {'accuracy': 0.91125} | {'precision': 0.9092039800995025} | {'recall': 0.91375} | {'f1': 0.9114713216957606} |
| 0.3401 | 5.0 | 18000 | 0.2671 | {'accuracy': 0.91625} | {'precision': 0.9291237113402062} | {'recall': 0.90125} | {'f1': 0.9149746192893401} |
| 0.352 | 6.0 | 21600 | 0.2429 | {'accuracy': 0.91875} | {'precision': 0.9294871794871795} | {'recall': 0.90625} | {'f1': 0.9177215189873418} |
| 0.2883 | 7.0 | 25200 | 0.2857 | {'accuracy': 0.915625} | {'precision': 0.917189460476788} | {'recall': 0.91375} | {'f1': 0.915466499686913} |
| 0.2894 | 8.0 | 28800 | 0.2270 | {'accuracy': 0.92375} | {'precision': 0.9302030456852792} | {'recall': 0.91625} | {'f1': 0.9231738035264484} |
| 0.282 | 9.0 | 32400 | 0.2518 | {'accuracy': 0.92} | {'precision': 0.9189526184538653} | {'recall': 0.92125} | {'f1': 0.920099875156055} |
| 0.2485 | 10.0 | 36000 | 0.2351 | {'accuracy': 0.92375} | {'precision': 0.9269521410579346} | {'recall': 0.92} | {'f1': 0.9234629861982434} |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2