Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Instructions to use IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds") model = AutoModelForSequenceClassification.from_pretrained("IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds", device_map="auto") - Notebooks
- Google Colab
- Kaggle
sentiment-analysis-roberta-base-V1.9_ima_ds
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3483
- Accuracy: 0.5693
- Precision Macro: 0.5275
- Recall Macro: 0.5324
- F1 Macro: 0.5206
- Precision Weighted: 0.5879
- Recall Weighted: 0.5693
- F1 Weighted: 0.5668
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: 32
- eval_batch_size: 8
- seed: 3407
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | Precision Weighted | Recall Weighted | F1 Weighted |
|---|---|---|---|---|---|---|---|---|---|---|
| 1.6229 | 0.4 | 20 | 1.6164 | 0.2670 | 0.0534 | 0.2 | 0.0843 | 0.0713 | 0.2670 | 0.1125 |
| 1.5993 | 0.8 | 40 | 1.6014 | 0.2393 | 0.0861 | 0.2594 | 0.1258 | 0.0948 | 0.2393 | 0.1340 |
| 1.4284 | 1.2 | 60 | 1.4381 | 0.3476 | 0.4967 | 0.3845 | 0.3198 | 0.5513 | 0.3476 | 0.3430 |
| 1.3692 | 1.6 | 80 | 1.3492 | 0.3829 | 0.4535 | 0.4169 | 0.3788 | 0.5300 | 0.3829 | 0.4068 |
| 1.2286 | 2.0 | 100 | 1.3083 | 0.4257 | 0.4991 | 0.4568 | 0.4257 | 0.5720 | 0.4257 | 0.4611 |
| 1.2534 | 2.4 | 120 | 1.2267 | 0.5063 | 0.5083 | 0.5091 | 0.4848 | 0.5775 | 0.5063 | 0.5260 |
| 1.3777 | 2.8 | 140 | 1.2962 | 0.5290 | 0.5201 | 0.4887 | 0.4516 | 0.5963 | 0.5290 | 0.4952 |
| 0.8628 | 3.2 | 160 | 1.1360 | 0.5718 | 0.5487 | 0.5649 | 0.5433 | 0.6049 | 0.5718 | 0.5809 |
| 0.5909 | 3.6 | 180 | 1.2415 | 0.5718 | 0.5393 | 0.5602 | 0.5380 | 0.6050 | 0.5718 | 0.5792 |
| 1.2763 | 4.0 | 200 | 1.1941 | 0.5869 | 0.5431 | 0.5566 | 0.5443 | 0.5982 | 0.5869 | 0.5862 |
| 0.8283 | 4.4 | 220 | 1.2656 | 0.5693 | 0.5146 | 0.5185 | 0.5098 | 0.5666 | 0.5693 | 0.5615 |
| 0.8827 | 4.8 | 240 | 1.3241 | 0.5844 | 0.5369 | 0.5469 | 0.5390 | 0.5913 | 0.5844 | 0.5850 |
| 0.6598 | 5.2 | 260 | 1.3483 | 0.5693 | 0.5275 | 0.5324 | 0.5206 | 0.5879 | 0.5693 | 0.5668 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Model tree for IMA-StreamSolve/sentiment-analysis-roberta-base-V1.9_ima_ds
Base model
FacebookAI/roberta-base