TOKENIZER & TRAINER CORRUPTED
electra-5-epoch-sentiment
This model is a fine-tuned version of google/electra-small-discriminator on the tweet_eval dataset. It achieves the following results on the evaluation set:
- Loss: 0.7949
- Accuracy: 0.6894
- Precision: 0.6914
- Recall: 0.6894
- Micro-avg-recall: 0.6894
- Micro-avg-precision: 0.6894
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
---|---|---|---|---|---|---|---|---|
0.5949 | 1.0 | 2851 | 0.6963 | 0.6926 | 0.6943 | 0.6926 | 0.6926 | 0.6926 |
0.6502 | 2.0 | 5702 | 0.7348 | 0.6911 | 0.6929 | 0.6911 | 0.6911 | 0.6911 |
0.556 | 3.0 | 8553 | 0.7322 | 0.6943 | 0.6952 | 0.6943 | 0.6943 | 0.6943 |
0.4561 | 4.0 | 11404 | 0.7601 | 0.6895 | 0.6916 | 0.6895 | 0.6895 | 0.6895 |
0.471 | 5.0 | 14255 | 0.7949 | 0.6894 | 0.6914 | 0.6894 | 0.6894 | 0.6894 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 22
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Priyanka-Balivada/electra-5-epoch-sentiment
Base model
google/electra-small-discriminatorDataset used to train Priyanka-Balivada/electra-5-epoch-sentiment
Evaluation results
- Accuracy on tweet_evaltest set self-reported0.689
- Precision on tweet_evaltest set self-reported0.691
- Recall on tweet_evaltest set self-reported0.689