metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: deberta-v3-base_MNLI_10_19_v0
results: []
deberta-v3-base_MNLI_10_19_v0
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset.
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
Model Recycling
Evaluation on 36 datasets using mariolinml/deberta-v3-base_MNLI_10_19_v0 as a base model yields average score of 79.75 in comparison to 79.04 by microsoft/deberta-v3-base.
The model is ranked 3rd among all tested models for the microsoft/deberta-v3-base architecture as of 22/01/2023 Results:
| 20_newsgroup | ag_news | amazon_reviews_multi | anli | boolq | cb | cola | copa | dbpedia | esnli | financial_phrasebank | imdb | isear | mnli | mrpc | multirc | poem_sentiment | qnli | qqp | rotten_tomatoes | rte | sst2 | sst_5bins | stsb | trec_coarse | trec_fine | tweet_ev_emoji | tweet_ev_emotion | tweet_ev_hate | tweet_ev_irony | tweet_ev_offensive | tweet_ev_sentiment | wic | wnli | wsc | yahoo_answers |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 85.8471 | 90.2333 | 66.74 | 60.0625 | 81.8349 | 82.1429 | 84.8514 | 69 | 79.4333 | 91.1136 | 86.9 | 94.372 | 71.382 | 89.7172 | 88.2353 | 64.3771 | 88.4615 | 93.758 | 91.8699 | 89.7749 | 85.5596 | 95.1835 | 57.4661 | 91.7396 | 97.6 | 91.8 | 45.526 | 84.2365 | 55.9933 | 79.8469 | 84.3023 | 71.2634 | 70.0627 | 74.6479 | 63.4615 | 72.1333 |
For more information, see: Model Recycling