update model card README.md

README.md

@@ -19,17 +19,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0267
+- Loss: 0.0453
 - Precision: 0.0
 - Recall: 0.0
 - F1: 0.0
-- Accuracy: 0.9886
+- Accuracy: 0.9857
 
 ## Model description
 
-Identify negation words in sentences. If there is a negation word, it will be labeled as "Y" in token classification task.
-Common negation words:
-['halt', 'inhospitable', 'unhappy', 'unserviceable', 'dislike', 'unaware', 'unfavorable', 'barely', 'unseen', 'unoccupied', 'unreliability', 'insulator', 'stop', 'indistinguishable', 'unrestricted', 'unfairly', 'unsupervised', 'unicameral', 'forbid', 'unforgettable', 'reject', 'uneducated', 'unlimited', 'illegal', 'uncertainty', 'nonhuman', 'unborn', 'unshaven', 'uncanny', 'incomplete', 'unsure', 'unconscious', 'atypical', 'indirectly', 'unloaded', 'disadvantage', 'contrary', 'infrequent', 'unofficial', 'few', 'untouched', 'refuse', 'inequitable', 'disproportionate', 'unexpected', 'displeased', 'unpaved', 'unwieldy', 'not at all', 'absent', 'unnoticed', 'unpleasant', 'unsafe', 'unsigned', 'not', 'inaccurate', 'cannot', 'involuntary', 'unequipped', 'illiterate', 'cease', 'disagreeable', 'prohibit', 'unable', 'unstable', 'uninhabited', 'unclean', 'useless', 'disapprove', 'insensitive', 'in the absence of', 'impractical', 'unorthodox', 'untreated', 'unsuccessful', 'unwitting', 'unfashionable', 'disagreement', 'unmyelinated', 'unfortunate', 'unknown', 'ineffective', 'a lack of', 'instead of', 'refused', 'illegitimate', 'little', 'unpaid', 'fail', 'unintentionally', 'unglazed', "didn't", 'unprocessed', 'inability', 'undeveloped', 'exclude', 'neither', 'except', 'unequivocal', 'unconventional', 'incorrectly', 'unconditional', 'prevent', 'dissimilar', 'uncommon', 'inorganic', 'unquestionable', 'uncoated', 'unassisted', 'unprecedented', 'nonviolent', 'unarmed', 'unpopular', 'inadequate', 'uncomfortable', 'unwilling', 'unaffected', 'unfaithful', 'nobody', 'loss', 'without', 'undamaged', 'nothing', 'could not', 'impossible to', 'unaccompanied', 'unlike', 'oppose', 'compromising', 'unmarried', 'rarely', 'unlighted', 'inexperienced', 'rather than', 'unrelated', 'untied', 'dishonest', 'insecure', 'uneven', 'harmless', 'avoid', 'with the exception of', 'no', 'undefeated', 'no longer', 'inadvertently', 'absence', 'lack', 'unconnected', 'unfinished', 'invalid', 'unnecessary', 'invisibility', 'unusual', 'none', 'incredulous', 'impossible', 'never', 'untrained', 'incorrect', 'immobility', 'unclear', 'impartial', 'unlucky', 'deny', 'uncertain', 'hardly', 'unsaturated', 'informal', 'irregular', 'dissatisfaction']
+More information needed
 
 ## Intended uses & limitations
 
@@ -37,7 +35,7 @@ More information needed
 
 ## Training and evaluation data
 
-Use original setence and negation cue annotation from CondaQA dataset. You can find it on both github and huggingface.
+More information needed
 
 ## Training procedure
 
@@ -56,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
-| No log        | 1.0   | 6    | 0.0868          | 0.0       | 0.0    | 0.0 | 0.9762   |
-| No log        | 2.0   | 12   | 0.0533          | 0.0       | 0.0    | 0.0 | 0.9762   |
-| No log        | 3.0   | 18   | 0.0303          | 0.0       | 0.0    | 0.0 | 0.9878   |
-| No log        | 4.0   | 24   | 0.0267          | 0.0       | 0.0    | 0.0 | 0.9886   |
+| No log        | 1.0   | 4    | 0.1549          | 0.0       | 0.0    | 0.0 | 0.9588   |
+| No log        | 2.0   | 8    | 0.1007          | 0.0       | 0.0    | 0.0 | 0.9588   |
+| No log        | 3.0   | 12   | 0.0592          | 0.0       | 0.0    | 0.0 | 0.9818   |
+| No log        | 4.0   | 16   | 0.0453          | 0.0       | 0.0    | 0.0 | 0.9857   |
 
 
 ### Framework versions