End of training

DisamBertSingleSense.py

@@ -115,13 +115,17 @@ class DisamBertSingleSense(PreTrainedModel):
 
 
 class CandidateLabeller:
-    def __init__(self, tokenizer: PreTrainedTokenizer, ontology: Generator[LexicalExample], device:torch.device):
+    def __init__(self, tokenizer: PreTrainedTokenizer, 
+                 ontology: Generator[LexicalExample], 
+                 device:torch.device,
+                 retain_candidates: bool = False):
         self.tokenizer = tokenizer
         self.device = device
         self.gloss_tokens = {
             example.concept: self.tokenizer(example.definition, padding=True)
             for example in ontology
         }
+        self.retain_candidates = retain_candidates
 
     def __call__(self, batch: dict) -> dict:
         with self.device:
@@ -154,4 +158,6 @@ class CandidateLabeller:
                 result["labels"] = torch.tensor(
                     [example["candidates"].index(example["label"]) for example in batch]
                 )
+            if self.retain_candidates:
+                result['candidates'] = [example['candidates'] for example in batch]
             return result

README.md

@@ -22,11 +22,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the semcor dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.8247
-- Precision: 0.7569
-- Recall: 0.7432
-- F1: 0.7500
-- Matthews: 0.7427
+- Loss: 7.9132
+- Precision: 0.7725
+- Recall: 0.7594
+- F1: 0.7659
+- Matthews: 0.7589
 
 ## Model description
 
@@ -58,17 +58,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1     | Matthews |
 |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0     | 0      | 81.7936         | 0.4396    | 0.3681 | 0.4007 | 0.3673   |
-| 0.5564        | 1.0   | 28027  | 0.8047          | 0.7521    | 0.7485 | 0.7503 | 0.7480   |
-| 0.4256        | 2.0   | 56054  | 1.0294          | 0.7659    | 0.7590 | 0.7624 | 0.7585   |
-| 0.2639        | 3.0   | 84081  | 1.6682          | 0.7656    | 0.7480 | 0.7567 | 0.7475   |
-| 0.1907        | 4.0   | 112108 | 3.4982          | 0.7703    | 0.7498 | 0.7599 | 0.7493   |
-| 0.0368        | 5.0   | 140135 | 5.1443          | 0.7635    | 0.7458 | 0.7546 | 0.7453   |
-| 0.0382        | 6.0   | 168162 | 6.3556          | 0.7674    | 0.7463 | 0.7567 | 0.7458   |
-| 0.0172        | 7.0   | 196189 | 8.0398          | 0.7548    | 0.7410 | 0.7479 | 0.7405   |
-| 0.0172        | 8.0   | 224216 | 7.1042          | 0.7605    | 0.7467 | 0.7536 | 0.7462   |
-| 0.0113        | 9.0   | 252243 | 7.6688          | 0.7624    | 0.7467 | 0.7545 | 0.7462   |
-| 0.0064        | 10.0  | 280270 | 7.8247          | 0.7569    | 0.7432 | 0.7500 | 0.7427   |
+| No log        | 0     | 0      | 83.4924         | 0.4375    | 0.3642 | 0.3975 | 0.3634   |
+| 0.4971        | 1.0   | 28027  | 0.7339          | 0.7793    | 0.7669 | 0.7730 | 0.7664   |
+| 0.3296        | 2.0   | 56054  | 0.9845          | 0.7756    | 0.7656 | 0.7705 | 0.7651   |
+| 0.1843        | 3.0   | 84081  | 2.0537          | 0.7743    | 0.7616 | 0.7679 | 0.7611   |
+| 0.0903        | 4.0   | 112108 | 3.9497          | 0.7729    | 0.7559 | 0.7643 | 0.7554   |
+| 0.0171        | 5.0   | 140135 | 5.8641          | 0.7727    | 0.7555 | 0.7640 | 0.7550   |
+| 0.0394        | 6.0   | 168162 | 6.5708          | 0.7747    | 0.7555 | 0.7650 | 0.7550   |
+| 0.0011        | 7.0   | 196189 | 7.4188          | 0.7705    | 0.7550 | 0.7627 | 0.7545   |
+| 0.0231        | 8.0   | 224216 | 7.0225          | 0.7762    | 0.7621 | 0.7691 | 0.7615   |
+| 0.0015        | 9.0   | 252243 | 6.9004          | 0.7766    | 0.7599 | 0.7681 | 0.7594   |
+| 0.0000        | 10.0  | 280270 | 7.9132          | 0.7725    | 0.7594 | 0.7659 | 0.7589   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fa38968a9a12b8f7abd761f6134a5a79193c9984529af17ec8f2117dfc7050
+oid sha256:c0e4738031e8de40fca39c5b910e41d301a71d07047dbc0b28893383db23b534
 size 596077624