Sarmila
/

scibert_scivocab_uncased_ml-finetuned-imdb

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Sarmila commited on Mar 27, 2023

Commit

5fbe74e

·

1 Parent(s): 8a7304e

update model card README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.7114
 ## Model description
@@ -45,9 +45,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.7982        | 1.0   | 32   | 7.2343          |
-| 7.0165        | 2.0   | 64   | 6.9615          |
-| 6.8176        | 3.0   | 96   | 6.7678          |
 ### Framework versions

 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.7940
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.7945        | 1.0   | 30   | 1.7968          |
+| 1.8117        | 2.0   | 60   | 1.8293          |
+| 1.8011        | 3.0   | 90   | 1.7923          |
 ### Framework versions