SashaSheykina
/

codeT5-finetuned-cXg-nl-to-code

@@ -5,7 +5,6 @@ tags:
 - code-generation
 - generated_from_trainer
 metrics:
-- rouge
 - bleu
 model-index:
 - name: codeT5-finetuned-cXg-nl-to-code
@@ -19,14 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3402
-- Rouge1: 0.5424
-- Rouge2: 0.3557
-- Rougel: 0.5176
-- Bleu: 21.0146
-- Meteor: 0.5332
-- Codebleu: 0.2686
-- Em: 0.15
 ## Model description
@@ -51,7 +47,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
 - mixed_precision_training: Native AMP
 ### Training results

 - code-generation
 - generated_from_trainer
 metrics:
 - bleu
 model-index:
 - name: codeT5-finetuned-cXg-nl-to-code
 This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.5214
+- Bleu: 26.2135
+- Meteor: 0.5517
+- Codebleu: 0.3175
+- Em: 0.139
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 ### Training results

runs/Aug06_09-31-33_4162cf012493/events.out.tfevents.1723005492.4162cf012493.2616.1 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:9436643ecfa743a3c68343960cbf2108bae73fd1a003a3963dd1b3e9465ea775
+size 555