Training complete

README.md

@@ -3,6 +3,9 @@ base_model: microsoft/graphcodebert-base
 tags:
 - Text2Text Generation
 - generated_from_trainer
+metrics:
+- rouge
+- bleu
 model-index:
 - name: graphCodeBert-finetuned-cXg-nl-to-code
   results: []
@@ -15,17 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/graphcodebert-base](https://huggingface.co/microsoft/graphcodebert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 22.1633
-- eval_rouge1: 0.0772
-- eval_rouge2: 0.0056
-- eval_rougeL: 0.0553
-- eval_bleu: 0.6387
-- eval_meteor: 0.0767
-- eval_codebleu: 0.2058
-- eval_runtime: 41.4626
-- eval_samples_per_second: 0.241
-- eval_steps_per_second: 0.024
-- step: 0
+- Loss: 8.5374
+- Rouge1: 0.0803
+- Rouge2: 0.0056
+- Rougel: 0.0590
+- Bleu: 0.7208
+- Meteor: 0.1076
+- Codebleu: 0.2064
 
 ## Model description
 
@@ -53,6 +52,10 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.42.4

runs/Jul29_11-20-38_7e87b5bf63d4/events.out.tfevents.1722252340.7e87b5bf63d4.2591.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae8132df1172122d689e22664b96b8e9045593b961060d039c745a559829f69
+size 648