Training complete

README.md

@@ -4,6 +4,9 @@ base_model: Salesforce/codet5-small
 tags:
 - Code Generation
 - generated_from_trainer
+metrics:
+- rouge
+- bleu
 model-index:
 - name: codeT5small-finetuned-cXg-nl-to-code
   results: []
@@ -16,17 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 6.3971
-- eval_rouge1: 0.0
-- eval_rouge2: 0.0
-- eval_rougeL: 0.0
-- eval_bleu: 0.5236
-- eval_meteor: 0.0250
-- eval_codebleu: 0.2548
-- eval_runtime: 16.1101
-- eval_samples_per_second: 0.621
-- eval_steps_per_second: 0.062
-- step: 0
+- Loss: 3.8098
+- Rouge1: 0.0074
+- Rouge2: 0.0
+- Rougel: 0.0074
+- Bleu: 0.9845
+- Meteor: 0.0255
+- Codebleu: 0.2550
 
 ## Model description
 
@@ -54,6 +53,10 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.42.4

runs/Jul24_13-04-35_a71dc02be579/events.out.tfevents.1721826410.a71dc02be579.554.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fd9789c9546e1bac18f20f2dfb2132355e80f6efcd963d125d7b8a3cd21feb
+size 648