Training complete

README.md

@@ -4,6 +4,9 @@ base_model: facebook/bart-large-cnn
 tags:
 - Code Generation
 - generated_from_trainer
+metrics:
+- rouge
+- bleu
 model-index:
 - name: bart-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 [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.9866
-- eval_rouge1: 0.0521
-- eval_rouge2: 0.0051
-- eval_rougeL: 0.0444
-- eval_bleu: 0.5881
-- eval_meteor: 0.0687
-- eval_codebleu: 0.2509
-- eval_runtime: 145.8637
-- eval_samples_per_second: 0.069
-- eval_steps_per_second: 0.007
-- step: 0
+- Loss: 1.0056
+- Rouge1: 0.0578
+- Rouge2: 0.0
+- Rougel: 0.0459
+- Bleu: 0.3824
+- Meteor: 0.0845
+- Codebleu: 0.2175
 
 ## 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_12-15-24_ba56a2514472/events.out.tfevents.1721824767.ba56a2514472.7642.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9eb5d21e03556dbb68825bfad696541aee2a6cb6300c98c502282c9e0d5109
+size 648