Training complete

README.md

@@ -2,8 +2,12 @@
 license: mit
 base_model: gpt2
 tags:
+- Code Generation
 - Text Generation
 - generated_from_trainer
+metrics:
+- rouge
+- bleu
 model-index:
 - name: gpt2-finetuned-cXg-nl-to-code
   results: []
@@ -16,17 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 11.7810
-- eval_rouge1: 0.0273
-- eval_rouge2: 0.0018
-- eval_rougeL: 0.0210
-- eval_bleu: 0.3071
-- eval_meteor: 0.0819
-- eval_codebleu: 0.2306
-- eval_runtime: 20.2991
-- eval_samples_per_second: 0.493
-- eval_steps_per_second: 0.148
-- step: 0
+- Loss: 6.4614
+- Rouge1: 0.0220
+- Rouge2: 0.0014
+- Rougel: 0.0148
+- Bleu: 0.3339
+- Meteor: 0.0862
+- Codebleu: 0.2699
 
 ## Model description
 
@@ -54,6 +54,10 @@ 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_12-50-47_7918791504de/events.out.tfevents.1721825520.7918791504de.172.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428e4210eb4936539abaf35485c536df45f2b47f2df14c7271732d16c1aa80f8
+size 648