codet5_train_2

README.md

@@ -6,9 +6,24 @@ tags:
 - generated_from_trainer
 datasets:
 - code_search_net
+metrics:
+- bleu
 model-index:
 - name: code_docstring_model
-  results: []
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: code_search_net
+      type: code_search_net
+      config: python
+      split: validation
+      args: python
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 0.009912737763560728
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 # code_docstring_model
 
 This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on the code_search_net dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1194
+- Bleu: 0.0099
 
 ## Model description
 
@@ -43,9 +61,20 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Bleu   |
+|:-------------:|:------:|:-----:|:---------------:|:------:|
+| 1.4113        | 1.0    | 2004  | 1.2082          | 0.0095 |
+| 1.3283        | 2.0    | 4008  | 1.1537          | 0.0097 |
+| 1.3036        | 3.0    | 6012  | 1.1331          | 0.0098 |
+| 1.2585        | 4.0    | 8016  | 1.1226          | 0.0098 |
+| 1.2613        | 4.9978 | 10015 | 1.1194          | 0.0099 |
+
+
 ### Framework versions
 
 - Transformers 4.47.0

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "decoder_start_token_id": 0,
   "eos_token_id": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cafe8ce68a18578c7f0750f117e520ba7303b3b85fa8b8549feb35e985168b8
+oid sha256:96e6e7f07f24e59be74c6d559a79325413ed1d8aed5a419fa41906e70a5bf66d
 size 242037800

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ddd8794676d2453affc90705f6e1c633c806093eddd2350630cec45d0681d36
+oid sha256:3b37b21c03d518303a92294b07f5807779171f7cb7ed6a230c85043641d48951
 size 5496