codet5_train_2

README.md

@@ -6,24 +6,9 @@ tags:
 - generated_from_trainer
 datasets:
 - code_search_net
-metrics:
-- bleu
 model-index:
 - name: code_docstring_model
-  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: 0.08377962983846503
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +17,6 @@ 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: 0.9435
-- Bleu: 0.0838
 
 ## Model description
 
@@ -61,35 +43,9 @@ 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: 20
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch   | Step  | Validation Loss | Bleu   |
-|:-------------:|:-------:|:-----:|:---------------:|:------:|
-| 1.2873        | 0.9993  | 1076  | 1.1220          | 0.2248 |
-| 1.1474        | 1.9993  | 2152  | 1.0673          | 0.2589 |
-| 1.112         | 2.9993  | 3228  | 1.0406          | 0.2379 |
-| 1.0849        | 3.9993  | 4304  | 1.0252          | 0.2432 |
-| 1.0602        | 4.9993  | 5380  | 1.0126          | 0.1499 |
-| 1.0565        | 5.9993  | 6456  | 1.0030          | 0.1413 |
-| 1.0576        | 6.9993  | 7532  | 0.9964          | 0.0616 |
-| 1.0174        | 7.9993  | 8608  | 0.9883          | 0.0935 |
-| 1.0301        | 8.9993  | 9684  | 0.9828          | 0.0843 |
-| 0.9884        | 9.9993  | 10760 | 0.9768          | 0.1363 |
-| 0.9998        | 10.9993 | 11836 | 0.9702          | 0.1104 |
-| 0.995         | 11.9993 | 12912 | 0.9647          | 0.1169 |
-| 0.9852        | 12.9993 | 13988 | 0.9593          | 0.0962 |
-| 0.9594        | 13.9993 | 15064 | 0.9549          | 0.0973 |
-| 0.9553        | 14.9993 | 16140 | 0.9510          | 0.0923 |
-| 0.9717        | 15.9993 | 17216 | 0.9486          | 0.0821 |
-| 0.9667        | 16.9993 | 18292 | 0.9468          | 0.0888 |
-| 0.957         | 17.9993 | 19368 | 0.9448          | 0.0858 |
-| 0.9649        | 18.9993 | 20444 | 0.9438          | 0.0875 |
-| 0.9454        | 19.9993 | 21520 | 0.9435          | 0.0838 |
-
-
 ### Framework versions
 
 - Transformers 4.47.0

added_tokens.json

@@ -1,6 +1,28 @@
 {
+  ".. code-block:: python": 32125,
+  ".. deprecated::": 32124,
+  ".. note::": 32121,
+  ".. seealso::": 32122,
+  ".. warning::": 32123,
+  ":ivar:": 32117,
+  ":meth:": 32118,
+  ":param": 32114,
+  ":raises:": 32116,
+  ":returns:": 32115,
+  ":type:": 32119,
+  ":yields:": 32120,
   "Args:": 32100,
+  "Attributes:": 32104,
+  "Deprecated:": 32110,
   "Examples:": 32103,
+  "Methods:": 32105,
+  "Note:": 32107,
+  "Raises": 32111,
   "Raises:": 32102,
-  "Returns:": 32101
+  "References:": 32108,
+  "Returns:": 32101,
+  "Type:": 32113,
+  "Warning:": 32109,
+  "Yields": 32112,
+  "Yields:": 32106
 }

config.json

@@ -65,5 +65,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
-  "vocab_size": 32104
+  "vocab_size": 32126
 }

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "_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 sha256:139c4cfde4ed2c2ae9f4c2888db34288d73de0e738f4796f12e13207547f3236
-size 241992744
+oid sha256:1cafe8ce68a18578c7f0750f117e520ba7303b3b85fa8b8549feb35e985168b8
+size 242037800

special_tokens_map.json

@@ -27,6 +27,216 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false
+    },
+    {
+      "content": "Attributes:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Methods:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Yields:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Note:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "References:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Warning:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Deprecated:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Parameters",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Returns",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Raises",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Examples",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Attributes",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Yields",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Notes",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "References",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Warnings",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Deprecated",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "Type:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":param",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":returns:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":raises:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":ivar:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":meth:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":type:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ":yields:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ".. note::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ".. seealso::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ".. warning::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ".. deprecated::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": ".. code-block:: python",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
     }
   ],
   "bos_token": {

tokenizer.json

@@ -62,6 +62,78 @@
       "normalized": true,
       "special": true
     },
+    {
+      "id": 1356,
+      "content": "Returns",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2402,
+      "content": "Parameters",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2498,
+      "content": "Attributes",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4312,
+      "content": "Warnings",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 8221,
+      "content": "References",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 13534,
+      "content": "Deprecated",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 18063,
+      "content": "Notes",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 23905,
+      "content": "Examples",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
     {
       "id": 32000,
       "content": "<extra_id_99>",
@@ -997,6 +1069,204 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32104,
+      "content": "Attributes:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32105,
+      "content": "Methods:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32106,
+      "content": "Yields:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32107,
+      "content": "Note:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32108,
+      "content": "References:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32109,
+      "content": "Warning:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32110,
+      "content": "Deprecated:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32111,
+      "content": "Raises",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32112,
+      "content": "Yields",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32113,
+      "content": "Type:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32114,
+      "content": ":param",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32115,
+      "content": ":returns:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32116,
+      "content": ":raises:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32117,
+      "content": ":ivar:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32118,
+      "content": ":meth:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32119,
+      "content": ":type:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32120,
+      "content": ":yields:",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32121,
+      "content": ".. note::",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32122,
+      "content": ".. seealso::",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32123,
+      "content": ".. warning::",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32124,
+      "content": ".. deprecated::",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32125,
+      "content": ".. code-block:: python",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -41,6 +41,70 @@
       "single_word": false,
       "special": true
     },
+    "1356": {
+      "content": "Returns",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2402": {
+      "content": "Parameters",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2498": {
+      "content": "Attributes",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4312": {
+      "content": "Warnings",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8221": {
+      "content": "References",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13534": {
+      "content": "Deprecated",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18063": {
+      "content": "Notes",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23905": {
+      "content": "Examples",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
     "32000": {
       "content": "<extra_id_99>",
       "lstrip": true,
@@ -872,13 +936,219 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32104": {
+      "content": "Attributes:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32105": {
+      "content": "Methods:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32106": {
+      "content": "Yields:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32107": {
+      "content": "Note:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32108": {
+      "content": "References:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32109": {
+      "content": "Warning:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32110": {
+      "content": "Deprecated:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32111": {
+      "content": "Raises",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32112": {
+      "content": "Yields",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32113": {
+      "content": "Type:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32114": {
+      "content": ":param",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32115": {
+      "content": ":returns:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32116": {
+      "content": ":raises:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32117": {
+      "content": ":ivar:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32118": {
+      "content": ":meth:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32119": {
+      "content": ":type:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32120": {
+      "content": ":yields:",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32121": {
+      "content": ".. note::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32122": {
+      "content": ".. seealso::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32123": {
+      "content": ".. warning::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32124": {
+      "content": ".. deprecated::",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32125": {
+      "content": ".. code-block:: python",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
     "Args:",
     "Returns:",
     "Raises:",
-    "Examples:"
+    "Examples:",
+    "Attributes:",
+    "Methods:",
+    "Yields:",
+    "Note:",
+    "References:",
+    "Warning:",
+    "Deprecated:",
+    "Parameters",
+    "Returns",
+    "Raises",
+    "Examples",
+    "Attributes",
+    "Yields",
+    "Notes",
+    "References",
+    "Warnings",
+    "Deprecated",
+    "Type:",
+    ":param",
+    ":returns:",
+    ":raises:",
+    ":ivar:",
+    ":meth:",
+    ":type:",
+    ":yields:",
+    ".. note::",
+    ".. seealso::",
+    ".. warning::",
+    ".. deprecated::",
+    ".. code-block:: python"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef2df3496087df5e39737165b6368e1e8c1ada498e92b93d63343e96ccc4ce8
+oid sha256:9ddd8794676d2453affc90705f6e1c633c806093eddd2350630cec45d0681d36
 size 5496