codet5_local_e8_7_mix

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: Salesforce/codet5-small
+base_model: softhell/results
 tags:
 - generated_from_trainer
 datasets:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on the code_search_net dataset.
+This model is a fine-tuned version of [softhell/results](https://huggingface.co/softhell/results) on the code_search_net dataset.
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 8
+- num_epochs: 7
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Salesforce/codet5-small",
+  "_name_or_path": "softhell/results",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f009e39ef7a9de24c0b7d7e2fcdf7cc93e78ddd7f6509ca7054546d39831ffe6
+oid sha256:8b5118a11a85873a3b392153ed7511f8a5295b83379c179ee45d2d8a3ce15658
 size 242017320

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9e738442e8c22206e2097775172f821f36f0ea13e67cfd510c4339cda7ae29
+oid sha256:739d001731451542e3c523319b2640fd01e5e20e8d47b10825e8c538ada59108
 size 5368