Model save

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: code-completion-01
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# code-completion-01
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 48
+- eval_batch_size: 96
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+- label_smoothing_factor: 0.1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.4.1
+- Datasets 2.16.1
+- Tokenizers 0.15.2

config.json

@@ -1,9 +1,8 @@
 {
-  "_name_or_path": "/home/user1-system11/Documents/research-shradha/CODE-SPT-Code-TreeSitterV3/SPT-Code/outputs/pre_train_20241105_105459/models",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
-    "BartModel"
+    "BartForClassificationAndGeneration"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -31,8 +30,8 @@
     "LABEL_0": 0,
     "LABEL_1": 1
   },
-  "max_length": 256,
-  "max_position_embeddings": 1024,
+  "max_length": 100,
+  "max_position_embeddings": 512,
   "min_length": 1,
   "model_type": "bart",
   "num_beams": 5,
@@ -42,5 +41,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "use_cache": true,
-  "vocab_size": 80092
+  "vocab_size": 3007
 }

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 100,
+  "min_length": 1,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b820619f5b5b3f7d2e91eb188d666715363b8a665e3c049dacb25ab027b1319
-size 1046317760
+oid sha256:1ef76a4d38031e57965ec78834cf9981599601c43e49c19cb84ad97df2932304
+size 808750996

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20f391e8e3b163098e6d63569233579889e8fae5aa65e858153195ff0ac000c
+size 4984