Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 80.14440338125033,
+    "eval_exact_match": 0.212,
+    "eval_exact_match_pct": 21.2,
+    "eval_loss": 0.12204901874065399,
+    "eval_num_evaluated": 1000.0,
+    "eval_pred_len_mean": 28.06,
+    "eval_runtime": 64.095,
+    "eval_samples_per_second": 15.602,
+    "eval_steps_per_second": 0.25,
+    "total_flos": 4.858486798123008e+16,
+    "train_loss": 0.22325511785955607,
+    "train_runtime": 5103.6189,
+    "train_samples_per_second": 91.465,
+    "train_steps_per_second": 2.859
+}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scale_decoder_outputs": true,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "use_cache": false,
+  "vocab_size": 32100
+}

dataset_summary.json

@@ -0,0 +1,88 @@
+{
+  "dataset_name": "google/code_x_glue_cc_code_refinement",
+  "dataset_config": "small",
+  "splits": {
+    "train": 46680,
+    "validation": 5835,
+    "test": 5835
+  },
+  "source_column": "buggy",
+  "target_column": "fixed",
+  "detected_language": "java (heuristic, score=1193)",
+  "columns": [
+    "id",
+    "buggy",
+    "fixed"
+  ],
+  "malformed": {
+    "train": 0,
+    "validation": 0,
+    "test": 0
+  },
+  "identical_pairs": {
+    "train": 0,
+    "validation": 0,
+    "test": 0
+  },
+  "length_stats": {
+    "train/buggy": {
+      "mean": 53.388110539845755,
+      "p50": 53.0,
+      "p95": 82.0,
+      "p99": 92.0,
+      "max": 132
+    },
+    "train/fixed": {
+      "mean": 48.23601113967438,
+      "p50": 47.0,
+      "p95": 79.0,
+      "p99": 89.0,
+      "max": 124
+    },
+    "validation/buggy": {
+      "mean": 53.56966580976864,
+      "p50": 53.0,
+      "p95": 82.0,
+      "p99": 91.65999999999985,
+      "max": 119
+    },
+    "validation/fixed": {
+      "mean": 48.40222793487575,
+      "p50": 48.0,
+      "p95": 79.0,
+      "p99": 87.0,
+      "max": 111
+    },
+    "test/buggy": {
+      "mean": 53.23547557840617,
+      "p50": 53.0,
+      "p95": 83.0,
+      "p99": 92.0,
+      "max": 128
+    },
+    "test/fixed": {
+      "mean": 48.16915167095116,
+      "p50": 48.0,
+      "p95": 78.0,
+      "p99": 88.0,
+      "max": 130
+    }
+  },
+  "truncated": {
+    "train": {
+      "source_truncated": 0,
+      "target_truncated": 0,
+      "total": 46680
+    },
+    "validation": {
+      "source_truncated": 0,
+      "target_truncated": 0,
+      "total": 5835
+    },
+    "test": {
+      "source_truncated": 0,
+      "target_truncated": 0,
+      "total": 5835
+    }
+  }
+}

eval/metrics_test.json

@@ -0,0 +1,11 @@
+{
+  "exact_match": 0.22433590402742073,
+  "exact_match_pct": 22.433590402742073,
+  "bleu": 80.13394782533952,
+  "num_evaluated": 5835.0,
+  "pred_len_mean": 27.43050556983719,
+  "copy_input_pct": 3.37617823479006,
+  "partial_fix_pct": 13.48757497857755,
+  "incorrect_pct": 64.07883461868038,
+  "eval_loss": 0.12569236884946408
+}

eval/metrics_validation.json

@@ -0,0 +1,11 @@
+{
+  "exact_match": 0.212853470437018,
+  "exact_match_pct": 21.2853470437018,
+  "bleu": 80.2746460915236,
+  "num_evaluated": 5835.0,
+  "pred_len_mean": 27.832390745501286,
+  "copy_input_pct": 2.9648671808054843,
+  "partial_fix_pct": 13.50471293916024,
+  "incorrect_pct": 65.20994001713797,
+  "eval_loss": 0.12715422718421274
+}

eval/qualitative_test.json

@@ -0,0 +1,44 @@
+[
+  {
+    "bucket": "exact",
+    "index": "2",
+    "buggy": "private void METHOD_1 ( java.lang.Class VAR_1 ) { android.content.Intent intent = new android.content.Intent ( this , VAR_1 ) ; METHOD_2 ( intent ) ; } \n",
+    "reference": "public void METHOD_1 ( java.lang.Class VAR_1 ) { android.content.Intent intent = new android.content.Intent ( this , VAR_1 ) ; METHOD_2 ( intent ) ; }",
+    "prediction": "public void METHOD_1 ( java.lang.Class VAR_1 ) { android.content.Intent intent = new android.content.Intent ( this , VAR_1 ) ; METHOD_2 ( intent ) ; }"
+  },
+  {
+    "bucket": "exact",
+    "index": "6",
+    "buggy": "private static boolean METHOD_1 ( final byte status ) { return status == ( VAR_1 ) ; } \n",
+    "reference": "private static boolean METHOD_1 ( final int status ) { return status == ( VAR_1 ) ; }",
+    "prediction": "private static boolean METHOD_1 ( final int status ) { return status == ( VAR_1 ) ; }"
+  },
+  {
+    "bucket": "partial",
+    "index": "3",
+    "buggy": "public void METHOD_1 ( ) { for ( TYPE_1 VAR_1 : VAR_2 ) VAR_1 . METHOD_2 ( ) ; METHOD_3 ( ) ; if ( ( VAR_3 ) != null ) VAR_3 . METHOD_1 ( ) ; } \n",
+    "reference": "public void METHOD_1 ( ) { METHOD_3 ( ) ; if ( ( VAR_3 ) != null ) VAR_3 . METHOD_1 ( VAR_2 ) ; }",
+    "prediction": "public void METHOD_1 ( ) { METHOD_3 ( ) ; if ( ( VAR_3 ) != null ) VAR_3 . METHOD_1 ( ) ; }"
+  },
+  {
+    "bucket": "partial",
+    "index": "9",
+    "buggy": "public void METHOD_1 ( final java.lang.String ... VAR_1 ) { if ( VAR_1 != null ) format . METHOD_2 ( ) . METHOD_3 ( VAR_2 , VAR_1 ) ; } \n",
+    "reference": "public void METHOD_1 ( final java.lang.String ... VAR_1 ) { if ( ( VAR_1 != null ) && ( 0 < ( VAR_1 . length ) ) ) format . METHOD_2 ( ) . METHOD_3 ( VAR_2 , VAR_1 ) ; }",
+    "prediction": "public void METHOD_1 ( final java.lang.String ... VAR_1 ) { if ( ( VAR_1 != null ) && ( ( format . METHOD_2 ( ) ) != null ) ) format . METHOD_2 ( ) . METHOD_3 ( VAR_2 , VAR_1 ) ; }"
+  },
+  {
+    "bucket": "incorrect",
+    "index": "0",
+    "buggy": "private TYPE_1 getType ( TYPE_2 VAR_1 ) { TYPE_3 VAR_2 = new TYPE_3 ( STRING_1 ) ; return new TYPE_1 ( VAR_2 , VAR_2 ) ; } \n",
+    "reference": "private TYPE_1 getType ( TYPE_2 VAR_1 ) { TYPE_3 VAR_2 = new TYPE_3 ( STRING_1 ) ; return new TYPE_1 ( VAR_2 , VAR_2 , this , VAR_1 ) ; }",
+    "prediction": "private TYPE_1 getType ( TYPE_2 VAR_1 ) { TYPE_3 VAR_2 = new TYPE_3 ( STRING_1 ) ; return new TYPE_1 ( VAR_2 , VAR_1 ) ; }"
+  },
+  {
+    "bucket": "incorrect",
+    "index": "1",
+    "buggy": "public TYPE_1 METHOD_1 ( ) { TYPE_1 output = VAR_1 [ VAR_2 ] ; if ( ( VAR_2 ) > 0 ) { VAR_2 = ( VAR_2 ) - 1 ; } else { } return output ; } \n",
+    "reference": "public TYPE_1 METHOD_1 ( ) { TYPE_1 output = VAR_1 [ VAR_2 ] ; if ( ( VAR_2 ) >= 0 ) { VAR_2 = ( VAR_2 ) - 1 ; } else { } return output ; }",
+    "prediction": "public TYPE_1 METHOD_1 ( ) { TYPE_1 output = VAR_1 [ VAR_2 ] ; if ( ( VAR_2 ) > 0 ) { VAR_2 = ( VAR_2 ) - 1 ; } return output ; }"
+  }
+]

eval/qualitative_validation.json

@@ -0,0 +1,44 @@
+[
+  {
+    "bucket": "exact",
+    "index": "15",
+    "buggy": "public static TYPE_1 METHOD_1 ( final TYPE_2 VAR_1 , final java.lang.Object msg ) { TYPE_3 VAR_2 = TYPE_4 . METHOD_2 ( VAR_1 ) ; return TYPE_5 . METHOD_1 ( VAR_2 , msg ) ; } \n",
+    "reference": "public static TYPE_1 METHOD_1 ( final TYPE_2 VAR_1 , final java.lang.Object msg ) { TYPE_3 VAR_2 = TYPE_4 . METHOD_2 ( VAR_1 ) ; return TYPE_5 . METHOD_1 ( VAR_2 , msg , null ) ; }",
+    "prediction": "public static TYPE_1 METHOD_1 ( final TYPE_2 VAR_1 , final java.lang.Object msg ) { TYPE_3 VAR_2 = TYPE_4 . METHOD_2 ( VAR_1 ) ; return TYPE_5 . METHOD_1 ( VAR_2 , msg , null ) ; }"
+  },
+  {
+    "bucket": "exact",
+    "index": "23",
+    "buggy": "public void METHOD_1 ( ) { TYPE_1 . METHOD_2 ( VAR_1 , STRING_1 ) ; METHOD_3 ( false ) ; METHOD_4 ( ) ; super . METHOD_1 ( ) ; } \n",
+    "reference": "public void METHOD_1 ( ) { TYPE_1 . METHOD_2 ( VAR_1 , STRING_1 ) ; METHOD_4 ( ) ; super . METHOD_1 ( ) ; }",
+    "prediction": "public void METHOD_1 ( ) { TYPE_1 . METHOD_2 ( VAR_1 , STRING_1 ) ; METHOD_4 ( ) ; super . METHOD_1 ( ) ; }"
+  },
+  {
+    "bucket": "partial",
+    "index": "0",
+    "buggy": "public java.util.List < TYPE_1 > METHOD_1 ( ) { java.util.ArrayList < TYPE_1 > VAR_1 = new java.util.ArrayList < TYPE_1 > ( ) ; for ( TYPE_2 VAR_2 : VAR_3 ) { VAR_1 . METHOD_2 ( VAR_2 . METHOD_1 ( ) ) ; } return VAR_1 ; } \n",
+    "reference": "public java.util.List < TYPE_1 > METHOD_1 ( ) { return VAR_1 ; }",
+    "prediction": "public java.util.List < TYPE_1 > METHOD_1 ( ) { return VAR_3 ; }"
+  },
+  {
+    "bucket": "partial",
+    "index": "2",
+    "buggy": "public static void main ( java.lang.String [ ] args ) throws java.lang.Exception { TYPE_1 VAR_1 = new TYPE_1 ( ) ; VAR_1 . METHOD_1 ( ) ; VAR_1 . add ( VAR_2 ) ; VAR_1 . METHOD_2 ( true ) ; VAR_1 . init ( STRING_1 ) ; } \n",
+    "reference": "public static void main ( java.lang.String [ ] args ) throws java.lang.Exception { TYPE_1 VAR_1 = new TYPE_1 ( ) ; VAR_1 . METHOD_1 ( ) ; VAR_1 . METHOD_2 ( true ) ; VAR_1 . init ( STRING_1 ) ; }",
+    "prediction": "public static void main ( java.lang.String [ ] args ) throws java.lang.Exception { TYPE_1 VAR_1 = new TYPE_1 ( ) ; VAR_1 . METHOD_1 ( ) ; VAR_1 . add ( VAR_2 ) ; VAR_1 . init ( STRING_1 ) ; }"
+  },
+  {
+    "bucket": "incorrect",
+    "index": "1",
+    "buggy": "public TYPE_1 < TYPE_2 > METHOD_1 ( TYPE_3 VAR_1 , java.lang.String VAR_2 ) { return METHOD_1 ( VAR_1 . toString ( ) , VAR_2 ) ; } \n",
+    "reference": "public TYPE_1 < TYPE_2 > METHOD_1 ( TYPE_3 VAR_1 , java.lang.String VAR_2 , java.util.HashMap < java.lang.String , java.lang.String > parameters ) { return METHOD_1 ( VAR_1 . toString ( ) , VAR_2 , parameters ) ; }",
+    "prediction": "public TYPE_1 < TYPE_2 > METHOD_1 ( TYPE_3 VAR_1 , java.lang.String VAR_2 ) { return METHOD_1 ( VAR_1 , VAR_2 , null ) ; }"
+  },
+  {
+    "bucket": "incorrect",
+    "index": "3",
+    "buggy": "public void METHOD_1 ( int VAR_1 , java.lang.String VAR_2 , long VAR_3 ) { if ( VAR_1 == 0 ) { VAR_4 . METHOD_2 ( java.lang.String . METHOD_3 ( VAR_3 ) ) ; } else { VAR_4 . error ( VAR_2 ) ; } } \n",
+    "reference": "public void METHOD_1 ( int VAR_1 , java.lang.String VAR_2 , long VAR_3 ) { if ( VAR_1 == 0 ) { VAR_4 . METHOD_2 ( java.lang.String . METHOD_3 ( VAR_3 ) ) ; } else { VAR_4 . error ( VAR_1 ) ; } }",
+    "prediction": "public void METHOD_1 ( int VAR_1 , java.lang.String VAR_2 , long VAR_3 ) { if ( VAR_1 == 0 ) { VAR_4 . METHOD_2 ( java.lang.String . METHOD_3 ( VAR_3 ) ) ; } }"
+  }
+]

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 80.14440338125033,
+    "eval_exact_match": 0.212,
+    "eval_exact_match_pct": 21.2,
+    "eval_loss": 0.12204901874065399,
+    "eval_num_evaluated": 1000.0,
+    "eval_pred_len_mean": 28.06,
+    "eval_runtime": 64.095,
+    "eval_samples_per_second": 15.602,
+    "eval_steps_per_second": 0.25
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "do_sample": false,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 1.0,
+  "max_length": 256,
+  "max_new_tokens": 256,
+  "num_beams": 4,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.17.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0dbe4604ded324127c608bd4e8aff3ceb32af60fa11a4765e9f00e82c553e7
+size 891558696

run_config.json

@@ -0,0 +1,51 @@
+{
+  "model_name": "Salesforce/codet5-base",
+  "dataset_name": "google/code_x_glue_cc_code_refinement",
+  "dataset_config": "small",
+  "source_column": null,
+  "target_column": null,
+  "language": "java",
+  "train_split": "train",
+  "eval_split": "validation",
+  "test_split": "test",
+  "max_source_length": 256,
+  "max_target_length": 256,
+  "pad_to_multiple_of": 8,
+  "learning_rate": 5e-05,
+  "per_device_train_batch_size": 16,
+  "per_device_eval_batch_size": 64,
+  "gradient_accumulation_steps": 2,
+  "num_train_epochs": 10.0,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.05,
+  "lr_scheduler_type": "linear",
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "gradient_checkpointing": false,
+  "eval_strategy": "epoch",
+  "save_strategy": "epoch",
+  "logging_steps": 100,
+  "save_total_limit": 2,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "exact_match",
+  "greater_is_better": true,
+  "early_stopping_patience": 3,
+  "eval_subset_size": 1000,
+  "max_eval_examples": 0,
+  "num_beams": 4,
+  "max_new_tokens": 256,
+  "generation_early_stopping": true,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "seed": 42,
+  "output_dir": "outputs/codet5-base-code-repair",
+  "precision": "auto",
+  "dataloader_num_workers": 4,
+  "report_to": "none",
+  "resume_from_checkpoint": null,
+  "compute_codebleu": true,
+  "smoke_test": false,
+  "smoke_train_size": 256,
+  "smoke_eval_size": 32,
+  "smoke_epochs": 1.0
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 4.858486798123008e+16,
+    "train_loss": 0.22325511785955607,
+    "train_runtime": 5103.6189,
+    "train_samples_per_second": 91.465,
+    "train_steps_per_second": 2.859
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21c5d4e30108428603fa9c4b5c15ba7bde35035f2f7c01b9d2ed30b839d952b
+size 7313