Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "microsoft/codebert-base",
+  "architectures": [
+    "CodeBERTHSUMForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "count": 4,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "max_query_length": 128,
+  "max_seq_length": -68,
+  "mix_type": "HSUM",
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sc_comment": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34f98112e532201ee5d44baf25db0d5f682f4c21e155eda91a5243f25c882c1
+size 612026240

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a304b1a49755b0733ead29cd3ac8b427e2b3cd750d3803d3247f20e7941ae2f4
+size 1224210309

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a1f04f0c4251f78963522b5e9d1cd8c0fa756cce5bbdff7db3bf68898a58f9
+size 14511

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d0ddce317420304e0452fb4975742c804af0156b5519a2acdb8b056f7765a9
+size 627

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 64,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.8450704225352113,
+  "best_model_checkpoint": "/cm/archive/namlh35/code-comment-classification/results/selection_wo_valid/Verification/codebert-postpretrained-HSUM-4layers-datav2-class-comment/java_deprecation/checkpoint-250",
+  "epoch": 3.0303030303030303,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "eval_f1": 0.0,
+      "eval_loss": 0.056170761585235596,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 15.1951,
+      "eval_samples_per_second": 139.058,
+      "eval_steps_per_second": 8.753,
+      "step": 50
+    },
+    {
+      "epoch": 0.76,
+      "eval_f1": 0.8059701492537312,
+      "eval_loss": 0.029947876930236816,
+      "eval_precision": 0.9,
+      "eval_recall": 0.7297297297297297,
+      "eval_runtime": 8.6149,
+      "eval_samples_per_second": 245.272,
+      "eval_steps_per_second": 15.438,
+      "step": 100
+    },
+    {
+      "epoch": 1.14,
+      "eval_f1": 0.8169014084507041,
+      "eval_loss": 0.03486325964331627,
+      "eval_precision": 0.8529411764705882,
+      "eval_recall": 0.7837837837837838,
+      "eval_runtime": 8.6487,
+      "eval_samples_per_second": 244.315,
+      "eval_steps_per_second": 15.378,
+      "step": 150
+    },
+    {
+      "epoch": 1.52,
+      "eval_f1": 0.8169014084507041,
+      "eval_loss": 0.030027925968170166,
+      "eval_precision": 0.8529411764705882,
+      "eval_recall": 0.7837837837837838,
+      "eval_runtime": 8.7028,
+      "eval_samples_per_second": 242.796,
+      "eval_steps_per_second": 15.282,
+      "step": 200
+    },
+    {
+      "epoch": 1.89,
+      "eval_f1": 0.8450704225352113,
+      "eval_loss": 0.025771863758563995,
+      "eval_precision": 0.8823529411764706,
+      "eval_recall": 0.8108108108108109,
+      "eval_runtime": 8.4673,
+      "eval_samples_per_second": 249.547,
+      "eval_steps_per_second": 15.707,
+      "step": 250
+    },
+    {
+      "epoch": 2.27,
+      "eval_f1": 0.823529411764706,
+      "eval_loss": 0.03130728378891945,
+      "eval_precision": 0.9032258064516129,
+      "eval_recall": 0.7567567567567568,
+      "eval_runtime": 9.0162,
+      "eval_samples_per_second": 234.356,
+      "eval_steps_per_second": 14.751,
+      "step": 300
+    },
+    {
+      "epoch": 2.65,
+      "eval_f1": 0.8219178082191781,
+      "eval_loss": 0.028314711526036263,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.8108108108108109,
+      "eval_runtime": 9.6845,
+      "eval_samples_per_second": 218.183,
+      "eval_steps_per_second": 13.733,
+      "step": 350
+    },
+    {
+      "epoch": 3.03,
+      "eval_f1": 0.8219178082191781,
+      "eval_loss": 0.030898844823241234,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.8108108108108109,
+      "eval_runtime": 8.964,
+      "eval_samples_per_second": 235.72,
+      "eval_steps_per_second": 14.837,
+      "step": 400
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1320,
+  "num_train_epochs": 10,
+  "save_steps": 50,
+  "total_flos": 1119873879427584.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3cc83794fd06e45c57b267b5d26d0d9232358cd428a8e432c7f2b362435056
+size 4539