Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+reduced_main_data.csv filter=lfs diff=lfs merge=lfs -text
+test_data_for_future_evaluation.csv filter=lfs diff=lfs merge=lfs -text
+test_top_repo_data.csv filter=lfs diff=lfs merge=lfs -text
+top_repo_data.csv filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/metrics-checkpoint.json

@@ -0,0 +1 @@
+{"precision": 0.9784045835169678, "recall": 0.9854153455928979, "acc": 0.9821283762709749, "mcc": 0.9642753423345738, "f1": 0.9818974504786276, "auc": 0.9972255251769351}

checkpoint-10020/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-10020/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d90de7783c499123fe65e335d2cde00dd1a30a1100aef423f0e83cfe1db8a6
+size 328492280

checkpoint-10020/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cf7d2a0570ddaf4ed1fce57e1b163a5f627b2bdb671321c8cc81aa0da9eb72
+size 657047610

checkpoint-10020/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c132fbab01ba44ae5a4600e89c22e5e82ed9781d053ce7ec542ea0107af78e8a
+size 14244

checkpoint-10020/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ae05b0103f90146ce39046375ae878319f4c7d09227e8bc0c984a5fcb5bda2
+size 1064

checkpoint-10020/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 0.0373,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.9663165247662615e-05,
+      "loss": 0.0614,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.865640637350898e-05,
+      "loss": 0.0588,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.700706468751901e-05,
+      "loss": 0.0661,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.475994152602118e-05,
+      "loss": 0.0515,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.197607586073667e-05,
+      "loss": 0.0518,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.8731086287268264e-05,
+      "loss": 0.052,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.511311698489561e-05,
+      "loss": 0.0506,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1228433624560175e-05,
+      "loss": 0.0383,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.7175240839918063e-05,
+      "loss": 0.0409,
+      "step": 5000
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.3054972130358894e-05,
+      "loss": 0.0372,
+      "step": 5500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.8987536529000545e-05,
+      "loss": 0.0349,
+      "step": 6000
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.5083418450272521e-05,
+      "loss": 0.0246,
+      "step": 6500
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.1455599648308674e-05,
+      "loss": 0.0232,
+      "step": 7000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 8.188115868146839e-06,
+      "loss": 0.0255,
+      "step": 7500
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 5.377296029546741e-06,
+      "loss": 0.0236,
+      "step": 8000
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 3.1034708332441433e-06,
+      "loss": 0.0154,
+      "step": 8500
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 1.4193117617159691e-06,
+      "loss": 0.0195,
+      "step": 9000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 3.756787580085019e-07,
+      "loss": 0.0224,
+      "step": 9500
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 9.201950512210955e-10,
+      "loss": 0.0249,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10020,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8.494405705116672e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10020/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f5690b2a5603554c13f29c439ae2d9aa25bbf66bfb42a129aa8aa35ad4b2c1
+size 4664

classification_report.json

@@ -0,0 +1 @@
+{"0": {"precision": 0.9945378666993986, "recall": 0.9946599558065308, "f1-score": 0.994598907506291, "support": 16292}, "1": {"precision": 0.994482496194825, "recall": 0.9943563728598604, "f1-score": 0.9944194305282515, "support": 15770}, "accuracy": 0.9945106356434409, "macro avg": {"precision": 0.9945101814471118, "recall": 0.9945081643331957, "f1-score": 0.9945091690172713, "support": 32062}, "weighted avg": {"precision": 0.9945106321894764, "recall": 0.9945106356434409, "f1-score": 0.9945106300456309, "support": 32062}}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

fold_results.json

@@ -0,0 +1,67 @@
+{
+    "0": {
+        "eval_loss": 0.40148600935935974,
+        "eval_precision": 0.8656669790690409,
+        "eval_recall": 0.8785111914273033,
+        "eval_acc": 0.8731871627732901,
+        "eval_mcc": 0.746447037107958,
+        "eval_f1": 0.8720417925478348,
+        "eval_auc": 0.9394272614942787,
+        "eval_runtime": 90.2981,
+        "eval_samples_per_second": 355.079,
+        "eval_steps_per_second": 5.548,
+        "epoch": 5.0
+    },
+    "1": {
+        "eval_loss": 0.2502449154853821,
+        "eval_precision": 0.9276957718288716,
+        "eval_recall": 0.9405199746353836,
+        "eval_acc": 0.9346890399850291,
+        "eval_mcc": 0.8694527772027904,
+        "eval_f1": 0.934063857925562,
+        "eval_auc": 0.9791706185357555,
+        "eval_runtime": 92.8544,
+        "eval_samples_per_second": 345.293,
+        "eval_steps_per_second": 5.396,
+        "epoch": 5.0
+    },
+    "2": {
+        "eval_loss": 0.06282494217157364,
+        "eval_precision": 0.9808663803990907,
+        "eval_recall": 0.9849714648065948,
+        "eval_acc": 0.9831576320878298,
+        "eval_mcc": 0.9663167846706998,
+        "eval_f1": 0.9829146364614314,
+        "eval_auc": 0.9976812207025214,
+        "eval_runtime": 93.3536,
+        "eval_samples_per_second": 343.447,
+        "eval_steps_per_second": 5.367,
+        "epoch": 5.0
+    },
+    "3": {
+        "eval_loss": 0.031204670667648315,
+        "eval_precision": 0.9902593295382669,
+        "eval_recall": 0.9927710843373494,
+        "eval_acc": 0.9916411951843304,
+        "eval_mcc": 0.9832816995905711,
+        "eval_f1": 0.9915136162127929,
+        "eval_auc": 0.9993127931888565,
+        "eval_runtime": 93.9085,
+        "eval_samples_per_second": 341.418,
+        "eval_steps_per_second": 5.335,
+        "epoch": 5.0
+    },
+    "4": {
+        "eval_loss": 0.021965384483337402,
+        "eval_precision": 0.994482496194825,
+        "eval_recall": 0.9943563728598604,
+        "eval_acc": 0.9945106356434409,
+        "eval_mcc": 0.9890183457782504,
+        "eval_f1": 0.9944194305282515,
+        "eval_auc": 0.9996556930812918,
+        "eval_runtime": 97.5799,
+        "eval_samples_per_second": 328.572,
+        "eval_steps_per_second": 5.134,
+        "epoch": 5.0
+    }
+}

metrics.json

@@ -0,0 +1 @@
+{"precision": 0.994482496194825, "recall": 0.9943563728598604, "acc": 0.9945106356434409, "mcc": 0.9890183457782504, "f1": 0.9944194305282515, "auc": 0.9996556930812918}

metrics_all_fold.json

@@ -0,0 +1,44 @@
+{
+    "precision": [
+        0.8656669790690409,
+        0.9276957718288716,
+        0.9808663803990907,
+        0.9902593295382669,
+        0.994482496194825
+    ],
+    "recall": [
+        0.8785111914273033,
+        0.9405199746353836,
+        0.9849714648065948,
+        0.9927710843373494,
+        0.9943563728598604
+    ],
+    "f1": [
+        0.8720417925478348,
+        0.934063857925562,
+        0.9829146364614314,
+        0.9915136162127929,
+        0.9944194305282515
+    ],
+    "auc": [
+        0.9394272614942787,
+        0.9791706185357555,
+        0.9976812207025214,
+        0.9993127931888565,
+        0.9996556930812918
+    ],
+    "acc": [
+        0.8731871627732901,
+        0.9346890399850291,
+        0.9831576320878298,
+        0.9916411951843304,
+        0.9945106356434409
+    ],
+    "mcc": [
+        0.746447037107958,
+        0.8694527772027904,
+        0.9663167846706998,
+        0.9832816995905711,
+        0.9890183457782504
+    ]
+}

metrics_ci_bounds.json

@@ -0,0 +1,26 @@
+{
+    "precision": {
+        "ci_lower": 0.8833738830452595,
+        "ci_upper": 1.0202144997667784
+    },
+    "recall": {
+        "ci_lower": 0.8965100687138844,
+        "ci_upper": 1.0199419665127125
+    },
+    "f1": {
+        "ci_lower": 0.8899164899500339,
+        "ci_upper": 1.0200648435203152
+    },
+    "auc": {
+        "ci_lower": 0.9509560876310184,
+        "ci_upper": 1.0151429471700633
+    },
+    "acc": {
+        "ci_lower": 0.8909140788106023,
+        "ci_upper": 1.019960187458966
+    },
+    "mcc": {
+        "ci_lower": 0.7819027817722539,
+        "ci_upper": 1.0399038759678538
+    }
+}

metrics_mean.json

@@ -0,0 +1,8 @@
+{
+    "precision": 0.951794191406019,
+    "recall": 0.9582260176132984,
+    "f1": 0.9549906667351745,
+    "auc": 0.9830495174005408,
+    "acc": 0.9554371331347842,
+    "mcc": 0.9109033288700539
+}

metrics_std.json

@@ -0,0 +1,8 @@
+{
+    "precision": 0.05510372247221357,
+    "recall": 0.04970422673822744,
+    "f1": 0.0524088456130476,
+    "auc": 0.02584711308047101,
+    "acc": 0.05196498764361626,
+    "mcc": 0.10389328134214777
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d90de7783c499123fe65e335d2cde00dd1a30a1100aef423f0e83cfe1db8a6
+size 328492280

reduced_main_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd150f0b5bda48f425f8e1b9f4696b7ea437ff7ecda7e84d25dd31c55c0880f0
+size 849480006

test_data_for_future_evaluation.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733dfa5955db9e10d260c78dfecbfb7fafc9b6a8d37eeefdf724910a8cb5f224
+size 157560896

test_top_repo_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe77360c0dd488094d463febe66cedd8a64e4d29c9124ab100df829aed41804
+size 50939436

top_repo_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295d7828a30a1ba76e323db3766d15240b86799484e5d4b2f82cd9f1bd394b2c
+size 40098789

tracker_carbon_statistics.json

@@ -0,0 +1,33 @@
+{
+    "cloud_provider": "",
+    "cloud_region": "",
+    "codecarbon_version": "2.3.4",
+    "country_iso_code": "NOR",
+    "country_name": "Norway",
+    "cpu_count": 64,
+    "cpu_energy": 0.34489881885688994,
+    "cpu_model": "AMD EPYC 7282 16-Core Processor",
+    "cpu_power": 7.064653799305303,
+    "duration": 26893.03911614418,
+    "emissions": 0.30508717075751984,
+    "emissions_rate": 1.134446610663548e-05,
+    "energy_consumed": 11.073944492105984,
+    "gpu_count": 8,
+    "gpu_energy": 10.0258240095417,
+    "gpu_model": "8 x NVIDIA GeForce RTX 2080 Ti",
+    "gpu_power": 1448.943161731065,
+    "latitude": 59.955,
+    "longitude": 10.859,
+    "on_cloud": "N",
+    "os": "Linux-4.18.0-513.9.1.el8_9.x86_64-x86_64-with-glibc2.28",
+    "project_name": "codecarbon",
+    "pue": 1.0,
+    "python_version": "3.10.8",
+    "ram_energy": 0.7032216637073923,
+    "ram_power": 94.2059955596924,
+    "ram_total_size": 251.2159881591797,
+    "region": "oslo county",
+    "run_id": "11e5a3b1-897b-4727-953f-800b88c69faa",
+    "timestamp": "2024-03-06T21:15:39",
+    "tracking_mode": "machine"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f5690b2a5603554c13f29c439ae2d9aa25bbf66bfb42a129aa8aa35ad4b2c1
+size 4664