karths commited on Mar 6, 2024

Commit

de67367

verified ·

1 Parent(s): d566f26

Upload folder using huggingface_hub

Browse files

Files changed (31) hide show

.gitattributes +3 -0
.ipynb_checkpoints/classification_report-checkpoint.json +1 -0
.ipynb_checkpoints/detailed_confusion_matrix-checkpoint.png +0 -0
.ipynb_checkpoints/metrics_visualisation-checkpoint.png +0 -0
checkpoint-20225/config.json +28 -0
checkpoint-20225/model.safetensors +3 -0
checkpoint-20225/optimizer.pt +3 -0
checkpoint-20225/rng_state.pth +3 -0
checkpoint-20225/scheduler.pt +3 -0
checkpoint-20225/trainer_state.json +259 -0
checkpoint-20225/training_args.bin +3 -0
classification_report.json +1 -0
config.json +28 -0
confusion_matrix.png +0 -0
detailed_confusion_matrix.png +0 -0
fold_results.json +67 -0
metrics.json +1 -0
metrics_all_fold.json +44 -0
metrics_ci_bounds.json +26 -0
metrics_mean.json +8 -0
metrics_std.json +8 -0
metrics_visualisation.png +0 -0
model.safetensors +3 -0
precision_recall_curve.png +0 -0
reduced_main_data.csv +3 -0
roc_curve.png +0 -0
test_data_for_future_evaluation.csv +3 -0
test_top_repo_data.csv +3 -0
top_repo_data.csv +0 -0
tracker_carbon_statistics.json +33 -0
training_args.bin +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,6 @@ 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

 *.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

.ipynb_checkpoints/classification_report-checkpoint.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"0": {"precision": 0.9938446386802905, "recall": 0.9927447122479095, "f1-score": 0.9932943709627806, "support": 32528}, "1": {"precision": 0.9926785381894894, "recall": 0.9937884340642276, "f1-score": 0.9932331760615842, "support": 32198}, "accuracy": 0.9932639124926613, "macro avg": {"precision": 0.9932615884348899, "recall": 0.9932665731560686, "f1-score": 0.9932637735121824, "support": 64726}, "weighted avg": {"precision": 0.9932645610669232, "recall": 0.9932639124926613, "f1-score": 0.9932639295106792, "support": 64726}}

.ipynb_checkpoints/detailed_confusion_matrix-checkpoint.png ADDED Viewed

.ipynb_checkpoints/metrics_visualisation-checkpoint.png ADDED Viewed

checkpoint-20225/config.json ADDED Viewed

	@@ -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-20225/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3946f649e08ed1c426447fd675d0096763e375885361ebb6cbb6723ac6f28f95
+size 328492280

checkpoint-20225/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a92bdff77e1da2f3f8c126d292c9e434b9941b4ee9f5560a1a15a776718978
+size 657047610

checkpoint-20225/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0618e19467fe9ca49fc6595ae81ac4036af305ae39cc2f7919069252abbcf9bc
+size 14244

checkpoint-20225/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fd75a6e80d2ac16734471e00c93a470bbdd017b254fd418d9792de84053859
+size 1064

checkpoint-20225/trainer_state.json ADDED Viewed

	@@ -0,0 +1,259 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9993820294154,
+  "eval_steps": 500,
+  "global_step": 20225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 0.0572,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.9921402862953804e-05,
+      "loss": 0.0701,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.968484642500649e-05,
+      "loss": 0.0733,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.92918287952728e-05,
+      "loss": 0.0821,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.8744841056973686e-05,
+      "loss": 0.0868,
+      "step": 2500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.8047350209739364e-05,
+      "loss": 0.0855,
+      "step": 3000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.720377719455276e-05,
+      "loss": 0.0851,
+      "step": 3500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.6219468872279157e-05,
+      "loss": 0.085,
+      "step": 4000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.510303139450832e-05,
+      "loss": 0.0704,
+      "step": 4500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.385706880295634e-05,
+      "loss": 0.0715,
+      "step": 5000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 0.0704,
+      "step": 5500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 4.101523044757859e-05,
+      "loss": 0.075,
+      "step": 6000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 3.94406177364273e-05,
+      "loss": 0.0718,
+      "step": 6500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.7771418094841905e-05,
+      "loss": 0.0701,
+      "step": 7000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.602126873772994e-05,
+      "loss": 0.0686,
+      "step": 7500
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.420126272394637e-05,
+      "loss": 0.0666,
+      "step": 8000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 3.2326742887008035e-05,
+      "loss": 0.0596,
+      "step": 8500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.0402081462665028e-05,
+      "loss": 0.0535,
+      "step": 9000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.844317975627921e-05,
+      "loss": 0.053,
+      "step": 9500
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.6462453972120053e-05,
+      "loss": 0.0531,
+      "step": 10000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.447643950291608e-05,
+      "loss": 0.0509,
+      "step": 10500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.24937302895087e-05,
+      "loss": 0.0528,
+      "step": 11000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.0522925817157924e-05,
+      "loss": 0.0509,
+      "step": 11500
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.858049860712845e-05,
+      "loss": 0.0534,
+      "step": 12000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 1.6678760442568807e-05,
+      "loss": 0.0397,
+      "step": 12500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.4829765205223683e-05,
+      "loss": 0.0384,
+      "step": 13000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.3045232473714773e-05,
+      "loss": 0.0378,
+      "step": 13500
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.1339807851507919e-05,
+      "loss": 0.0395,
+      "step": 14000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 9.717469167141063e-06,
+      "loss": 0.0417,
+      "step": 14500
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 8.191996509260754e-06,
+      "loss": 0.0412,
+      "step": 15000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 6.773058857206802e-06,
+      "loss": 0.0405,
+      "step": 15500
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 5.469649934184448e-06,
+      "loss": 0.0404,
+      "step": 16000
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 4.292261791598673e-06,
+      "loss": 0.0324,
+      "step": 16500
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 3.243640635932488e-06,
+      "loss": 0.0339,
+      "step": 17000
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 2.3329188966299516e-06,
+      "loss": 0.0355,
+      "step": 17500
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 1.565869046659435e-06,
+      "loss": 0.0357,
+      "step": 18000
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 9.484389467240757e-07,
+      "loss": 0.0335,
+      "step": 18500
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 4.820687255986694e-07,
+      "loss": 0.0346,
+      "step": 19000
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 1.711017296455786e-07,
+      "loss": 0.0391,
+      "step": 19500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 1.750897646625449e-08,
+      "loss": 0.0438,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20225,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.7146262160275866e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20225/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0992365096820d3986d2dcce239035c87f1cb33d7b827bb94719fa843996c1c
+size 4664

classification_report.json ADDED Viewed

	@@ -0,0 +1 @@

config.json ADDED Viewed

	@@ -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
+}

confusion_matrix.png ADDED Viewed

detailed_confusion_matrix.png ADDED Viewed

fold_results.json ADDED Viewed

	@@ -0,0 +1,67 @@

+{
+    "0": {
+        "eval_loss": 0.5060291290283203,
+        "eval_precision": 0.7967351550652672,
+        "eval_recall": 0.8321945462451084,
+        "eval_acc": 0.8109135291300384,
+        "eval_mcc": 0.622513076828615,
+        "eval_f1": 0.8140789013960413,
+        "eval_auc": 0.8931432140257628,
+        "eval_runtime": 136.9966,
+        "eval_samples_per_second": 472.472,
+        "eval_steps_per_second": 7.387,
+        "epoch": 5.0
+    },
+    "1": {
+        "eval_loss": 0.3167250156402588,
+        "eval_precision": 0.8843102821848129,
+        "eval_recall": 0.9071060314305236,
+        "eval_acc": 0.8947579835308295,
+        "eval_mcc": 0.7897977887593852,
+        "eval_f1": 0.8955631190016251,
+        "eval_auc": 0.9604396576501993,
+        "eval_runtime": 141.4613,
+        "eval_samples_per_second": 457.56,
+        "eval_steps_per_second": 7.154,
+        "epoch": 5.0
+    },
+    "2": {
+        "eval_loss": 0.1585075855255127,
+        "eval_precision": 0.9500986314881026,
+        "eval_recall": 0.9573575998509224,
+        "eval_acc": 0.9537743719679881,
+        "eval_mcc": 0.9075761429456463,
+        "eval_f1": 0.953714303394078,
+        "eval_auc": 0.9907196110403268,
+        "eval_runtime": 146.6969,
+        "eval_samples_per_second": 441.223,
+        "eval_steps_per_second": 6.899,
+        "epoch": 5.0
+    },
+    "3": {
+        "eval_loss": 0.040100980550050735,
+        "eval_precision": 0.9867785484270498,
+        "eval_recall": 0.9897819740356544,
+        "eval_acc": 0.9883199950560826,
+        "eval_mcc": 0.9766442214096415,
+        "eval_f1": 0.988277979346916,
+        "eval_auc": 0.9991408654599567,
+        "eval_runtime": 153.7473,
+        "eval_samples_per_second": 420.989,
+        "eval_steps_per_second": 6.582,
+        "epoch": 5.0
+    },
+    "4": {
+        "eval_loss": 0.023310726508498192,
+        "eval_precision": 0.9926785381894894,
+        "eval_recall": 0.9937884340642276,
+        "eval_acc": 0.9932639124926613,
+        "eval_mcc": 0.9865281615783651,
+        "eval_f1": 0.9932331760615842,
+        "eval_auc": 0.9996474991710019,
+        "eval_runtime": 157.9023,
+        "eval_samples_per_second": 409.912,
+        "eval_steps_per_second": 6.409,
+        "epoch": 5.0
+    }
+}

metrics.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"precision": 0.9926785381894894, "recall": 0.9937884340642276, "acc": 0.9932639124926613, "mcc": 0.9865281615783651, "f1": 0.9932331760615842, "auc": 0.9996474991710019}

metrics_all_fold.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+    "precision": [
+        0.7967351550652672,
+        0.8843102821848129,
+        0.9500986314881026,
+        0.9867785484270498,
+        0.9926785381894894
+    ],
+    "recall": [
+        0.8321945462451084,
+        0.9071060314305236,
+        0.9573575998509224,
+        0.9897819740356544,
+        0.9937884340642276
+    ],
+    "f1": [
+        0.8140789013960413,
+        0.8955631190016251,
+        0.953714303394078,
+        0.988277979346916,
+        0.9932331760615842
+    ],
+    "auc": [
+        0.8931432140257628,
+        0.9604396576501993,
+        0.9907196110403268,
+        0.9991408654599567,
+        0.9996474991710019
+    ],
+    "acc": [
+        0.8109135291300384,
+        0.8947579835308295,
+        0.9537743719679881,
+        0.9883199950560826,
+        0.9932639124926613
+    ],
+    "mcc": [
+        0.622513076828615,
+        0.7897977887593852,
+        0.9075761429456463,
+        0.9766442214096415,
+        0.9865281615783651
+    ]
+}

metrics_ci_bounds.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+    "precision": {
+        "ci_lower": 0.819931636459632,
+        "ci_upper": 1.024308825682257
+    },
+    "recall": {
+        "ci_lower": 0.8520643929619907,
+        "ci_upper": 1.0200270412885837
+    },
+    "f1": {
+        "ci_lower": 0.8356926730718772,
+        "ci_upper": 1.0222543186082205
+    },
+    "auc": {
+        "ci_lower": 0.9125838770880396,
+        "ci_upper": 1.0246524618508595
+    },
+    "acc": {
+        "ci_lower": 0.8332851116883261,
+        "ci_upper": 1.0231268051827143
+    },
+    "mcc": {
+        "ci_lower": 0.6671312144596856,
+        "ci_upper": 1.0460925421489755
+    }
+}

metrics_mean.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "precision": 0.9221202310709444,
+    "recall": 0.9360457171252872,
+    "f1": 0.9289734958400488,
+    "auc": 0.9686181694694496,
+    "acc": 0.9282059584355201,
+    "mcc": 0.8566118783043306
+}

metrics_std.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "precision": 0.0822997161544041,
+    "recall": 0.06763611112570454,
+    "f1": 0.07512565629922013,
+    "auc": 0.0451283861515443,
+    "acc": 0.07644648381889932,
+    "mcc": 0.15260220487889975
+}

metrics_visualisation.png ADDED Viewed

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3946f649e08ed1c426447fd675d0096763e375885361ebb6cbb6723ac6f28f95
+size 328492280

precision_recall_curve.png ADDED Viewed

reduced_main_data.csv ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:331d097c71f6a71603e10b9b53edfd360a04641997a3fe95f146dd4781bf432b
+size 1297101676

roc_curve.png ADDED Viewed

test_data_for_future_evaluation.csv ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7fba173ec0075297e47979ff939e2df3317001c133226328fd117e77e082f4
+size 225010581

test_top_repo_data.csv ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:221c223860b5370c4eb82f7b066ee6ff2ccc59bdaaf2fc766735548e5c89b89b
+size 16699625

top_repo_data.csv ADDED Viewed

The diff for this file is too large to render. See raw diff

tracker_carbon_statistics.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+    "cloud_provider": "",
+    "cloud_region": "",
+    "codecarbon_version": "2.3.4",
+    "country_iso_code": "NOR",
+    "country_name": "Norway",
+    "cpu_count": 192,
+    "cpu_energy": 0.38921054652735465,
+    "cpu_model": "AMD EPYC 7642 48-Core Processor",
+    "cpu_power": 7.467583301764944,
+    "duration": 37233.803218364716,
+    "emissions": 0.2889990545305626,
+    "emissions_rate": 7.76173878439634e-06,
+    "energy_consumed": 10.48998383051044,
+    "gpu_count": 4,
+    "gpu_energy": 6.198644186411384,
+    "gpu_model": "4 x NVIDIA GeForce RTX 3090",
+    "gpu_power": 616.9618014352897,
+    "latitude": 59.955,
+    "longitude": 10.859,
+    "on_cloud": "N",
+    "os": "Linux-4.18.0-513.11.1.el8_9.x86_64-x86_64-with-glibc2.28",
+    "project_name": "codecarbon",
+    "pue": 1.0,
+    "python_version": "3.10.8",
+    "ram_energy": 3.902129097571703,
+    "ram_power": 377.6938133239746,
+    "ram_total_size": 1007.1835021972656,
+    "region": "oslo county",
+    "run_id": "02adcb47-62a8-4727-a0c2-241bfe72ef89",
+    "timestamp": "2024-03-01T02:00:13",
+    "tracking_mode": "machine"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0992365096820d3986d2dcce239035c87f1cb33d7b827bb94719fa843996c1c
+size 4664