Upload 8 files

config.json

@@ -0,0 +1,101 @@
+{
+  "_name_or_path": "esgBERT_CICD/esgBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Access to Communications",
+    "1": "Access to Finance",
+    "2": "Access to Health Care",
+    "3": "Accounting",
+    "4": "Biodiversity and Land Use",
+    "5": "Board",
+    "6": "Business Ethics",
+    "7": "Carbon Emissions",
+    "8": "Chemical Safety",
+    "9": "Climate Change Vulnerability",
+    "10": "Community Relations",
+    "11": "Controversial Sourcing",
+    "12": "Electronic Waste",
+    "13": "Financial Product Safety",
+    "14": "Financing Environmental Impact",
+    "15": "Health and Demographic Risk",
+    "16": "Health and Safety",
+    "17": "Human Capital Development",
+    "18": "Labor Management",
+    "19": "Opportunities in Clean Tech",
+    "20": "Opportunities in Green Building",
+    "21": "Opportunities in Nutrition and Health",
+    "22": "Opportunities in Renewable Energy",
+    "23": "Ownership and Control",
+    "24": "Packaging Material and Waste",
+    "25": "Pay",
+    "26": "Privacy and Data Security",
+    "27": "Product Carbon Footprint",
+    "28": "Product Safety and Quality",
+    "29": "Raw Material Sourcing",
+    "30": "Responsible Investment",
+    "31": "Supply Chain Labor Standards",
+    "32": "Tax Transparency",
+    "33": "Toxic Emissions and Waste",
+    "34": "Water Stress"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Access to Communications": 0,
+    "Access to Finance": 1,
+    "Access to Health Care": 2,
+    "Accounting": 3,
+    "Biodiversity and Land Use": 4,
+    "Board": 5,
+    "Business Ethics": 6,
+    "Carbon Emissions": 7,
+    "Chemical Safety": 8,
+    "Climate Change Vulnerability": 9,
+    "Community Relations": 10,
+    "Controversial Sourcing": 11,
+    "Electronic Waste": 12,
+    "Financial Product Safety": 13,
+    "Financing Environmental Impact": 14,
+    "Health and Demographic Risk": 15,
+    "Health and Safety": 16,
+    "Human Capital Development": 17,
+    "Labor Management": 18,
+    "Opportunities in Clean Tech": 19,
+    "Opportunities in Green Building": 20,
+    "Opportunities in Nutrition and Health": 21,
+    "Opportunities in Renewable Energy": 22,
+    "Ownership and Control": 23,
+    "Packaging Material and Waste": 24,
+    "Pay": 25,
+    "Privacy and Data Security": 26,
+    "Product Carbon Footprint": 27,
+    "Product Safety and Quality": 28,
+    "Raw Material Sourcing": 29,
+    "Responsible Investment": 30,
+    "Supply Chain Labor Standards": 31,
+    "Tax Transparency": 32,
+    "Toxic Emissions and Waste": 33,
+    "Water Stress": 34
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

gitignore

@@ -0,0 +1 @@
+.ipynb_checkpoints

metrics.json

@@ -0,0 +1 @@
+{"eval_loss": 1.3751558065414429, "eval_accuracy": 0.6423027166882277, "eval_f1_micro": 0.6423027166882277, "eval_f1_macro": 0.4537580047630159, "eval_f1_weighted": 0.6294936346451356, "eval_runtime": 2.0229, "eval_samples_per_second": 764.26, "eval_steps_per_second": 95.903, "epoch": 100.0}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609fefbe6288d28b84b2cd0d34671e615fcab6c6c7fcb74fcca4e6c12586a18d
+size 438109429

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d1c10056ec71d7b1443cb642d19e3587fa41d6108a261e2a182b102063cd06
+size 3579