Update language model pre-trained on even more text

added_tokens.json

@@ -1 +1,237 @@
-{"profitability": 50454, "strategies": 50391, "Principles": 50494, "committed": 50334, "deliver": 50437, "investments": 50282, "achieve": 50379, "insurance": 50296, "objectives": 50387, "transition": 50273, "customers": 50279, "CO2": 50365, "companies": 50271, "consumption": 50314, "assess": 50378, "operating": 50372, "Governance": 50308, "renewable": 50274, "IFC": 50475, "mortgage": 50459, "commitment": 50337, "solutions": 50355, "equity": 50434, "planning": 50435, "costs": 50275, "Sustainable": 50341, "cement": 50492, "resilience": 50433, "requirements": 50335, "across": 50299, "scenarios": 50330, "sectors": 50312, "equivalent": 50457, "methodology": 50483, "financing": 50294, "Committee": 50329, "innovative": 50491, "institutions": 50450, "operate": 50415, "BNP": 50370, "prices": 50484, "achieving": 50498, "Carbon": 50358, "temperature": 50423, "impacts": 50272, "commitments": 50465, "infrastructure": 50310, "operational": 50302, "–": 50317, "included": 50393, "fossil": 50374, "continued": 50443, "challenges": 50400, "annually": 50488, "transactions": 50451, "regulations": 50321, "longer": 50431, "Paribas": 50385, "Corporate": 50408, "standards": 50349, "fiscal": 50436, "engagement": 50397, "particular": 50390, "waste": 50331, "severity": 50468, "2050": 50401, "plans": 50383, "compared": 50467, "addition": 50287, "solar": 50340, "investors": 50356, "clients": 50289, "businesses": 50309, "facilities": 50336, "potential": 50281, "adverse": 50411, "ESG": 50360, "manufacturing": 50425, "factors": 50301, "supporting": 50490, "plants": 50350, "relating": 50461, "failure": 50499, "following": 50371, "sustainable": 50288, "targets": 50305, "practices": 50394, "provide": 50313, "Finance": 50493, "industry": 50292, "developing": 50381, "risks": 50265, "legislation": 50485, "activities": 50283, "portfolios": 50363, "greenhouse": 50323, "supply": 50297, "several": 50416, "portfolio": 50277, "investing": 50392, "tonnes": 50447, "scenario": 50290, "caused": 50410, "stakeholders": 50384, "‘": 50426, "Agreement": 50344, "reduced": 50422, "2030": 50339, "Sustainability": 50362, "criteria": 50477, "claims": 50470, "statements": 50453, "others": 50472, "“": 50373, "vehicles": 50455, "€": 50303, "metrics": 50442, "Eni": 50476, "regarding": 50413, "governance": 50345, "mitigate": 50428, "customer": 50395, "decision": 50481, "suppliers": 50402, "exposed": 50386, "losses": 50346, "investment": 50269, "processes": 50354, "additional": 50367, "GHG": 50322, "footprint": 50338, "Greenhouse": 50463, "electricity": 50291, "buildings": 50404, "environmental": 50268, "sources": 50380, "emissions": 50266, "reducing": 50359, "BlackRock": 50480, "provides": 50409, "countries": 50328, "corporate": 50307, "•": 50276, "manage": 50326, "distribution": 50429, "contribute": 50405, "bond": 50418, "systems": 50333, "opportunities": 50278, "managing": 50421, "towards": 50414, "disasters": 50432, "finance": 50298, "reputational": 50469, "invested": 50439, "partners": 50482, "increase": 50280, "materials": 50357, "Operational": 50486, "considered": 50479, "efforts": 50324, "economy": 50304, "increased": 50293, "possible": 50420, "employees": 50332, "patterns": 50438, "decisions": 50412, "assessment": 50351, "exposure": 50343, "2025": 50403, "increases": 50446, "annual": 50342, "purchase": 50478, "indirect": 50445, "reputation": 50327, "launched": 50440, "significantly": 50458, "approach": 50311, "overall": 50366, "ensure": 50399, "bonds": 50452, "funds": 50398, "affect": 50320, "unable": 50464, "Risk": 50319, "2021": 50347, "goals": 50348, "loans": 50417, "resulting": 50361, "returns": 50495, "further": 50315, "therefore": 50456, "various": 50382, "initiative": 50424, "reduction": 50306, "greater": 50444, "areas": 50318, "strategic": 50300, "reduce": 50284, "adversely": 50497, "regulatory": 50295, "identify": 50377, "operations": 50270, "communities": 50389, "emerging": 50489, "loan": 50396, "floods": 50449, "taken": 50460, "basis": 50473, "already": 50496, "sands": 50441, "conditions": 50376, "construction": 50462, "flooding": 50407, "sustainability": 50285, "mainly": 50466, "dioxide": 50471, "developments": 50474, "policies": 50353, "experience": 50448, "emission": 50388, "asset": 50325, "initiatives": 50316, "transport": 50419, "directly": 50427, "technologies": 50352, "least": 50487, "society": 50364, "fuels": 50375, "’": 50267, "uncertainty": 50406, "—": 50430, "Investment": 50369, "lending": 50368, "strategy": 50286}
+{
+  "+/-": 50403,
+  "2021": 50328,
+  "2030": 50417,
+  "2050": 50487,
+  "CH4": 50354,
+  "CO2": 50265,
+  "Committee": 50410,
+  "GHG": 50397,
+  "N2O": 50382,
+  "achieve": 50437,
+  "across": 50277,
+  "activities": 50317,
+  "adaptation": 50377,
+  "addition": 50303,
+  "additional": 50444,
+  "affect": 50438,
+  "agreement": 50464,
+  "agricultural": 50395,
+  "already": 50435,
+  "analyses": 50485,
+  "annual": 50287,
+  "applied": 50360,
+  "approach": 50290,
+  "areas": 50275,
+  "assess": 50430,
+  "assessment": 50345,
+  "atmosphere": 50341,
+  "atmospheric": 50310,
+  "basis": 50372,
+  "become": 50394,
+  "benefits": 50402,
+  "biomass": 50314,
+  "capture": 50379,
+  "caused": 50389,
+  "challenges": 50404,
+  "characteristics": 50420,
+  "climatic": 50319,
+  "coastal": 50393,
+  "combined": 50451,
+  "communities": 50318,
+  "companies": 50312,
+  "compared": 50282,
+  "composition": 50418,
+  "concentration": 50357,
+  "concentrations": 50366,
+  "conditions": 50272,
+  "conducted": 50439,
+  "conservation": 50458,
+  "considered": 50339,
+  "consistent": 50494,
+  "construction": 50445,
+  "consumption": 50307,
+  "contribute": 50498,
+  "contribution": 50468,
+  "costs": 50326,
+  "countries": 50283,
+  "crisis": 50499,
+  "customers": 50358,
+  "decades": 50495,
+  "decision": 50452,
+  "decrease": 50367,
+  "decreased": 50396,
+  "degrees": 50276,
+  "delta": 50433,
+  "determine": 50480,
+  "determined": 50455,
+  "developing": 50412,
+  "differences": 50375,
+  "dioxide": 50346,
+  "distribution": 50296,
+  "diversity": 50431,
+  "drought": 50336,
+  "dynamics": 50390,
+  "ecological": 50401,
+  "economy": 50338,
+  "ecosystem": 50333,
+  "ecosystems": 50384,
+  "efforts": 50392,
+  "electricity": 50315,
+  "emission": 50279,
+  "emissions": 50266,
+  "employees": 50419,
+  "ensure": 50449,
+  "environmental": 50269,
+  "estimate": 50459,
+  "estimated": 50362,
+  "estimates": 50408,
+  "factors": 50292,
+  "findings": 50492,
+  "flood": 50363,
+  "flux": 50476,
+  "fluxes": 50491,
+  "following": 50369,
+  "forests": 50406,
+  "fossil": 50348,
+  "fuels": 50424,
+  "further": 50301,
+  "gases": 50471,
+  "greater": 50368,
+  "greenhouse": 50289,
+  "however": 50454,
+  "hydrogen": 50376,
+  "identify": 50460,
+  "impacts": 50281,
+  "importance": 50414,
+  "included": 50434,
+  "increase": 50271,
+  "increased": 50274,
+  "increases": 50361,
+  "indicate": 50388,
+  "industry": 50306,
+  "influence": 50329,
+  "infrastructure": 50425,
+  "integrated": 50483,
+  "investigated": 50385,
+  "investment": 50321,
+  "investments": 50466,
+  "least": 50429,
+  "losses": 50462,
+  "mainly": 50399,
+  "materials": 50398,
+  "means": 50486,
+  "measured": 50364,
+  "measurements": 50422,
+  "methane": 50359,
+  "methods": 50378,
+  "mitigation": 50457,
+  "moisture": 50493,
+  "monitoring": 50465,
+  "nitrogen": 50405,
+  "northern": 50446,
+  "observations": 50461,
+  "observed": 50293,
+  "obtained": 50391,
+  "ocean": 50347,
+  "operating": 50440,
+  "operations": 50374,
+  "opportunities": 50469,
+  "overall": 50426,
+  "pandemic": 50490,
+  "parameters": 50383,
+  "particular": 50413,
+  "patterns": 50349,
+  "performed": 50497,
+  "periods": 50432,
+  "planning": 50473,
+  "plans": 50423,
+  "plants": 50313,
+  "policies": 50355,
+  "pollution": 50467,
+  "populations": 50441,
+  "possible": 50332,
+  "potential": 50273,
+  "practices": 50453,
+  "precipitation": 50280,
+  "presented": 50428,
+  "previous": 50482,
+  "processes": 50291,
+  "productivity": 50463,
+  "proposed": 50370,
+  "provide": 50285,
+  "provides": 50373,
+  "rainfall": 50323,
+  "ratio": 50416,
+  "recovery": 50450,
+  "reduce": 50288,
+  "reduced": 50327,
+  "reducing": 50381,
+  "reduction": 50286,
+  "regional": 50308,
+  "regions": 50302,
+  "relationship": 50400,
+  "relatively": 50484,
+  "renewable": 50294,
+  "requirements": 50477,
+  "respectively": 50316,
+  "responses": 50427,
+  "resulting": 50456,
+  "risks": 50309,
+  "scenario": 50421,
+  "scenarios": 50334,
+  "seasonal": 50411,
+  "sediment": 50475,
+  "several": 50342,
+  "shares": 50474,
+  "showed": 50304,
+  "significantly": 50299,
+  "simulations": 50470,
+  "snow": 50496,
+  "soil": 50270,
+  "soils": 50448,
+  "solar": 50320,
+  "solutions": 50351,
+  "sources": 50331,
+  "southern": 50481,
+  "spatial": 50322,
+  "statements": 50472,
+  "strategies": 50387,
+  "strategy": 50353,
+  "structure": 50337,
+  "studied": 50443,
+  "studies": 50297,
+  "summer": 50335,
+  "supply": 50311,
+  "sustainability": 50325,
+  "sustainable": 50284,
+  "systems": 50278,
+  "targets": 50436,
+  "technologies": 50343,
+  "temperature": 50268,
+  "temperatures": 50295,
+  "temporal": 50479,
+  "thermal": 50365,
+  "towards": 50409,
+  "transition": 50344,
+  "transport": 50352,
+  "trees": 50478,
+  "trend": 50407,
+  "trends": 50371,
+  "tropical": 50415,
+  "uncertainty": 50489,
+  "understanding": 50356,
+  "variability": 50298,
+  "variables": 50447,
+  "variation": 50380,
+  "variations": 50442,
+  "various": 50340,
+  "vegetation": 50330,
+  "waste": 50350,
+  "yield": 50386,
+  "–": 50300,
+  "’": 50267,
+  "“": 50305,
+  "”": 50488,
+  "•": 50324
+}

special_tokens_map.json

@@ -1 +1,15 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,65 @@
-{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "language_model/model/ClimateBERT_16102021_acc_grad_roberta/checkpoint-7908", "special_tokens_map_file": "pre_model/14102021_roberta/special_tokens_map.json", "tokenizer_class": "RobertaTokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "language_model/model/ClimateBERT_21072022_acc_grad_roberta",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "pre_model/21072022_roberta/special_tokens_map.json",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}