bert-full-competicao / config.json
vladjr's picture
Training in progress epoch 0
53e52b5
raw
history blame
16.4 kB
{
"_name_or_path": "bert-base-uncased",
"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": "secrecy rate",
"1": "markov geographic model",
"2": "graph convolution networks",
"3": "convolutional neural network",
"4": "computed tomography",
"5": "betweenness centrality",
"6": "forward error correction",
"7": "fusion center",
"8": "random vaccination",
"9": "adversarial risk analysis",
"10": "nash equilibrium",
"11": "maximum likelihood",
"12": "synthetic aperture radar",
"13": "sound pressure level",
"14": "support vector machine",
"15": "high performance computing",
"16": "access point",
"17": "downlink",
"18": "strictly piecewise",
"19": "atomic , independent , declarative , and absolute",
"20": "shortest dependency path",
"21": "multi - layer same - resolution compressed",
"22": "marginal contribution",
"23": "spectral angle distance",
"24": "information retrieval",
"25": "resource description framework",
"26": "atomic function computation",
"27": "part of speech",
"28": "long term evolution",
"29": "mean squared error",
"30": "permutation invariant training",
"31": "minimum generation error",
"32": "alternating least squares",
"33": "reinforcement learning",
"34": "machine learning",
"35": "recurrent neural network",
"36": "recurrent weighted average",
"37": "question answering",
"38": "multiple parallel instances",
"39": "gaussian process",
"40": "base station",
"41": "receiver operating characteristic",
"42": "threshold algorithm",
"43": "click through rates",
"44": "virtual machine",
"45": "test case prioritization",
"46": "neural network",
"47": "belief propagation",
"48": "contention adaptions",
"49": "dynamic induction control",
"50": "information embedding cost",
"51": "lifelong metric learning",
"52": "linear programming",
"53": "multiple description coding",
"54": "latent dirichlet allocation",
"55": "collaborative filtering",
"56": "medium access control",
"57": "description logics",
"58": "radio frequency",
"59": "adaptive radix tree",
"60": "integer linear programming",
"61": "minimum risk training",
"62": "constructive interference",
"63": "line of sight",
"64": "deep belief network",
"65": "average precision",
"66": "dropped pronoun",
"67": "rate distortion function",
"68": "intellectual property",
"69": "geometric programming",
"70": "gaussian mixture model",
"71": "language model",
"72": "adversarially robust distillation",
"73": "controlled natural language",
"74": "federated learning",
"75": "augmented reality",
"76": "matrix factorization",
"77": "principal component analysis",
"78": "node classification",
"79": "smart object",
"80": "poisson point process",
"81": "attention network",
"82": "constrained least squares",
"83": "global positioning system",
"84": "prepositional phrase",
"85": "artificial neural network",
"86": "directed belief net",
"87": "false positive rate",
"88": "latent semantic analysis",
"89": "artificial intelligence",
"90": "model predictive control",
"91": "genetic algorithm",
"92": "access part'",
"93": "sensing application recently",
"94": "mutual information",
"95": "universal dependencies",
"96": "secrecy outage probability",
"97": "statistical compressed sensing",
"98": "information bottleneck",
"99": "ergodic sum capacity",
"100": "image signal processor",
"101": "particle swarm optimization",
"102": "differential rectifier",
"103": "technical debt",
"104": "deep learning",
"105": "hybrid monte carlo",
"106": "ordinary differential equation",
"107": "scalar multiplication",
"108": "inductive logic programming",
"109": "simulated annealing",
"110": "entity set expansion",
"111": "autism spectrum disorders",
"112": "artificial bee colony",
"113": "property graph",
"114": "centralized solution",
"115": "social status",
"116": "taint dependency sequences",
"117": "expectation maximization",
"118": "machine translation",
"119": "dynamic vision sensor",
"120": "automatic speech recognition",
"121": "user equipment",
"122": "random neural networks",
"123": "mean absolute error",
"124": "bayesian network",
"125": "singular value decomposition",
"126": "multimedia event detection",
"127": "median recovery error",
"128": "nearest neighbor",
"129": "friendly jamming",
"130": "formal methods",
"131": "intraclass correlation coefficient",
"132": "central cloud",
"133": "cumulative activation",
"134": "mitral valve",
"135": "discriminative correlation filter",
"136": "transformation error",
"137": "relation extraction",
"138": "linear discriminant analysis",
"139": "integrated circuit",
"140": "stochastic block model",
"141": "information extraction",
"142": "socially assistive robots",
"143": "hierarchical attention network",
"144": "deep reinforcement learning",
"145": "logistic regression",
"146": "message passing interface",
"147": "bug reports",
"148": "alzheimer 's disease",
"149": "data science and analytics",
"150": "automatic differentiation",
"151": "conditional random field",
"152": "false negatives",
"153": "sequential monte carlo",
"154": "basic question",
"155": "physical access",
"156": "point multiplication",
"157": "leicester scientific corpus",
"158": "transformation encoder",
"159": "deep convolutional neural network",
"160": "thompson sampling",
"161": "orthogonal least square",
"162": "acquaintance vaccination",
"163": "rate - selective",
"164": "dynamic assignment ratio",
"165": "multiple description",
"166": "million song dataset",
"167": "machine type communications",
"168": "self attention network",
"169": "term frequency",
"170": "portable document format",
"171": "parameter server",
"172": "physical machines",
"173": "exponential moving average",
"174": "matrix pair beamformer",
"175": "optimal transport",
"176": "finite element method",
"177": "differential evolution",
"178": "product - based neural network",
"179": "mean average conceptual similarity",
"180": "power splitting",
"181": "parkinson 's disease",
"182": "new persian",
"183": "artifact disentanglement network",
"184": "statistical machine translation",
"185": "manifold geometry matching",
"186": "batch normalization",
"187": "rank residual constraint",
"188": "oblivious transfer",
"189": "positive pointwise mutual information",
"190": "triad significance profile",
"191": "reverse classification accuracy",
"192": "fully connected",
"193": "corresponding arcs",
"194": "maximum a posteriori",
"195": "false positive",
"196": "certain natural language",
"197": "strategic dependency",
"198": "strictly local",
"199": "internet protocol",
"200": "foveal tilt effects",
"201": "dynamic cluster",
"202": "domain name system",
"203": "mean average precision",
"204": "semantic role labeling",
"205": "recurrent convolution",
"206": "optical character recognition",
"207": "charging current",
"208": "low resolution",
"209": "power system operations",
"210": "compressive sensing",
"211": "optimal power flow",
"212": "deep context prediction",
"213": "secondary users",
"214": "o - d demand estimation",
"215": "fully convolutional neural network",
"216": "maximal ratio combining",
"217": "quantile random forest",
"218": "adaptive threshold",
"219": "situation entity",
"220": "relay station",
"221": "discrete choice models",
"222": "random forest",
"223": "left ventricle",
"224": "artificial noise"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"access part'": 92,
"access point": 16,
"acquaintance vaccination": 162,
"adaptive radix tree": 59,
"adaptive threshold": 218,
"adversarial risk analysis": 9,
"adversarially robust distillation": 72,
"alternating least squares": 32,
"alzheimer 's disease": 148,
"artifact disentanglement network": 183,
"artificial bee colony": 112,
"artificial intelligence": 89,
"artificial neural network": 85,
"artificial noise": 224,
"atomic , independent , declarative , and absolute": 19,
"atomic function computation": 26,
"attention network": 81,
"augmented reality": 75,
"autism spectrum disorders": 111,
"automatic differentiation": 150,
"automatic speech recognition": 120,
"average precision": 65,
"base station": 40,
"basic question": 154,
"batch normalization": 186,
"bayesian network": 124,
"belief propagation": 47,
"betweenness centrality": 5,
"bug reports": 147,
"central cloud": 132,
"centralized solution": 114,
"certain natural language": 196,
"charging current": 207,
"click through rates": 43,
"collaborative filtering": 55,
"compressive sensing": 210,
"computed tomography": 4,
"conditional random field": 151,
"constrained least squares": 82,
"constructive interference": 62,
"contention adaptions": 48,
"controlled natural language": 73,
"convolutional neural network": 3,
"corresponding arcs": 193,
"cumulative activation": 133,
"data science and analytics": 149,
"deep belief network": 64,
"deep context prediction": 212,
"deep convolutional neural network": 159,
"deep learning": 104,
"deep reinforcement learning": 144,
"description logics": 57,
"differential evolution": 177,
"differential rectifier": 102,
"directed belief net": 86,
"discrete choice models": 221,
"discriminative correlation filter": 135,
"domain name system": 202,
"downlink": 17,
"dropped pronoun": 66,
"dynamic assignment ratio": 164,
"dynamic cluster": 201,
"dynamic induction control": 49,
"dynamic vision sensor": 119,
"entity set expansion": 110,
"ergodic sum capacity": 99,
"expectation maximization": 117,
"exponential moving average": 173,
"false negatives": 152,
"false positive": 195,
"false positive rate": 87,
"federated learning": 74,
"finite element method": 176,
"formal methods": 130,
"forward error correction": 6,
"foveal tilt effects": 200,
"friendly jamming": 129,
"fully connected": 192,
"fully convolutional neural network": 215,
"fusion center": 7,
"gaussian mixture model": 70,
"gaussian process": 39,
"genetic algorithm": 91,
"geometric programming": 69,
"global positioning system": 83,
"graph convolution networks": 2,
"hierarchical attention network": 143,
"high performance computing": 15,
"hybrid monte carlo": 105,
"image signal processor": 100,
"inductive logic programming": 108,
"information bottleneck": 98,
"information embedding cost": 50,
"information extraction": 141,
"information retrieval": 24,
"integer linear programming": 60,
"integrated circuit": 139,
"intellectual property": 68,
"internet protocol": 199,
"intraclass correlation coefficient": 131,
"language model": 71,
"latent dirichlet allocation": 54,
"latent semantic analysis": 88,
"left ventricle": 223,
"leicester scientific corpus": 157,
"lifelong metric learning": 51,
"line of sight": 63,
"linear discriminant analysis": 138,
"linear programming": 52,
"logistic regression": 145,
"long term evolution": 28,
"low resolution": 208,
"machine learning": 34,
"machine translation": 118,
"machine type communications": 167,
"manifold geometry matching": 185,
"marginal contribution": 22,
"markov geographic model": 1,
"matrix factorization": 76,
"matrix pair beamformer": 174,
"maximal ratio combining": 216,
"maximum a posteriori": 194,
"maximum likelihood": 11,
"mean absolute error": 123,
"mean average conceptual similarity": 179,
"mean average precision": 203,
"mean squared error": 29,
"median recovery error": 127,
"medium access control": 56,
"message passing interface": 146,
"million song dataset": 166,
"minimum generation error": 31,
"minimum risk training": 61,
"mitral valve": 134,
"model predictive control": 90,
"multi - layer same - resolution compressed": 21,
"multimedia event detection": 126,
"multiple description": 165,
"multiple description coding": 53,
"multiple parallel instances": 38,
"mutual information": 94,
"nash equilibrium": 10,
"nearest neighbor": 128,
"neural network": 46,
"new persian": 182,
"node classification": 78,
"o - d demand estimation": 214,
"oblivious transfer": 188,
"optical character recognition": 206,
"optimal power flow": 211,
"optimal transport": 175,
"ordinary differential equation": 106,
"orthogonal least square": 161,
"parameter server": 171,
"parkinson 's disease": 181,
"part of speech": 27,
"particle swarm optimization": 101,
"permutation invariant training": 30,
"physical access": 155,
"physical machines": 172,
"point multiplication": 156,
"poisson point process": 80,
"portable document format": 170,
"positive pointwise mutual information": 189,
"power splitting": 180,
"power system operations": 209,
"prepositional phrase": 84,
"principal component analysis": 77,
"product - based neural network": 178,
"property graph": 113,
"quantile random forest": 217,
"question answering": 37,
"radio frequency": 58,
"random forest": 222,
"random neural networks": 122,
"random vaccination": 8,
"rank residual constraint": 187,
"rate - selective": 163,
"rate distortion function": 67,
"receiver operating characteristic": 41,
"recurrent convolution": 205,
"recurrent neural network": 35,
"recurrent weighted average": 36,
"reinforcement learning": 33,
"relation extraction": 137,
"relay station": 220,
"resource description framework": 25,
"reverse classification accuracy": 191,
"scalar multiplication": 107,
"secondary users": 213,
"secrecy outage probability": 96,
"secrecy rate": 0,
"self attention network": 168,
"semantic role labeling": 204,
"sensing application recently": 93,
"sequential monte carlo": 153,
"shortest dependency path": 20,
"simulated annealing": 109,
"singular value decomposition": 125,
"situation entity": 219,
"smart object": 79,
"social status": 115,
"socially assistive robots": 142,
"sound pressure level": 13,
"spectral angle distance": 23,
"statistical compressed sensing": 97,
"statistical machine translation": 184,
"stochastic block model": 140,
"strategic dependency": 197,
"strictly local": 198,
"strictly piecewise": 18,
"support vector machine": 14,
"synthetic aperture radar": 12,
"taint dependency sequences": 116,
"technical debt": 103,
"term frequency": 169,
"test case prioritization": 45,
"thompson sampling": 160,
"threshold algorithm": 42,
"transformation encoder": 158,
"transformation error": 136,
"triad significance profile": 190,
"universal dependencies": 95,
"user equipment": 121,
"virtual machine": 44
},
"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",
"transformers_version": "4.34.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}