add model

analogy.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "sat/test": 0.685459940652819, "sat/valid": 0.7027027027027027, "u2/test": 0.631578947368421, "u2/valid": 0.5416666666666666, "u4/test": 0.6527777777777778, "u4/valid": 0.5416666666666666, "google/test": 0.93, "google/valid": 0.96, "bats/test": 0.7715397443023903, "bats/valid": 0.8241206030150754, "sat_full": 0.6871657754010695}

classification.json

@@ -0,0 +1 @@
+{"lexical_relation_classification/BLESS": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.9205966551152629, "test/f1_macro": 0.9178786648785846, "test/f1_micro": 0.9205966551152629, "test/p_macro": 0.9046966308013684, "test/p_micro": 0.9205966551152629, "test/r_macro": 0.9327432150086388, "test/r_micro": 0.9205966551152629}, "lexical_relation_classification/CogALexV": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.8643192488262911, "test/f1_macro": 0.7176774180702856, "test/f1_micro": 0.8643192488262911, "test/p_macro": 0.7344339835379079, "test/p_micro": 0.8643192488262911, "test/r_macro": 0.7066467961276637, "test/r_micro": 0.8643192488262911}, "lexical_relation_classification/EVALution": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.6814734561213435, "test/f1_macro": 0.6668276311830647, "test/f1_micro": 0.6814734561213435, "test/p_macro": 0.6843695843230375, "test/p_micro": 0.6814734561213435, "test/r_macro": 0.655742273291389, "test/r_micro": 0.6814734561213435}, "lexical_relation_classification/K&H+N": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.9590317868818251, "test/f1_macro": 0.865524335026249, "test/f1_micro": 0.9590317868818251, "test/p_macro": 0.895525142860836, "test/p_micro": 0.9590317868818251, "test/r_macro": 0.8441647225873297, "test/r_micro": 0.9590317868818251}, "lexical_relation_classification/ROOT09": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.8968975242870574, "test/f1_macro": 0.8920343126786042, "test/f1_micro": 0.8968975242870574, "test/p_macro": 0.9032915912744034, "test/p_micro": 0.8968975242870574, "test/r_macro": 0.8846113690524335, "test/r_micro": 0.8968975242870574}}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "relbert-roberta-large-semeval2012-v2-average-prompt-d-nce",
   "architectures": [
     "RobertaModel"
   ],