model update

README.md

@@ -113,10 +113,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.9225553714027421
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.9197291498009345
   - task:
       name: Lexical Relation Classification (CogALexV)
       type: classification
@@ -127,10 +127,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.8448356807511737
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.6748981211013405
   - task:
       name: Lexical Relation Classification (EVALution)
       type: classification
@@ -141,10 +141,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.6847237269772481
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.6766012034119605
   - task:
       name: Lexical Relation Classification (K&H+N)
       type: classification
@@ -155,10 +155,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.9536760102942199
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.8593518348956461
   - task:
       name: Lexical Relation Classification (ROOT09)
       type: classification
@@ -169,10 +169,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: None
+      value: 0.9072391099968662
     - name: F1 (macro)
       type: f1_macro
-      value: None
+      value: 0.9056105194658931
 
 ---
 # relbert/relbert-roberta-large-nce-e-semeval2012
@@ -189,11 +189,11 @@ This model achieves the following results on the relation understanding tasks:
     - Accuracy on ConceptNet Analogy: 0.3640939597315436
     - Accuracy on T-Rex Analogy: 0.5846994535519126
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-e-semeval2012/raw/main/classification.json)):
-    - Micro F1 score on BLESS: None
-    - Micro F1 score on CogALexV: None
-    - Micro F1 score on EVALution: None
-    - Micro F1 score on K&H+N: None
-    - Micro F1 score on ROOT09: None
+    - Micro F1 score on BLESS: 0.9225553714027421
+    - Micro F1 score on CogALexV: 0.8448356807511737
+    - Micro F1 score on EVALution: 0.6847237269772481
+    - Micro F1 score on K&H+N: 0.9536760102942199
+    - Micro F1 score on ROOT09: 0.9072391099968662
 - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-e-semeval2012/raw/main/relation_mapping.json)):
     - Accuracy on Relation Mapping: 0.8825793650793651 
 

classification.json

@@ -1 +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": 0.92240470091909, "test/f1_macro": 0.9188233632869808, "test/f1_micro": 0.92240470091909, "test/p_macro": 0.9183108289528753, "test/p_micro": 0.92240470091909, "test/r_macro": 0.9194352763902186, "test/r_micro": 0.92240470091909}, "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": 0.8546948356807512, "test/f1_macro": 0.6896373041346763, "test/f1_micro": 0.8546948356807512, "test/p_macro": 0.7148463319701758, "test/p_micro": 0.8546948356807512, "test/r_macro": 0.6700660518744752, "test/r_micro": 0.8546948356807512}, "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": 0.6863488624052004, "test/f1_macro": 0.6694518857409998, "test/f1_micro": 0.6863488624052004, "test/p_macro": 0.6819920226152291, "test/p_micro": 0.6863488624052004, "test/r_macro": 0.6672826960878729, "test/r_micro": 0.6863488624052004}, "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": 0.9589622313417264, "test/f1_macro": 0.8730986989284496, "test/f1_micro": 0.9589622313417264, "test/p_macro": 0.8707798136462076, "test/p_micro": 0.9589622313417264, "test/r_macro": 0.8755540260729457, "test/r_micro": 0.9589622313417264}, "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": 0.9138201190849263, "test/f1_macro": 0.9121911051636283, "test/f1_micro": 0.9138201190849262, "test/p_macro": 0.9121801667203941, "test/p_micro": 0.9138201190849263, "test/r_macro": 0.9122317099157158, "test/r_micro": 0.9138201190849263}}
+{"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": 0.9225553714027422, "test/f1_macro": 0.9197291498009345, "test/f1_micro": 0.9225553714027421, "test/p_macro": 0.9150094905573273, "test/p_micro": 0.9225553714027422, "test/r_macro": 0.9255428117096391, "test/r_micro": 0.9225553714027422}, "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": 0.8448356807511737, "test/f1_macro": 0.6748981211013405, "test/f1_micro": 0.8448356807511737, "test/p_macro": 0.6910806285341508, "test/p_micro": 0.8448356807511737, "test/r_macro": 0.662819068684954, "test/r_micro": 0.8448356807511737}, "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": 0.6847237269772481, "test/f1_macro": 0.6766012034119605, "test/f1_micro": 0.6847237269772481, "test/p_macro": 0.6885422680797412, "test/p_micro": 0.6847237269772481, "test/r_macro": 0.6679318977886294, "test/r_micro": 0.6847237269772481}, "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": 0.9536760102942199, "test/f1_macro": 0.8593518348956461, "test/f1_micro": 0.9536760102942199, "test/p_macro": 0.8369706300928008, "test/p_micro": 0.9536760102942199, "test/r_macro": 0.8877934020457473, "test/r_micro": 0.9536760102942199}, "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": 0.9072391099968662, "test/f1_macro": 0.9056105194658931, "test/f1_micro": 0.9072391099968662, "test/p_macro": 0.9072040983082953, "test/p_micro": 0.9072391099968662, "test/r_macro": 0.9041836458174983, "test/r_micro": 0.9072391099968662}}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "relbert_output/ckpt/nce_semeval2012/template-e/epoch_6",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaModel"
   ],

tokenizer_config.json

@@ -6,7 +6,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "relbert_output/ckpt/nce_semeval2012/template-e/epoch_6",
+  "name_or_path": "roberta-large",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,