model update

README.md

@@ -14,7 +14,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.817202380952381
+      value: 0.8133333333333334
   - task:
       name: Analogy Questions (SAT full)
       type: multiple-choice-qa
@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5989304812834224
+      value: 0.6818181818181818
   - task:
       name: Analogy Questions (SAT)
       type: multiple-choice-qa
@@ -36,7 +36,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6083086053412463
+      value: 0.6824925816023739
   - task:
       name: Analogy Questions (BATS)
       type: multiple-choice-qa
@@ -47,7 +47,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7031684269038355
+      value: 0.783212896053363
   - task:
       name: Analogy Questions (Google)
       type: multiple-choice-qa
@@ -58,7 +58,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.892
+      value: 0.934
   - task:
       name: Analogy Questions (U2)
       type: multiple-choice-qa
@@ -69,7 +69,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5964912280701754
+      value: 0.6754385964912281
   - task:
       name: Analogy Questions (U4)
       type: multiple-choice-qa
@@ -80,7 +80,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5740740740740741
+      value: 0.6388888888888888
   - task:
       name: Analogy Questions (ConceptNet Analogy)
       type: multiple-choice-qa
@@ -91,7 +91,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.3976510067114094
+      value: 0.43288590604026844
   - task:
       name: Analogy Questions (TREX Analogy)
       type: multiple-choice-qa
@@ -102,7 +102,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6666666666666666
+      value: 0.6775956284153005
   - task:
       name: Analogy Questions (NELL-ONE Analogy)
       type: multiple-choice-qa
@@ -113,7 +113,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.62
+      value: 0.605
   - task:
       name: Lexical Relation Classification (BLESS)
       type: classification
@@ -124,10 +124,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8998041283712521
+      value: 0.9148711767364774
     - name: F1 (macro)
       type: f1_macro
-      value: 0.896201243435411
+      value: 0.9119056356713013
   - task:
       name: Lexical Relation Classification (CogALexV)
       type: classification
@@ -138,10 +138,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8370892018779342
+      value: 0.8485915492957746
     - name: F1 (macro)
       type: f1_macro
-      value: 0.6583174043371445
+      value: 0.6811794888962958
   - task:
       name: Lexical Relation Classification (EVALution)
       type: classification
@@ -152,10 +152,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.6419284940411701
+      value: 0.6690140845070423
     - name: F1 (macro)
       type: f1_macro
-      value: 0.6294309369547718
+      value: 0.6624009209291007
   - task:
       name: Lexical Relation Classification (K&H+N)
       type: classification
@@ -166,10 +166,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9396953467343674
+      value: 0.9508937886902692
     - name: F1 (macro)
       type: f1_macro
-      value: 0.8459283973092365
+      value: 0.8677983904224069
   - task:
       name: Lexical Relation Classification (ROOT09)
       type: classification
@@ -180,34 +180,34 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8815418364149169
+      value: 0.8918834221247258
     - name: F1 (macro)
       type: f1_macro
-      value: 0.879329189992711
+      value: 0.8905814580868343
 
 ---
 # relbert/relbert-roberta-base-nce-semeval2012-0
 
-RelBERT based on [roberta-base](https://huggingface.co/roberta-base) fine-tuned on [relbert/semeval2012_relational_similarity](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity) (see the [`relbert`](https://github.com/asahi417/relbert) for more detail of fine-tuning).
+RelBERT based on [roberta-large](https://huggingface.co/roberta-large) fine-tuned on [relbert/semeval2012_relational_similarity](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity) (see the [`relbert`](https://github.com/asahi417/relbert) for more detail of fine-tuning).
 This model achieves the following results on the relation understanding tasks:
 - Analogy Question ([dataset](https://huggingface.co/datasets/relbert/analogy_questions), [full result](https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-0/raw/main/analogy.forward.json)):
-    - Accuracy on SAT (full): 0.5989304812834224 
-    - Accuracy on SAT: 0.6083086053412463
-    - Accuracy on BATS: 0.7031684269038355
-    - Accuracy on U2: 0.5964912280701754
-    - Accuracy on U4: 0.5740740740740741
-    - Accuracy on Google: 0.892
-    - Accuracy on ConceptNet Analogy: 0.3976510067114094
-    - Accuracy on T-Rex Analogy: 0.6666666666666666
-    - Accuracy on NELL-ONE Analogy: 0.62
+    - Accuracy on SAT (full): 0.6818181818181818 
+    - Accuracy on SAT: 0.6824925816023739
+    - Accuracy on BATS: 0.783212896053363
+    - Accuracy on U2: 0.6754385964912281
+    - Accuracy on U4: 0.6388888888888888
+    - Accuracy on Google: 0.934
+    - Accuracy on ConceptNet Analogy: 0.43288590604026844
+    - Accuracy on T-Rex Analogy: 0.6775956284153005
+    - Accuracy on NELL-ONE Analogy: 0.605
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-0/raw/main/classification.json)):
-    - Micro F1 score on BLESS: 0.8998041283712521
-    - Micro F1 score on CogALexV: 0.8370892018779342
-    - Micro F1 score on EVALution: 0.6419284940411701
-    - Micro F1 score on K&H+N: 0.9396953467343674
-    - Micro F1 score on ROOT09: 0.8815418364149169
+    - Micro F1 score on BLESS: 0.9148711767364774
+    - Micro F1 score on CogALexV: 0.8485915492957746
+    - Micro F1 score on EVALution: 0.6690140845070423
+    - Micro F1 score on K&H+N: 0.9508937886902692
+    - Micro F1 score on ROOT09: 0.8918834221247258
 - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-0/raw/main/relation_mapping.json)):
-    - Accuracy on Relation Mapping: 0.817202380952381 
+    - Accuracy on Relation Mapping: 0.8133333333333334 
 
 
 ### Usage
@@ -224,7 +224,7 @@ vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (n_dim, )
 
 ### Training hyperparameters
 
- - model: roberta-base
+ - model: roberta-large
  - max_length: 64
  - epoch: 10
  - batch: 32
@@ -239,7 +239,7 @@ vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (n_dim, )
  - split_valid: validation
  - loss_function: nce
  - classification_loss: False
- - loss_function_config: {'temperature': 0.05, 'num_negative': 400, 'num_positive': 10}
+ - loss_function_config: {'temperature': 0.05, 'num_negative': 100, 'num_positive': 10}
  - augment_negative_by_positive: True
 
 See the full configuration at [config file](https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-0/raw/main/finetuning_config.json).

analogy.forward.json

@@ -1 +1 @@
-{"semeval2012_relational_similarity/validation": 0.7848101265822784, "scan/test": 0.2592821782178218, "sat_full/test": 0.5989304812834224, "sat/test": 0.6083086053412463, "u2/test": 0.5964912280701754, "u4/test": 0.5740740740740741, "google/test": 0.892, "bats/test": 0.7031684269038355, "t_rex_relational_similarity/test": 0.6666666666666666, "conceptnet_relational_similarity/test": 0.3976510067114094, "nell_relational_similarity/test": 0.62, "scan/validation": 0.25842696629213485, "sat/validation": 0.5135135135135135, "u2/validation": 0.4583333333333333, "u4/validation": 0.6458333333333334, "google/validation": 0.96, "bats/validation": 0.7738693467336684, "t_rex_relational_similarity/validation": 0.2661290322580645, "conceptnet_relational_similarity/validation": 0.32823741007194246, "nell_relational_similarity/validation": 0.575}
+{"semeval2012_relational_similarity/validation": 0.7468354430379747, "scan/test": 0.2592821782178218, "sat_full/test": 0.6818181818181818, "sat/test": 0.6824925816023739, "u2/test": 0.6754385964912281, "u4/test": 0.6388888888888888, "google/test": 0.934, "bats/test": 0.783212896053363, "t_rex_relational_similarity/test": 0.6775956284153005, "conceptnet_relational_similarity/test": 0.43288590604026844, "nell_relational_similarity/test": 0.605}

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": 0.8998041283712521, "test/f1_macro": 0.896201243435411, "test/f1_micro": 0.8998041283712521, "test/p_macro": 0.8876829436591316, "test/p_micro": 0.8998041283712521, "test/r_macro": 0.9054007585142311, "test/r_micro": 0.8998041283712521}, "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": 0.8370892018779342, "test/f1_macro": 0.6583174043371445, "test/f1_micro": 0.8370892018779342, "test/p_macro": 0.6822907887970884, "test/p_micro": 0.8370892018779342, "test/r_macro": 0.6384370436284232, "test/r_micro": 0.8370892018779342}, "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": 0.6419284940411701, "test/f1_macro": 0.6294309369547718, "test/f1_micro": 0.6419284940411701, "test/p_macro": 0.6360186480100325, "test/p_micro": 0.6419284940411701, "test/r_macro": 0.6300178037199379, "test/r_micro": 0.6419284940411701}, "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": 0.9396953467343674, "test/f1_macro": 0.8459283973092365, "test/f1_micro": 0.9396953467343674, "test/p_macro": 0.8614600859106621, "test/p_micro": 0.9396953467343674, "test/r_macro": 0.8351465630922283, "test/r_micro": 0.9396953467343674}, "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": 0.8815418364149169, "test/f1_macro": 0.879329189992711, "test/f1_micro": 0.8815418364149169, "test/p_macro": 0.8763389203201842, "test/p_micro": 0.8815418364149169, "test/r_macro": 0.882560877928503, "test/r_micro": 0.8815418364149169}}
+{"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": 0.9148711767364773, "test/f1_macro": 0.9119056356713013, "test/f1_micro": 0.9148711767364774, "test/p_macro": 0.908504306097206, "test/p_micro": 0.9148711767364773, "test/r_macro": 0.9162009423798682, "test/r_micro": 0.9148711767364773, "test/f1/attri": 0.9090909090909092, "test/p/attri": 0.9130434782608695, "test/r/attri": 0.9051724137931034, "test/f1/coord": 0.9614309670206819, "test/p/coord": 0.948180815876516, "test/r/coord": 0.9750566893424036, "test/f1/event": 0.8515742128935532, "test/p/event": 0.8145315487571702, "test/r/event": 0.8921465968586387, "test/f1/hyper": 0.9331395348837209, "test/p/hyper": 0.9497041420118343, "test/r/hyper": 0.9171428571428571, "test/f1/mero": 0.8878566688785667, "test/p/mero": 0.8791064388961892, "test/r/mero": 0.8967828418230563, "test/f1/random": 0.9283415212603762, "test/p/random": 0.9464594127806563, "test/r/random": 0.910904255319149}, "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": 0.8485915492957746, "test/f1_macro": 0.6811794888962958, "test/f1_micro": 0.8485915492957746, "test/p_macro": 0.716549900315324, "test/p_micro": 0.8485915492957746, "test/r_macro": 0.6520962513564919, "test/r_micro": 0.8485915492957746, "test/f1/ANT": 0.7326440177252584, "test/p/ANT": 0.7823343848580442, "test/r/ANT": 0.6888888888888889, "test/f1/HYPER": 0.6017441860465116, "test/p/HYPER": 0.6764705882352942, "test/r/HYPER": 0.5418848167539267, "test/f1/PART_OF": 0.6872037914691943, "test/p/PART_OF": 0.7323232323232324, "test/r/PART_OF": 0.6473214285714286, "test/f1/RANDOM": 0.926255562619199, "test/p/RANDOM": 0.9013300340241261, "test/r/RANDOM": 0.952598888525662, "test/f1/SYN": 0.4580498866213152, "test/p/SYN": 0.49029126213592233, "test/r/SYN": 0.4297872340425532}, "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": 0.6690140845070423, "test/f1_macro": 0.6624009209291007, "test/f1_micro": 0.6690140845070423, "test/p_macro": 0.6762790775482931, "test/p_micro": 0.6690140845070423, "test/r_macro": 0.6547629962331695, "test/r_micro": 0.6690140845070423, "test/f1/Antonym": 0.7820512820512822, "test/p/Antonym": 0.8356164383561644, "test/r/Antonym": 0.7349397590361446, "test/f1/HasA": 0.6754098360655738, "test/p/HasA": 0.6319018404907976, "test/r/HasA": 0.7253521126760564, "test/f1/HasProperty": 0.8161434977578476, "test/p/HasProperty": 0.7867435158501441, "test/r/HasProperty": 0.8478260869565217, "test/f1/IsA": 0.6150670794633643, "test/p/IsA": 0.5843137254901961, "test/r/IsA": 0.6492374727668845, "test/f1/MadeOf": 0.6282051282051283, "test/p/MadeOf": 0.7, "test/r/MadeOf": 0.5697674418604651, "test/f1/PartOf": 0.706766917293233, "test/p/PartOf": 0.7768595041322314, "test/r/PartOf": 0.6482758620689655, "test/f1/Synonym": 0.41316270566727603, "test/p/Synonym": 0.4185185185185185, "test/r/Synonym": 0.40794223826714804}, "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": 0.9508937886902692, "test/f1_macro": 0.8677983904224069, "test/f1_micro": 0.9508937886902692, "test/p_macro": 0.8771720388507485, "test/p_micro": 0.9508937886902692, "test/r_macro": 0.8593517976091283, "test/r_micro": 0.9508937886902692, "test/f1/false": 0.960130428338521, "test/p/false": 0.9599881446354476, "test/r/false": 0.9602727542247258, "test/f1/hypo": 0.9278557114228457, "test/p/hypo": 0.9706498951781971, "test/r/hypo": 0.8886756238003839, "test/f1/mero": 0.6263048016701461, "test/p/mero": 0.6276150627615062, "test/r/mero": 0.625, "test/f1/sibl": 0.956902620258115, "test/p/sibl": 0.9504350528278434, "test/r/sibl": 0.9634588124114034}, "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": 0.8918834221247258, "test/f1_macro": 0.8905814580868343, "test/f1_micro": 0.8918834221247258, "test/p_macro": 0.8915743175976042, "test/p_micro": 0.8918834221247258, "test/r_macro": 0.8896098856499345, "test/r_micro": 0.8918834221247258, "test/f1/COORD": 0.971709717097171, "test/p/COORD": 0.9753086419753086, "test/r/COORD": 0.9681372549019608, "test/f1/HYPER": 0.8047117172969622, "test/p/HYPER": 0.8072139303482587, "test/r/HYPER": 0.8022249690976514, "test/f1/RANDOM": 0.8953229398663697, "test/p/RANDOM": 0.8922003804692454, "test/r/RANDOM": 0.8984674329501916}}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaModel"
   ],
@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "relbert_config": {
@@ -24,7 +24,7 @@
     "template": "Today, I finally discovered the relation between <subj> and <obj> : <subj> is the <mask> of <obj>"
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.26.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

finetuning_config.json

@@ -1,6 +1,6 @@
 {
   "template": "Today, I finally discovered the relation between <subj> and <obj> : <subj> is the <mask> of <obj>",
-  "model": "roberta-base",
+  "model": "roberta-large",
   "max_length": 64,
   "epoch": 10,
   "batch": 32,
@@ -17,7 +17,7 @@
   "classification_loss": false,
   "loss_function_config": {
     "temperature": 0.05,
-    "num_negative": 400,
+    "num_negative": 100,
     "num_positive": 10
   },
   "augment_negative_by_positive": true

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94a92b29ec3435777fd39e26c2ad122e32bb0d45e73dc050bca78cbc525fd26
-size 498663921
+oid sha256:3222067087f440c0c63e7bec1c581c12ba961c9c47a777787f99bad40f363360
+size 1421575277

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.json

@@ -53,7 +53,8 @@
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": false,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "post_processor": {
     "type": "RobertaProcessing",
@@ -71,7 +72,8 @@
   "decoder": {
     "type": "ByteLevel",
     "add_prefix_space": true,
-    "trim_offsets": true
+    "trim_offsets": true,
+    "use_regex": true
   },
   "model": {
     "type": "BPE",

tokenizer_config.json

@@ -1 +1,16 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}