init

README.md

@@ -2,7 +2,7 @@
 datasets:
 - relbert/semeval2012_relational_similarity
 model-index:
-- name: relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce
+- name: relbert/relbert-roberta-large-nce-d-0
   results:
   - task:
       name: Relation Mapping
@@ -14,7 +14,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9407142857142857
+      value: 0.8022222222222222
   - task:
       name: Analogy Questions (SAT full)
       type: multiple-choice-qa
@@ -25,7 +25,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7165775401069518
+      value: 0.7219251336898396
   - task:
       name: Analogy Questions (SAT)
       type: multiple-choice-qa
@@ -36,7 +36,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7151335311572701
+      value: 0.7270029673590505
   - task:
       name: Analogy Questions (BATS)
       type: multiple-choice-qa
@@ -47,7 +47,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8126737076153419
+      value: 0.7937743190661478
   - task:
       name: Analogy Questions (Google)
       type: multiple-choice-qa
@@ -58,7 +58,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.964
+      value: 0.942
   - task:
       name: Analogy Questions (U2)
       type: multiple-choice-qa
@@ -69,7 +69,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7192982456140351
+      value: 0.6578947368421053
   - task:
       name: Analogy Questions (U4)
       type: multiple-choice-qa
@@ -80,7 +80,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6921296296296297
+      value: 0.6527777777777778
   - task:
       name: Lexical Relation Classification (BLESS)
       type: classification
@@ -91,10 +91,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9251167696248305
+      value: 0.9193912912460449
     - name: F1 (macro)
       type: f1_macro
-      value: 0.9196346516032302
+      value: 0.9154281897413815
   - task:
       name: Lexical Relation Classification (CogALexV)
       type: classification
@@ -105,10 +105,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8607981220657277
+      value: 0.855868544600939
     - name: F1 (macro)
       type: f1_macro
-      value: 0.7029050751301971
+      value: 0.6848847419105534
   - task:
       name: Lexical Relation Classification (EVALution)
       type: classification
@@ -119,10 +119,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.6841820151679306
+      value: 0.6890574214517876
     - name: F1 (macro)
       type: f1_macro
-      value: 0.6749077706444823
+      value: 0.6776463157716582
   - task:
       name: Lexical Relation Classification (K&H+N)
       type: classification
@@ -133,10 +133,10 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9595882312026153
+      value: 0.960283786603603
     - name: F1 (macro)
       type: f1_macro
-      value: 0.8789234569786473
+      value: 0.8788008952006335
   - task:
       name: Lexical Relation Classification (ROOT09)
       type: classification
@@ -150,33 +150,28 @@ model-index:
       value: 0.9103729238483234
     - name: F1 (macro)
       type: f1_macro
-      value: 0.9076447549069412
+      value: 0.9087639459806999
 
 ---
+# relbert/relbert-roberta-large-nce-d-0
 
-# Copy of https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce
-
-# relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce
-
-RelBERT fine-tuned from [roberta-large](https://huggingface.co/roberta-large) on  
-[relbert/semeval2012_relational_similarity](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity).
-Fine-tuning is done via [RelBERT](https://github.com/asahi417/relbert) library (see the repository for more detail).
-It 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-large-semeval2012-average-prompt-d-nce/raw/main/analogy.json)):
-    - Accuracy on SAT (full): 0.7165775401069518 
-    - Accuracy on SAT: 0.7151335311572701
-    - Accuracy on BATS: 0.8126737076153419
-    - Accuracy on U2: 0.7192982456140351
-    - Accuracy on U4: 0.6921296296296297
-    - Accuracy on Google: 0.964
-- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce/raw/main/classification.json)):
-    - Micro F1 score on BLESS: 0.9251167696248305
-    - Micro F1 score on CogALexV: 0.8607981220657277
-    - Micro F1 score on EVALution: 0.6841820151679306
-    - Micro F1 score on K&H+N: 0.9595882312026153
+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-large-nce-d-0/raw/main/analogy.forward.json)):
+    - Accuracy on SAT (full): 0.7219251336898396 
+    - Accuracy on SAT: 0.7270029673590505
+    - Accuracy on BATS: 0.7937743190661478
+    - Accuracy on U2: 0.6578947368421053
+    - Accuracy on U4: 0.6527777777777778
+    - Accuracy on Google: 0.942
+- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-d-0/raw/main/classification.json)):
+    - Micro F1 score on BLESS: 0.9193912912460449
+    - Micro F1 score on CogALexV: 0.855868544600939
+    - Micro F1 score on EVALution: 0.6890574214517876
+    - Micro F1 score on K&H+N: 0.960283786603603
     - Micro F1 score on ROOT09: 0.9103729238483234
-- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce/raw/main/relation_mapping.json)):
-    - Accuracy on Relation Mapping: 0.9407142857142857 
+- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-d-0/raw/main/relation_mapping.json)):
+    - Accuracy on Relation Mapping: 0.8022222222222222 
 
 
 ### Usage
@@ -187,49 +182,49 @@ pip install relbert
 and activate model as below.
 ```python
 from relbert import RelBERT
-model = RelBERT("relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce")
-vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (1024, )
+model = RelBERT("relbert/relbert-roberta-large-nce-d-0")
+vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (n_dim, )
 ```
 
 ### Training hyperparameters
 
-The following hyperparameters were used during training:
  - model: roberta-large
  - max_length: 64
- - mode: average
- - data: relbert/semeval2012_relational_similarity
- - template_mode: manual
- - template: I wasn’t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>
- - loss_function: nce_logout
- - temperature_nce_constant: 0.05
- - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
- - epoch: 29
- - batch: 128
- - lr: 5e-06
- - lr_decay: False
- - lr_warmup: 1
- - weight_decay: 0
+ - epoch: 10
+ - batch: 32
  - random_seed: 0
+ - lr: 5e-06
+ - lr_warmup: 10
+ - aggregation_mode: average_no_mask
+ - data: relbert/semeval2012_relational_similarity
  - exclude_relation: None
- - n_sample: 640
- - gradient_accumulation: 8
+ - split: train
+ - split_valid: validation
+ - loss_function: nce
+ - classification_loss: False
+ - loss_function_config: {'temperature': 0.05, 'gradient_accumulation': 1, 'num_negative': 400, 'num_positive': 10}
 
-The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-prompt-d-nce/raw/main/trainer_config.json).
+See the full configuration at [config file](https://huggingface.co/relbert/relbert-roberta-large-nce-d-0/raw/main/finetuning_config.json).
 
 ### Reference
-If you use any resource from RelBERT, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
+If you use any resource from RelBERT, please consider to cite our [paper](https://aclanthology.org/2021.emnlp-main.712/).
 
 ```
 
-@inproceedings{ushio-etal-2021-distilling-relation-embeddings,
-    title = "{D}istilling {R}elation {E}mbeddings from {P}re-trained {L}anguage {M}odels",
+@inproceedings{ushio-etal-2021-distilling,
+    title = "Distilling Relation Embeddings from Pretrained Language Models",
     author = "Ushio, Asahi  and
-      Schockaert, Steven  and
-      Camacho-Collados, Jose",
-    booktitle = "EMNLP 2021",
+      Camacho-Collados, Jose  and
+      Schockaert, Steven",
+    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
+    month = nov,
     year = "2021",
-    address = "Online",
+    address = "Online and Punta Cana, Dominican Republic",
     publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2021.emnlp-main.712",
+    doi = "10.18653/v1/2021.emnlp-main.712",
+    pages = "9044--9062",
+    abstract = "Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it possible to distill high-quality word vectors from pre-trained language models. However, it is currently unclear to what extent it is possible to distill relation embeddings, i.e. vectors that characterize the relationship between two words. Such relation embeddings are appealing because they can, in principle, encode relational knowledge in a more fine-grained way than is possible with knowledge graphs. To obtain relation embeddings from a pre-trained language model, we encode word pairs using a (manually or automatically generated) prompt, and we fine-tune the language model such that relationally similar word pairs yield similar output vectors. We find that the resulting relation embeddings are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks, even without any task-specific fine-tuning. Source code to reproduce our experimental results and the model checkpoints are available in the following repository: https://github.com/asahi417/relbert",
 }
 
 ```

analogy.bidirection.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "sat/test": 0.7270029673590505, "u2/test": 0.6578947368421053, "u4/test": 0.6527777777777778, "google/test": 0.942, "bats/test": 0.7937743190661478, "sat_full": 0.7219251336898396, "sat/validation": 0.6756756756756757, "u2/validation": 0.625, "u4/validation": 0.6458333333333334, "google/validation": 0.96, "bats/validation": 0.8341708542713567}

analogy.forward.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "sat/test": 0.7270029673590505, "u2/test": 0.6578947368421053, "u4/test": 0.6527777777777778, "google/test": 0.942, "bats/test": 0.7937743190661478, "sat_full": 0.7219251336898396, "sat/validation": 0.6756756756756757, "u2/validation": 0.625, "u4/validation": 0.6458333333333334, "google/validation": 0.96, "bats/validation": 0.8341708542713567}

analogy.reverse.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "sat/test": 0.7270029673590505, "u2/test": 0.6578947368421053, "u4/test": 0.6527777777777778, "google/test": 0.942, "bats/test": 0.7937743190661478, "sat_full": 0.7219251336898396, "sat/validation": 0.6756756756756757, "u2/validation": 0.625, "u4/validation": 0.6458333333333334, "google/validation": 0.96, "bats/validation": 0.8341708542713567}

analogy_relation_dataset.bidirection.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "relbert/semeval2012_relational_similarity/validation": 0.759493670886076}

analogy_relation_dataset.forward.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "relbert/semeval2012_relational_similarity/validation": 0.759493670886076}

analogy_relation_dataset.reverse.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "model": "relbert_output/ckpt/nce/template-d.random-0/model", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "aggregation": "average_no_mask", "relbert/semeval2012_relational_similarity/validation": 0.7088607594936709}

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": 0.9251167696248305, "test/f1_macro": 0.9196346516032302, "test/f1_micro": 0.9251167696248305, "test/p_macro": 0.9228914915504977, "test/p_micro": 0.9251167696248305, "test/r_macro": 0.9167390763548414, "test/r_micro": 0.9251167696248305}, "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": 0.8607981220657277, "test/f1_macro": 0.7029050751301971, "test/f1_micro": 0.8607981220657277, "test/p_macro": 0.7313949055416683, "test/p_micro": 0.8607981220657277, "test/r_macro": 0.6804383005626553, "test/r_micro": 0.8607981220657277}, "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": 0.6841820151679306, "test/f1_macro": 0.6749077706444823, "test/f1_micro": 0.6841820151679306, "test/p_macro": 0.6822611969186971, "test/p_micro": 0.6841820151679306, "test/r_macro": 0.6691999606355179, "test/r_micro": 0.6841820151679306}, "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": 0.9595882312026153, "test/f1_macro": 0.8789234569786473, "test/f1_micro": 0.9595882312026153, "test/p_macro": 0.8849555927607803, "test/p_micro": 0.9595882312026153, "test/r_macro": 0.8732016591900109, "test/r_micro": 0.9595882312026153}, "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": 0.9103729238483234, "test/f1_macro": 0.9076447549069412, "test/f1_micro": 0.9103729238483234, "test/p_macro": 0.9086898349896138, "test/p_micro": 0.9103729238483234, "test/r_macro": 0.9069026663387998, "test/r_micro": 0.9103729238483234}}
+{"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": 0.9193912912460449, "test/f1_macro": 0.9154281897413815, "test/f1_micro": 0.9193912912460449, "test/p_macro": 0.909030256916922, "test/p_micro": 0.9193912912460449, "test/r_macro": 0.9234515644685003, "test/r_micro": 0.9193912912460449}, "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": 0.855868544600939, "test/f1_macro": 0.6848847419105534, "test/f1_micro": 0.855868544600939, "test/p_macro": 0.7136216119555865, "test/p_micro": 0.855868544600939, "test/r_macro": 0.6606656363820599, "test/r_micro": 0.855868544600939}, "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": 0.6890574214517876, "test/f1_macro": 0.6776463157716582, "test/f1_micro": 0.6890574214517876, "test/p_macro": 0.6879578603963917, "test/p_micro": 0.6890574214517876, "test/r_macro": 0.6716342581634464, "test/r_micro": 0.6890574214517876}, "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": 0.960283786603603, "test/f1_macro": 0.8788008952006335, "test/f1_micro": 0.960283786603603, "test/p_macro": 0.9021078679303638, "test/p_micro": 0.960283786603603, "test/r_macro": 0.8590979187227483, "test/r_micro": 0.960283786603603}, "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": 0.9103729238483234, "test/f1_macro": 0.9087639459806999, "test/f1_micro": 0.9103729238483234, "test/p_macro": 0.9080934147603116, "test/p_micro": 0.9103729238483234, "test/r_macro": 0.9094813347276341, "test/r_micro": 0.9103729238483234}}

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "roberta-large",
+  "_name_or_path": "relbert-roberta-large-nce-d-0",
   "architectures": [
     "RobertaModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
+  "classifier_dropout": null,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
@@ -20,11 +20,11 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "relbert_config": {
-    "aggregation_mode": "average",
-    "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>",
-    "template_mode": "manual"
+    "aggregation_mode": "average_no_mask",
+    "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>"
   },
-  "transformers_version": "4.6.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

finetuning_config.json

@@ -0,0 +1,23 @@
+{
+  "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>",
+  "model": "roberta-large",
+  "max_length": 64,
+  "epoch": 10,
+  "batch": 32,
+  "random_seed": 0,
+  "lr": 5e-06,
+  "lr_warmup": 10,
+  "aggregation_mode": "average_no_mask",
+  "data": "relbert/semeval2012_relational_similarity",
+  "exclude_relation": null,
+  "split": "train",
+  "split_valid": "validation",
+  "loss_function": "nce",
+  "classification_loss": false,
+  "loss_function_config": {
+    "temperature": 0.05,
+    "gradient_accumulation": 1,
+    "num_negative": 400,
+    "num_positive": 10
+  }
+}

loss.json

@@ -0,0 +1 @@
+{"loss": 142.95112896549483}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe324fc457c22a64a75a79aa71b8a559ef77deb2afa0bd10c37ffad4791ac2f
-size 1421595889
+oid sha256:01c29cec100f4c5df9b4f783fd780f19366cadea2b7858e9a7e08f34faa678d0
+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_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>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large"}
+{
+  "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": "relbert-roberta-large-nce-d-0",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}