update

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "relbert_config": {
+    "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",
+    "mode": "average_no_mask"
+  },
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21396e4b870bb50cb843a295a8454a7060248fcf9a8e0a179b7d7cf109d41b9
+size 1421600584

special_tokens_map.json

@@ -0,0 +1 @@
+{"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}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"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"}

trainer_config.json

@@ -0,0 +1 @@
+{"model": "roberta-large", "max_length": 64, "mode": "average_no_mask", "data": "semeval2012", "n_sample": 10, "custom_template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>", "template": null, "softmax_loss": true, "in_batch_negative": true, "parent_contrast": true, "mse_margin": 1, "epoch": 1, "lr_warmup": 10, "batch": 64, "lr": 2e-05, "lr_decay": false, "weight_decay": 0, "optimizer": "adam", "momentum": 0.9, "fp16": false, "random_seed": 0}