model update

analogy.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "sat/test": 0.7297297297297297, "sat/valid": 0.7151335311572701, "u2/test": 0.5416666666666666, "u2/valid": 0.7192982456140351, "u4/test": 0.625, "u4/valid": 0.6921296296296297, "google/test": 1.0, "google/valid": 0.964, "bats/test": 0.8241206030150754, "bats/valid": 0.8126737076153419, "sat_full": 0.7165775401069518}

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "relbert_output/models/d.nce_logout.average.roberta-large.0.000005.8.0.05.640/best_model",
+  "_name_or_path": "roberta-large",
   "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",
@@ -25,8 +24,7 @@
     "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"
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.20.1",
+  "transformers_version": "4.6.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e4b567259d9fdaa8b8a2f01bacf34b837eae0b7edcd1a7ba619d883492e457
-size 1421566897
+oid sha256:dfe324fc457c22a64a75a79aa71b8a559ef77deb2afa0bd10c37ffad4791ac2f
+size 1421595889

special_tokens_map.json

@@ -1,15 +1 @@
-{
-  "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>"
-}
+{"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

@@ -1,16 +1 @@
-{
-  "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_output/models/d.nce_logout.average.roberta-large.0.000005.8.0.05.640/best_model",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
-}
+{"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", "data": "relbert/semeval2012_relational_similarity", "template_mode": "manual", "template": "I wasn\u2019t 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, "random_seed": 0, "exclude_relation": null, "n_sample": 640, "gradient_accumulation": 8}

validation_loss.json

@@ -0,0 +1 @@
+{"validation_loss": 4.891365619187944, "validation_data": "relbert/semeval2012_relational_similarity", "validation_data/exclude_relation": null}