model update

analogy.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "sat/test": 0.6216216216216216, "sat/valid": 0.6083086053412463, "u2/test": 0.6666666666666666, "u2/valid": 0.5833333333333334, "u4/test": 0.6041666666666666, "u4/valid": 0.5995370370370371, "google/test": 0.94, "google/valid": 0.93, "bats/test": 0.7688442211055276, "bats/valid": 0.7854363535297387, "sat_full": 0.6096256684491979}

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "relbert_output/models/b.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": "Today, I finally discovered the relation between <subj> and <obj> : <obj>  is <subj>'s <mask>",
     "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:cd92ed3d73b15038c692f81646e2a7b262dd0ac28c30da01c8efacdd987ffd6f
-size 1421566897
+oid sha256:975f3c7f3b111265d6b82e88c3610f0e11e32eda68565db79f1ffa5ca3f6a316
+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/b.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": "Today, I finally discovered the relation between <subj> and <obj> : <obj>  is <subj>'s <mask>", "loss_function": "nce_logout", "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 23, "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": 5.0396512157461615, "validation_data": "relbert/semeval2012_relational_similarity", "validation_data/exclude_relation": null}