asahi417 commited on
Commit
3b65c9f
1 Parent(s): a7ae740

model update

Browse files
analogy.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"distance_function": "cosine_similarity", "sat/test": 0.7567567567567568, "sat/valid": 0.7062314540059347, "u2/test": 0.625, "u2/valid": 0.6754385964912281, "u4/test": 0.5833333333333334, "u4/valid": 0.6921296296296297, "google/test": 0.96, "google/valid": 0.936, "bats/test": 0.7989949748743719, "bats/valid": 0.782657031684269, "sat_full": 0.7112299465240641}
config.json CHANGED
@@ -1,11 +1,10 @@
1
  {
2
- "_name_or_path": "relbert_output/models/a.nce_logout.average_no_mask.roberta-large.0.000005.8.0.05.640/best_model",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
- "classifier_dropout": null,
9
  "eos_token_id": 2,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
@@ -25,8 +24,7 @@
25
  "template": "Today, I finally discovered the relation between <subj> and <obj> : <subj> is the <mask> of <obj>",
26
  "template_mode": "manual"
27
  },
28
- "torch_dtype": "float32",
29
- "transformers_version": "4.20.1",
30
  "type_vocab_size": 1,
31
  "use_cache": true,
32
  "vocab_size": 50265
 
1
  {
2
+ "_name_or_path": "roberta-large",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
 
8
  "eos_token_id": 2,
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
 
24
  "template": "Today, I finally discovered the relation between <subj> and <obj> : <subj> is the <mask> of <obj>",
25
  "template_mode": "manual"
26
  },
27
+ "transformers_version": "4.6.1",
 
28
  "type_vocab_size": 1,
29
  "use_cache": true,
30
  "vocab_size": 50265
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3767dd247b9d602d98242c424ba55abf355e98498676c6915592bf4a2cf9d0bc
3
- size 1421566897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d9ac2f55794ca8e59c4315f97405e45db2663c26b8baace1d5d859157ec5fba
3
+ size 1421595889
special_tokens_map.json CHANGED
@@ -1,15 +1 @@
1
- {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
- }
 
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.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,16 +1 @@
1
- {
2
- "add_prefix_space": false,
3
- "bos_token": "<s>",
4
- "cls_token": "<s>",
5
- "eos_token": "</s>",
6
- "errors": "replace",
7
- "mask_token": "<mask>",
8
- "model_max_length": 512,
9
- "name_or_path": "relbert_output/models/a.nce_logout.average_no_mask.roberta-large.0.000005.8.0.05.640/best_model",
10
- "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
- "special_tokens_map_file": null,
13
- "tokenizer_class": "RobertaTokenizer",
14
- "trim_offsets": true,
15
- "unk_token": "<unk>"
16
- }
 
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 ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "roberta-large", "max_length": 64, "mode": "average_no_mask", "data": "relbert/semeval2012_relational_similarity", "template_mode": "manual", "template": "Today, I finally discovered the relation between <subj> and <obj> : <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 ADDED
@@ -0,0 +1 @@
 
 
1
+ {"validation_loss": 4.856707855556788, "validation_data": "relbert/semeval2012_relational_similarity", "validation_data/exclude_relation": null}