first commit
Browse files- config.json +26 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +2465 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "voidism/diffcse-roberta-base-sts",
|
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",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"transformers_version": "4.2.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 50265
|
26 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b792aba0b664d672181d12edb092a4e53501e5197f331ff3c97ceed4fed45320
|
3 |
+
size 1487809454
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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>", "special_tokens_map_file": null, "name_or_path": "./roberta-base"}
|
trainer_state.json
ADDED
@@ -0,0 +1,2465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8442339359569462,
|
3 |
+
"best_model_checkpoint": "result/simcse-celectra-amlp-dmlp-2ep-bs64-lr1e-5-mask0.20-elew0.005-roberta-base",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 31252,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"electra_acc": 0.1088,
|
12 |
+
"electra_fix_acc": 0.0079,
|
13 |
+
"electra_rep_acc": 0.9968,
|
14 |
+
"epoch": 0.0,
|
15 |
+
"learning_rate": 9.99968002047869e-06,
|
16 |
+
"loss": 8.4419,
|
17 |
+
"neg_sim": 0.2061,
|
18 |
+
"pos_sim": 0.3449,
|
19 |
+
"step": 1
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 0.01,
|
23 |
+
"eval_avg_sts": 0.755574714462574,
|
24 |
+
"eval_sickr_spearman": 0.7098302262826256,
|
25 |
+
"eval_stsb_spearman": 0.8013192026425223,
|
26 |
+
"step": 125
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.02,
|
30 |
+
"eval_avg_sts": 0.761612717263195,
|
31 |
+
"eval_sickr_spearman": 0.7112582869905835,
|
32 |
+
"eval_stsb_spearman": 0.8119671475358067,
|
33 |
+
"step": 250
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.02,
|
37 |
+
"eval_avg_sts": 0.766754789307388,
|
38 |
+
"eval_sickr_spearman": 0.7152875680591253,
|
39 |
+
"eval_stsb_spearman": 0.8182220105556509,
|
40 |
+
"step": 375
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"electra_acc": 0.8686,
|
44 |
+
"electra_fix_acc": 0.9713,
|
45 |
+
"electra_rep_acc": 0.0311,
|
46 |
+
"epoch": 0.03,
|
47 |
+
"learning_rate": 9.840010239344683e-06,
|
48 |
+
"loss": 0.1729,
|
49 |
+
"neg_sim": -0.0093,
|
50 |
+
"pos_sim": 0.695,
|
51 |
+
"step": 500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"eval_avg_sts": 0.7675239503020774,
|
56 |
+
"eval_sickr_spearman": 0.7166760511394983,
|
57 |
+
"eval_stsb_spearman": 0.8183718494646566,
|
58 |
+
"step": 500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04,
|
62 |
+
"eval_avg_sts": 0.7749845711206813,
|
63 |
+
"eval_sickr_spearman": 0.724027931681123,
|
64 |
+
"eval_stsb_spearman": 0.8259412105602397,
|
65 |
+
"step": 625
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.05,
|
69 |
+
"eval_avg_sts": 0.7751202672393465,
|
70 |
+
"eval_sickr_spearman": 0.7197742012755609,
|
71 |
+
"eval_stsb_spearman": 0.8304663332031321,
|
72 |
+
"step": 750
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.06,
|
76 |
+
"eval_avg_sts": 0.7760175671946854,
|
77 |
+
"eval_sickr_spearman": 0.7239823981969596,
|
78 |
+
"eval_stsb_spearman": 0.8280527361924113,
|
79 |
+
"step": 875
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"electra_acc": 0.8964,
|
83 |
+
"electra_fix_acc": 0.9953,
|
84 |
+
"electra_rep_acc": 0.0862,
|
85 |
+
"epoch": 0.06,
|
86 |
+
"learning_rate": 9.680020478689364e-06,
|
87 |
+
"loss": 0.0014,
|
88 |
+
"neg_sim": -0.0136,
|
89 |
+
"pos_sim": 0.736,
|
90 |
+
"step": 1000
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.06,
|
94 |
+
"eval_avg_sts": 0.7775564387382596,
|
95 |
+
"eval_sickr_spearman": 0.7228041472475814,
|
96 |
+
"eval_stsb_spearman": 0.832308730228938,
|
97 |
+
"step": 1000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.07,
|
101 |
+
"eval_avg_sts": 0.7784780411860817,
|
102 |
+
"eval_sickr_spearman": 0.7230463680921337,
|
103 |
+
"eval_stsb_spearman": 0.8339097142800296,
|
104 |
+
"step": 1125
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.08,
|
108 |
+
"eval_avg_sts": 0.7802639531360682,
|
109 |
+
"eval_sickr_spearman": 0.726064546444302,
|
110 |
+
"eval_stsb_spearman": 0.8344633598278346,
|
111 |
+
"step": 1250
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.09,
|
115 |
+
"eval_avg_sts": 0.778730071271978,
|
116 |
+
"eval_sickr_spearman": 0.7238748085297384,
|
117 |
+
"eval_stsb_spearman": 0.8335853340142177,
|
118 |
+
"step": 1375
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"electra_acc": 0.8989,
|
122 |
+
"electra_fix_acc": 0.9938,
|
123 |
+
"electra_rep_acc": 0.1172,
|
124 |
+
"epoch": 0.1,
|
125 |
+
"learning_rate": 9.520030718034047e-06,
|
126 |
+
"loss": 0.0013,
|
127 |
+
"neg_sim": -0.0137,
|
128 |
+
"pos_sim": 0.7472,
|
129 |
+
"step": 1500
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.1,
|
133 |
+
"eval_avg_sts": 0.7716526802556551,
|
134 |
+
"eval_sickr_spearman": 0.7141475498664919,
|
135 |
+
"eval_stsb_spearman": 0.8291578106448184,
|
136 |
+
"step": 1500
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.1,
|
140 |
+
"eval_avg_sts": 0.7758744711124749,
|
141 |
+
"eval_sickr_spearman": 0.721181992858712,
|
142 |
+
"eval_stsb_spearman": 0.8305669493662378,
|
143 |
+
"step": 1625
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.11,
|
147 |
+
"eval_avg_sts": 0.7763031700578917,
|
148 |
+
"eval_sickr_spearman": 0.7214235412678442,
|
149 |
+
"eval_stsb_spearman": 0.8311827988479393,
|
150 |
+
"step": 1750
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.12,
|
154 |
+
"eval_avg_sts": 0.7806434242533656,
|
155 |
+
"eval_sickr_spearman": 0.7289663454376855,
|
156 |
+
"eval_stsb_spearman": 0.8323205030690458,
|
157 |
+
"step": 1875
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"electra_acc": 0.8998,
|
161 |
+
"electra_fix_acc": 0.9931,
|
162 |
+
"electra_rep_acc": 0.1339,
|
163 |
+
"epoch": 0.13,
|
164 |
+
"learning_rate": 9.36004095737873e-06,
|
165 |
+
"loss": 0.0012,
|
166 |
+
"neg_sim": -0.0138,
|
167 |
+
"pos_sim": 0.7538,
|
168 |
+
"step": 2000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.13,
|
172 |
+
"eval_avg_sts": 0.7795467000474285,
|
173 |
+
"eval_sickr_spearman": 0.722814521965492,
|
174 |
+
"eval_stsb_spearman": 0.836278878129365,
|
175 |
+
"step": 2000
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 0.14,
|
179 |
+
"eval_avg_sts": 0.7831655326956792,
|
180 |
+
"eval_sickr_spearman": 0.7220971294344124,
|
181 |
+
"eval_stsb_spearman": 0.8442339359569462,
|
182 |
+
"step": 2125
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.14,
|
186 |
+
"eval_avg_sts": 0.7784529836143297,
|
187 |
+
"eval_sickr_spearman": 0.7178746672758864,
|
188 |
+
"eval_stsb_spearman": 0.8390312999527729,
|
189 |
+
"step": 2250
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.15,
|
193 |
+
"eval_avg_sts": 0.7838110056478796,
|
194 |
+
"eval_sickr_spearman": 0.7265441850232628,
|
195 |
+
"eval_stsb_spearman": 0.8410778262724965,
|
196 |
+
"step": 2375
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"electra_acc": 0.9008,
|
200 |
+
"electra_fix_acc": 0.9925,
|
201 |
+
"electra_rep_acc": 0.1492,
|
202 |
+
"epoch": 0.16,
|
203 |
+
"learning_rate": 9.20005119672341e-06,
|
204 |
+
"loss": 0.0012,
|
205 |
+
"neg_sim": -0.0138,
|
206 |
+
"pos_sim": 0.7534,
|
207 |
+
"step": 2500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.16,
|
211 |
+
"eval_avg_sts": 0.781754791702129,
|
212 |
+
"eval_sickr_spearman": 0.723123794227652,
|
213 |
+
"eval_stsb_spearman": 0.8403857891766059,
|
214 |
+
"step": 2500
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.17,
|
218 |
+
"eval_avg_sts": 0.7798490649002168,
|
219 |
+
"eval_sickr_spearman": 0.7198115694724797,
|
220 |
+
"eval_stsb_spearman": 0.8398865603279537,
|
221 |
+
"step": 2625
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.18,
|
225 |
+
"eval_avg_sts": 0.7787504502510374,
|
226 |
+
"eval_sickr_spearman": 0.7188935990617945,
|
227 |
+
"eval_stsb_spearman": 0.8386073014402803,
|
228 |
+
"step": 2750
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.18,
|
232 |
+
"eval_avg_sts": 0.7702513371927302,
|
233 |
+
"eval_sickr_spearman": 0.7122062768396675,
|
234 |
+
"eval_stsb_spearman": 0.828296397545793,
|
235 |
+
"step": 2875
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"electra_acc": 0.9012,
|
239 |
+
"electra_fix_acc": 0.9922,
|
240 |
+
"electra_rep_acc": 0.157,
|
241 |
+
"epoch": 0.19,
|
242 |
+
"learning_rate": 9.040061436068092e-06,
|
243 |
+
"loss": 0.0012,
|
244 |
+
"neg_sim": -0.0139,
|
245 |
+
"pos_sim": 0.7662,
|
246 |
+
"step": 3000
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 0.19,
|
250 |
+
"eval_avg_sts": 0.77796510106683,
|
251 |
+
"eval_sickr_spearman": 0.7215734943665341,
|
252 |
+
"eval_stsb_spearman": 0.834356707767126,
|
253 |
+
"step": 3000
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 0.2,
|
257 |
+
"eval_avg_sts": 0.7773533173320899,
|
258 |
+
"eval_sickr_spearman": 0.7216049067068746,
|
259 |
+
"eval_stsb_spearman": 0.8331017279573052,
|
260 |
+
"step": 3125
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.21,
|
264 |
+
"eval_avg_sts": 0.7727609962405579,
|
265 |
+
"eval_sickr_spearman": 0.7192614692677092,
|
266 |
+
"eval_stsb_spearman": 0.8262605232134068,
|
267 |
+
"step": 3250
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.22,
|
271 |
+
"eval_avg_sts": 0.7705397769228735,
|
272 |
+
"eval_sickr_spearman": 0.7183345170410549,
|
273 |
+
"eval_stsb_spearman": 0.8227450368046919,
|
274 |
+
"step": 3375
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"electra_acc": 0.902,
|
278 |
+
"electra_fix_acc": 0.9917,
|
279 |
+
"electra_rep_acc": 0.1668,
|
280 |
+
"epoch": 0.22,
|
281 |
+
"learning_rate": 8.880071675412775e-06,
|
282 |
+
"loss": 0.0012,
|
283 |
+
"neg_sim": -0.0138,
|
284 |
+
"pos_sim": 0.762,
|
285 |
+
"step": 3500
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.22,
|
289 |
+
"eval_avg_sts": 0.7669127684681659,
|
290 |
+
"eval_sickr_spearman": 0.7153820452356542,
|
291 |
+
"eval_stsb_spearman": 0.8184434917006776,
|
292 |
+
"step": 3500
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.23,
|
296 |
+
"eval_avg_sts": 0.762067078104866,
|
297 |
+
"eval_sickr_spearman": 0.708602167081056,
|
298 |
+
"eval_stsb_spearman": 0.815531989128676,
|
299 |
+
"step": 3625
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.24,
|
303 |
+
"eval_avg_sts": 0.7603436095667805,
|
304 |
+
"eval_sickr_spearman": 0.7039441757894171,
|
305 |
+
"eval_stsb_spearman": 0.8167430433441438,
|
306 |
+
"step": 3750
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.25,
|
310 |
+
"eval_avg_sts": 0.7572330050419072,
|
311 |
+
"eval_sickr_spearman": 0.7035958853781614,
|
312 |
+
"eval_stsb_spearman": 0.810870124705653,
|
313 |
+
"step": 3875
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"electra_acc": 0.903,
|
317 |
+
"electra_fix_acc": 0.9917,
|
318 |
+
"electra_rep_acc": 0.1735,
|
319 |
+
"epoch": 0.26,
|
320 |
+
"learning_rate": 8.720081914757458e-06,
|
321 |
+
"loss": 0.0013,
|
322 |
+
"neg_sim": -0.0139,
|
323 |
+
"pos_sim": 0.769,
|
324 |
+
"step": 4000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.26,
|
328 |
+
"eval_avg_sts": 0.7565075332583117,
|
329 |
+
"eval_sickr_spearman": 0.7049569907307146,
|
330 |
+
"eval_stsb_spearman": 0.8080580757859087,
|
331 |
+
"step": 4000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.26,
|
335 |
+
"eval_avg_sts": 0.7571155448037524,
|
336 |
+
"eval_sickr_spearman": 0.7046521373298869,
|
337 |
+
"eval_stsb_spearman": 0.809578952277618,
|
338 |
+
"step": 4125
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.27,
|
342 |
+
"eval_avg_sts": 0.7558024272832136,
|
343 |
+
"eval_sickr_spearman": 0.7044353249379953,
|
344 |
+
"eval_stsb_spearman": 0.8071695296284319,
|
345 |
+
"step": 4250
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.28,
|
349 |
+
"eval_avg_sts": 0.7590707229344114,
|
350 |
+
"eval_sickr_spearman": 0.7043194258902251,
|
351 |
+
"eval_stsb_spearman": 0.8138220199785977,
|
352 |
+
"step": 4375
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"electra_acc": 0.9026,
|
356 |
+
"electra_fix_acc": 0.9912,
|
357 |
+
"electra_rep_acc": 0.1795,
|
358 |
+
"epoch": 0.29,
|
359 |
+
"learning_rate": 8.560092154102138e-06,
|
360 |
+
"loss": 0.0012,
|
361 |
+
"neg_sim": -0.0139,
|
362 |
+
"pos_sim": 0.7711,
|
363 |
+
"step": 4500
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.29,
|
367 |
+
"eval_avg_sts": 0.7618055470788606,
|
368 |
+
"eval_sickr_spearman": 0.7090844954016975,
|
369 |
+
"eval_stsb_spearman": 0.8145265987560237,
|
370 |
+
"step": 4500
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.3,
|
374 |
+
"eval_avg_sts": 0.7642277977124863,
|
375 |
+
"eval_sickr_spearman": 0.7120559394921663,
|
376 |
+
"eval_stsb_spearman": 0.8163996559328064,
|
377 |
+
"step": 4625
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.3,
|
381 |
+
"eval_avg_sts": 0.7631334021943239,
|
382 |
+
"eval_sickr_spearman": 0.7097783526930724,
|
383 |
+
"eval_stsb_spearman": 0.8164884516955754,
|
384 |
+
"step": 4750
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.31,
|
388 |
+
"eval_avg_sts": 0.7663792588185014,
|
389 |
+
"eval_sickr_spearman": 0.7141827086327445,
|
390 |
+
"eval_stsb_spearman": 0.8185758090042584,
|
391 |
+
"step": 4875
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"electra_acc": 0.9031,
|
395 |
+
"electra_fix_acc": 0.9911,
|
396 |
+
"electra_rep_acc": 0.1837,
|
397 |
+
"epoch": 0.32,
|
398 |
+
"learning_rate": 8.400102393446819e-06,
|
399 |
+
"loss": 0.0011,
|
400 |
+
"neg_sim": -0.014,
|
401 |
+
"pos_sim": 0.7781,
|
402 |
+
"step": 5000
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.32,
|
406 |
+
"eval_avg_sts": 0.7675828244876146,
|
407 |
+
"eval_sickr_spearman": 0.7151267119004091,
|
408 |
+
"eval_stsb_spearman": 0.8200389370748202,
|
409 |
+
"step": 5000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.33,
|
413 |
+
"eval_avg_sts": 0.7664182051626903,
|
414 |
+
"eval_sickr_spearman": 0.7138797284448728,
|
415 |
+
"eval_stsb_spearman": 0.8189566818805079,
|
416 |
+
"step": 5125
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.34,
|
420 |
+
"eval_avg_sts": 0.763298983477001,
|
421 |
+
"eval_sickr_spearman": 0.7031210499093442,
|
422 |
+
"eval_stsb_spearman": 0.8234769170446578,
|
423 |
+
"step": 5250
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.34,
|
427 |
+
"eval_avg_sts": 0.7609537736402838,
|
428 |
+
"eval_sickr_spearman": 0.7014618323453161,
|
429 |
+
"eval_stsb_spearman": 0.8204457149352516,
|
430 |
+
"step": 5375
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"electra_acc": 0.9041,
|
434 |
+
"electra_fix_acc": 0.9909,
|
435 |
+
"electra_rep_acc": 0.1929,
|
436 |
+
"epoch": 0.35,
|
437 |
+
"learning_rate": 8.240112632791502e-06,
|
438 |
+
"loss": 0.0013,
|
439 |
+
"neg_sim": -0.0139,
|
440 |
+
"pos_sim": 0.7703,
|
441 |
+
"step": 5500
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.35,
|
445 |
+
"eval_avg_sts": 0.7649139683546902,
|
446 |
+
"eval_sickr_spearman": 0.7016405392386158,
|
447 |
+
"eval_stsb_spearman": 0.8281873974707646,
|
448 |
+
"step": 5500
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 0.36,
|
452 |
+
"eval_avg_sts": 0.7660619062755463,
|
453 |
+
"eval_sickr_spearman": 0.7030690322264868,
|
454 |
+
"eval_stsb_spearman": 0.8290547803246057,
|
455 |
+
"step": 5625
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.37,
|
459 |
+
"eval_avg_sts": 0.7667448016301607,
|
460 |
+
"eval_sickr_spearman": 0.7080724800943964,
|
461 |
+
"eval_stsb_spearman": 0.825417123165925,
|
462 |
+
"step": 5750
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 0.38,
|
466 |
+
"eval_avg_sts": 0.7668525663367054,
|
467 |
+
"eval_sickr_spearman": 0.7080771871423374,
|
468 |
+
"eval_stsb_spearman": 0.8256279455310735,
|
469 |
+
"step": 5875
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"electra_acc": 0.9044,
|
473 |
+
"electra_fix_acc": 0.991,
|
474 |
+
"electra_rep_acc": 0.1933,
|
475 |
+
"epoch": 0.38,
|
476 |
+
"learning_rate": 8.080122872136184e-06,
|
477 |
+
"loss": 0.0011,
|
478 |
+
"neg_sim": -0.014,
|
479 |
+
"pos_sim": 0.7798,
|
480 |
+
"step": 6000
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.38,
|
484 |
+
"eval_avg_sts": 0.7666156811168598,
|
485 |
+
"eval_sickr_spearman": 0.709114370746792,
|
486 |
+
"eval_stsb_spearman": 0.8241169914869277,
|
487 |
+
"step": 6000
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.39,
|
491 |
+
"eval_avg_sts": 0.7644923521403739,
|
492 |
+
"eval_sickr_spearman": 0.7072277090823029,
|
493 |
+
"eval_stsb_spearman": 0.821756995198445,
|
494 |
+
"step": 6125
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.4,
|
498 |
+
"eval_avg_sts": 0.7661750461200847,
|
499 |
+
"eval_sickr_spearman": 0.7058679005694886,
|
500 |
+
"eval_stsb_spearman": 0.8264821916706808,
|
501 |
+
"step": 6250
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.41,
|
505 |
+
"eval_avg_sts": 0.7660352662732546,
|
506 |
+
"eval_sickr_spearman": 0.7060020514358052,
|
507 |
+
"eval_stsb_spearman": 0.8260684811107039,
|
508 |
+
"step": 6375
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"electra_acc": 0.9042,
|
512 |
+
"electra_fix_acc": 0.9906,
|
513 |
+
"electra_rep_acc": 0.2009,
|
514 |
+
"epoch": 0.42,
|
515 |
+
"learning_rate": 7.920133111480865e-06,
|
516 |
+
"loss": 0.0011,
|
517 |
+
"neg_sim": -0.014,
|
518 |
+
"pos_sim": 0.7785,
|
519 |
+
"step": 6500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.42,
|
523 |
+
"eval_avg_sts": 0.7705073293876892,
|
524 |
+
"eval_sickr_spearman": 0.7120254877738545,
|
525 |
+
"eval_stsb_spearman": 0.8289891710015237,
|
526 |
+
"step": 6500
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.42,
|
530 |
+
"eval_avg_sts": 0.7701345372028097,
|
531 |
+
"eval_sickr_spearman": 0.7109871514229654,
|
532 |
+
"eval_stsb_spearman": 0.829281922982654,
|
533 |
+
"step": 6625
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.43,
|
537 |
+
"eval_avg_sts": 0.7673565342593036,
|
538 |
+
"eval_sickr_spearman": 0.7094820007971993,
|
539 |
+
"eval_stsb_spearman": 0.8252310677214081,
|
540 |
+
"step": 6750
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.44,
|
544 |
+
"eval_avg_sts": 0.7663843153446501,
|
545 |
+
"eval_sickr_spearman": 0.7069766985461874,
|
546 |
+
"eval_stsb_spearman": 0.8257919321431128,
|
547 |
+
"step": 6875
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"electra_acc": 0.9052,
|
551 |
+
"electra_fix_acc": 0.9907,
|
552 |
+
"electra_rep_acc": 0.2032,
|
553 |
+
"epoch": 0.45,
|
554 |
+
"learning_rate": 7.760143350825547e-06,
|
555 |
+
"loss": 0.0011,
|
556 |
+
"neg_sim": -0.0141,
|
557 |
+
"pos_sim": 0.7899,
|
558 |
+
"step": 7000
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.45,
|
562 |
+
"eval_avg_sts": 0.7671374698909221,
|
563 |
+
"eval_sickr_spearman": 0.7035898814904816,
|
564 |
+
"eval_stsb_spearman": 0.8306850582913625,
|
565 |
+
"step": 7000
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.46,
|
569 |
+
"eval_avg_sts": 0.7657223525531744,
|
570 |
+
"eval_sickr_spearman": 0.7024468853695589,
|
571 |
+
"eval_stsb_spearman": 0.82899781973679,
|
572 |
+
"step": 7125
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.46,
|
576 |
+
"eval_avg_sts": 0.7644676880553354,
|
577 |
+
"eval_sickr_spearman": 0.707080829974105,
|
578 |
+
"eval_stsb_spearman": 0.8218545461365657,
|
579 |
+
"step": 7250
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.47,
|
583 |
+
"eval_avg_sts": 0.7659127144064692,
|
584 |
+
"eval_sickr_spearman": 0.7085741649489175,
|
585 |
+
"eval_stsb_spearman": 0.8232512638640211,
|
586 |
+
"step": 7375
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"electra_acc": 0.9051,
|
590 |
+
"electra_fix_acc": 0.9904,
|
591 |
+
"electra_rep_acc": 0.2082,
|
592 |
+
"epoch": 0.48,
|
593 |
+
"learning_rate": 7.600153590170229e-06,
|
594 |
+
"loss": 0.0011,
|
595 |
+
"neg_sim": -0.0141,
|
596 |
+
"pos_sim": 0.7901,
|
597 |
+
"step": 7500
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.48,
|
601 |
+
"eval_avg_sts": 0.7608800819642288,
|
602 |
+
"eval_sickr_spearman": 0.7044842686303607,
|
603 |
+
"eval_stsb_spearman": 0.817275895298097,
|
604 |
+
"step": 7500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.49,
|
608 |
+
"eval_avg_sts": 0.7596082078600037,
|
609 |
+
"eval_sickr_spearman": 0.714175648060833,
|
610 |
+
"eval_stsb_spearman": 0.8050407676591743,
|
611 |
+
"step": 7625
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.5,
|
615 |
+
"eval_avg_sts": 0.7601954211728121,
|
616 |
+
"eval_sickr_spearman": 0.713427179407123,
|
617 |
+
"eval_stsb_spearman": 0.8069636629385014,
|
618 |
+
"step": 7750
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.5,
|
622 |
+
"eval_avg_sts": 0.7595124397232403,
|
623 |
+
"eval_sickr_spearman": 0.7107700028133637,
|
624 |
+
"eval_stsb_spearman": 0.808254876633117,
|
625 |
+
"step": 7875
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"electra_acc": 0.9053,
|
629 |
+
"electra_fix_acc": 0.9904,
|
630 |
+
"electra_rep_acc": 0.2114,
|
631 |
+
"epoch": 0.51,
|
632 |
+
"learning_rate": 7.440163829514912e-06,
|
633 |
+
"loss": 0.0011,
|
634 |
+
"neg_sim": -0.014,
|
635 |
+
"pos_sim": 0.784,
|
636 |
+
"step": 8000
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 0.51,
|
640 |
+
"eval_avg_sts": 0.7600307296458793,
|
641 |
+
"eval_sickr_spearman": 0.7110970465830557,
|
642 |
+
"eval_stsb_spearman": 0.8089644127087027,
|
643 |
+
"step": 8000
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"epoch": 0.52,
|
647 |
+
"eval_avg_sts": 0.7591940023385597,
|
648 |
+
"eval_sickr_spearman": 0.709230365856765,
|
649 |
+
"eval_stsb_spearman": 0.8091576388203543,
|
650 |
+
"step": 8125
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.53,
|
654 |
+
"eval_avg_sts": 0.7591314547260735,
|
655 |
+
"eval_sickr_spearman": 0.7092257548710269,
|
656 |
+
"eval_stsb_spearman": 0.8090371545811201,
|
657 |
+
"step": 8250
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.54,
|
661 |
+
"eval_avg_sts": 0.7574056509175848,
|
662 |
+
"eval_sickr_spearman": 0.7065820269856703,
|
663 |
+
"eval_stsb_spearman": 0.8082292748494992,
|
664 |
+
"step": 8375
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"electra_acc": 0.9051,
|
668 |
+
"electra_fix_acc": 0.9903,
|
669 |
+
"electra_rep_acc": 0.2115,
|
670 |
+
"epoch": 0.54,
|
671 |
+
"learning_rate": 7.280174068859593e-06,
|
672 |
+
"loss": 0.001,
|
673 |
+
"neg_sim": -0.0141,
|
674 |
+
"pos_sim": 0.7991,
|
675 |
+
"step": 8500
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.54,
|
679 |
+
"eval_avg_sts": 0.7579907562127961,
|
680 |
+
"eval_sickr_spearman": 0.7058790918161235,
|
681 |
+
"eval_stsb_spearman": 0.8101024206094687,
|
682 |
+
"step": 8500
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.55,
|
686 |
+
"eval_avg_sts": 0.7588600922765898,
|
687 |
+
"eval_sickr_spearman": 0.7066013835195499,
|
688 |
+
"eval_stsb_spearman": 0.8111188010336298,
|
689 |
+
"step": 8625
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.56,
|
693 |
+
"eval_avg_sts": 0.7579781185788305,
|
694 |
+
"eval_sickr_spearman": 0.7017153716946564,
|
695 |
+
"eval_stsb_spearman": 0.8142408654630046,
|
696 |
+
"step": 8750
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.57,
|
700 |
+
"eval_avg_sts": 0.7583650057103912,
|
701 |
+
"eval_sickr_spearman": 0.7015226228845852,
|
702 |
+
"eval_stsb_spearman": 0.8152073885361973,
|
703 |
+
"step": 8875
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"electra_acc": 0.9061,
|
707 |
+
"electra_fix_acc": 0.9906,
|
708 |
+
"electra_rep_acc": 0.2147,
|
709 |
+
"epoch": 0.58,
|
710 |
+
"learning_rate": 7.120184308204276e-06,
|
711 |
+
"loss": 0.0011,
|
712 |
+
"neg_sim": -0.0142,
|
713 |
+
"pos_sim": 0.8009,
|
714 |
+
"step": 9000
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.58,
|
718 |
+
"eval_avg_sts": 0.7584798299886761,
|
719 |
+
"eval_sickr_spearman": 0.7013053301816793,
|
720 |
+
"eval_stsb_spearman": 0.815654329795673,
|
721 |
+
"step": 9000
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.58,
|
725 |
+
"eval_avg_sts": 0.7568426056984886,
|
726 |
+
"eval_sickr_spearman": 0.6953886669821268,
|
727 |
+
"eval_stsb_spearman": 0.8182965444148504,
|
728 |
+
"step": 9125
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.59,
|
732 |
+
"eval_avg_sts": 0.7582279310008209,
|
733 |
+
"eval_sickr_spearman": 0.6970180260362119,
|
734 |
+
"eval_stsb_spearman": 0.8194378359654299,
|
735 |
+
"step": 9250
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.6,
|
739 |
+
"eval_avg_sts": 0.7573982613352882,
|
740 |
+
"eval_sickr_spearman": 0.6927659286880986,
|
741 |
+
"eval_stsb_spearman": 0.8220305939824778,
|
742 |
+
"step": 9375
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"electra_acc": 0.9064,
|
746 |
+
"electra_fix_acc": 0.9904,
|
747 |
+
"electra_rep_acc": 0.2163,
|
748 |
+
"epoch": 0.61,
|
749 |
+
"learning_rate": 6.9601945475489575e-06,
|
750 |
+
"loss": 0.0011,
|
751 |
+
"neg_sim": -0.014,
|
752 |
+
"pos_sim": 0.7876,
|
753 |
+
"step": 9500
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.61,
|
757 |
+
"eval_avg_sts": 0.7553820601323997,
|
758 |
+
"eval_sickr_spearman": 0.690547148530363,
|
759 |
+
"eval_stsb_spearman": 0.8202169717344365,
|
760 |
+
"step": 9500
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.62,
|
764 |
+
"eval_avg_sts": 0.7567629669074094,
|
765 |
+
"eval_sickr_spearman": 0.6929571405029238,
|
766 |
+
"eval_stsb_spearman": 0.8205687933118949,
|
767 |
+
"step": 9625
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.62,
|
771 |
+
"eval_avg_sts": 0.7568625521954009,
|
772 |
+
"eval_sickr_spearman": 0.6927340360367437,
|
773 |
+
"eval_stsb_spearman": 0.8209910683540581,
|
774 |
+
"step": 9750
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.63,
|
778 |
+
"eval_avg_sts": 0.7524242981805003,
|
779 |
+
"eval_sickr_spearman": 0.6836492413863334,
|
780 |
+
"eval_stsb_spearman": 0.8211993549746672,
|
781 |
+
"step": 9875
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"electra_acc": 0.9058,
|
785 |
+
"electra_fix_acc": 0.9902,
|
786 |
+
"electra_rep_acc": 0.2192,
|
787 |
+
"epoch": 0.64,
|
788 |
+
"learning_rate": 6.800204786893639e-06,
|
789 |
+
"loss": 0.001,
|
790 |
+
"neg_sim": -0.0141,
|
791 |
+
"pos_sim": 0.7942,
|
792 |
+
"step": 10000
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.64,
|
796 |
+
"eval_avg_sts": 0.7508138636055113,
|
797 |
+
"eval_sickr_spearman": 0.6821391435571191,
|
798 |
+
"eval_stsb_spearman": 0.8194885836539034,
|
799 |
+
"step": 10000
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.65,
|
803 |
+
"eval_avg_sts": 0.7510417193281674,
|
804 |
+
"eval_sickr_spearman": 0.683803901532964,
|
805 |
+
"eval_stsb_spearman": 0.8182795371233709,
|
806 |
+
"step": 10125
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.66,
|
810 |
+
"eval_avg_sts": 0.7560510909697331,
|
811 |
+
"eval_sickr_spearman": 0.694022134115111,
|
812 |
+
"eval_stsb_spearman": 0.8180800478243552,
|
813 |
+
"step": 10250
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.66,
|
817 |
+
"eval_avg_sts": 0.7554822011048945,
|
818 |
+
"eval_sickr_spearman": 0.6934548868071269,
|
819 |
+
"eval_stsb_spearman": 0.8175095154026621,
|
820 |
+
"step": 10375
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"electra_acc": 0.9073,
|
824 |
+
"electra_fix_acc": 0.9904,
|
825 |
+
"electra_rep_acc": 0.2211,
|
826 |
+
"epoch": 0.67,
|
827 |
+
"learning_rate": 6.640215026238322e-06,
|
828 |
+
"loss": 0.0011,
|
829 |
+
"neg_sim": -0.0141,
|
830 |
+
"pos_sim": 0.7946,
|
831 |
+
"step": 10500
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.67,
|
835 |
+
"eval_avg_sts": 0.7614561025331773,
|
836 |
+
"eval_sickr_spearman": 0.7013578281755511,
|
837 |
+
"eval_stsb_spearman": 0.8215543768908035,
|
838 |
+
"step": 10500
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 0.68,
|
842 |
+
"eval_avg_sts": 0.7569156258584822,
|
843 |
+
"eval_sickr_spearman": 0.6959233972344373,
|
844 |
+
"eval_stsb_spearman": 0.817907854482527,
|
845 |
+
"step": 10625
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.69,
|
849 |
+
"eval_avg_sts": 0.7561592629720358,
|
850 |
+
"eval_sickr_spearman": 0.695029538436674,
|
851 |
+
"eval_stsb_spearman": 0.8172889875073976,
|
852 |
+
"step": 10750
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 0.7,
|
856 |
+
"eval_avg_sts": 0.7563428139477524,
|
857 |
+
"eval_sickr_spearman": 0.6957568734057513,
|
858 |
+
"eval_stsb_spearman": 0.8169287544897534,
|
859 |
+
"step": 10875
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"electra_acc": 0.9065,
|
863 |
+
"electra_fix_acc": 0.9902,
|
864 |
+
"electra_rep_acc": 0.2217,
|
865 |
+
"epoch": 0.7,
|
866 |
+
"learning_rate": 6.480225265583003e-06,
|
867 |
+
"loss": 0.001,
|
868 |
+
"neg_sim": -0.0142,
|
869 |
+
"pos_sim": 0.8004,
|
870 |
+
"step": 11000
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.7,
|
874 |
+
"eval_avg_sts": 0.7516024333799518,
|
875 |
+
"eval_sickr_spearman": 0.6886655615894285,
|
876 |
+
"eval_stsb_spearman": 0.8145393051704751,
|
877 |
+
"step": 11000
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.71,
|
881 |
+
"eval_avg_sts": 0.7513622883897111,
|
882 |
+
"eval_sickr_spearman": 0.6895086034818702,
|
883 |
+
"eval_stsb_spearman": 0.8132159732975519,
|
884 |
+
"step": 11125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.72,
|
888 |
+
"eval_avg_sts": 0.7524578381239166,
|
889 |
+
"eval_sickr_spearman": 0.6914134689338043,
|
890 |
+
"eval_stsb_spearman": 0.813502207314029,
|
891 |
+
"step": 11250
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.73,
|
895 |
+
"eval_avg_sts": 0.7529077801461861,
|
896 |
+
"eval_sickr_spearman": 0.7008521567396107,
|
897 |
+
"eval_stsb_spearman": 0.8049634035527615,
|
898 |
+
"step": 11375
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"electra_acc": 0.9069,
|
902 |
+
"electra_fix_acc": 0.9903,
|
903 |
+
"electra_rep_acc": 0.2207,
|
904 |
+
"epoch": 0.74,
|
905 |
+
"learning_rate": 6.320235504927685e-06,
|
906 |
+
"loss": 0.0011,
|
907 |
+
"neg_sim": -0.0141,
|
908 |
+
"pos_sim": 0.8003,
|
909 |
+
"step": 11500
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.74,
|
913 |
+
"eval_avg_sts": 0.7520009086329529,
|
914 |
+
"eval_sickr_spearman": 0.6998127156733884,
|
915 |
+
"eval_stsb_spearman": 0.8041891015925174,
|
916 |
+
"step": 11500
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.74,
|
920 |
+
"eval_avg_sts": 0.7528385713572732,
|
921 |
+
"eval_sickr_spearman": 0.6952667640466769,
|
922 |
+
"eval_stsb_spearman": 0.8104103786678696,
|
923 |
+
"step": 11625
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.75,
|
927 |
+
"eval_avg_sts": 0.7543110510513436,
|
928 |
+
"eval_sickr_spearman": 0.6966553431892527,
|
929 |
+
"eval_stsb_spearman": 0.8119667589134344,
|
930 |
+
"step": 11750
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.76,
|
934 |
+
"eval_avg_sts": 0.7483201703337362,
|
935 |
+
"eval_sickr_spearman": 0.6935844266877055,
|
936 |
+
"eval_stsb_spearman": 0.8030559139797669,
|
937 |
+
"step": 11875
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"electra_acc": 0.9071,
|
941 |
+
"electra_fix_acc": 0.99,
|
942 |
+
"electra_rep_acc": 0.2271,
|
943 |
+
"epoch": 0.77,
|
944 |
+
"learning_rate": 6.1602457442723675e-06,
|
945 |
+
"loss": 0.0011,
|
946 |
+
"neg_sim": -0.0141,
|
947 |
+
"pos_sim": 0.7871,
|
948 |
+
"step": 12000
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.77,
|
952 |
+
"eval_avg_sts": 0.751054540493113,
|
953 |
+
"eval_sickr_spearman": 0.692834276945445,
|
954 |
+
"eval_stsb_spearman": 0.809274804040781,
|
955 |
+
"step": 12000
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.78,
|
959 |
+
"eval_avg_sts": 0.7490596138849832,
|
960 |
+
"eval_sickr_spearman": 0.6888325657291288,
|
961 |
+
"eval_stsb_spearman": 0.8092866620408378,
|
962 |
+
"step": 12125
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.78,
|
966 |
+
"eval_avg_sts": 0.7507815525034611,
|
967 |
+
"eval_sickr_spearman": 0.6925058883049127,
|
968 |
+
"eval_stsb_spearman": 0.8090572167020096,
|
969 |
+
"step": 12250
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.79,
|
973 |
+
"eval_avg_sts": 0.7527821368803079,
|
974 |
+
"eval_sickr_spearman": 0.6942120971212987,
|
975 |
+
"eval_stsb_spearman": 0.8113521766393171,
|
976 |
+
"step": 12375
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"electra_acc": 0.9072,
|
980 |
+
"electra_fix_acc": 0.99,
|
981 |
+
"electra_rep_acc": 0.226,
|
982 |
+
"epoch": 0.8,
|
983 |
+
"learning_rate": 6.000255983617049e-06,
|
984 |
+
"loss": 0.0012,
|
985 |
+
"neg_sim": -0.014,
|
986 |
+
"pos_sim": 0.7847,
|
987 |
+
"step": 12500
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.8,
|
991 |
+
"eval_avg_sts": 0.7522991659637694,
|
992 |
+
"eval_sickr_spearman": 0.6944025884696023,
|
993 |
+
"eval_stsb_spearman": 0.8101957434579367,
|
994 |
+
"step": 12500
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.81,
|
998 |
+
"eval_avg_sts": 0.7521192684266835,
|
999 |
+
"eval_sickr_spearman": 0.6942240568655569,
|
1000 |
+
"eval_stsb_spearman": 0.8100144799878102,
|
1001 |
+
"step": 12625
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 0.82,
|
1005 |
+
"eval_avg_sts": 0.7503450494614133,
|
1006 |
+
"eval_sickr_spearman": 0.6922287968807163,
|
1007 |
+
"eval_stsb_spearman": 0.8084613020421104,
|
1008 |
+
"step": 12750
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.82,
|
1012 |
+
"eval_avg_sts": 0.7517083341962134,
|
1013 |
+
"eval_sickr_spearman": 0.6941311647153756,
|
1014 |
+
"eval_stsb_spearman": 0.8092855036770511,
|
1015 |
+
"step": 12875
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"electra_acc": 0.9071,
|
1019 |
+
"electra_fix_acc": 0.9901,
|
1020 |
+
"electra_rep_acc": 0.2276,
|
1021 |
+
"epoch": 0.83,
|
1022 |
+
"learning_rate": 5.840266222961732e-06,
|
1023 |
+
"loss": 0.0011,
|
1024 |
+
"neg_sim": -0.0141,
|
1025 |
+
"pos_sim": 0.798,
|
1026 |
+
"step": 13000
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.83,
|
1030 |
+
"eval_avg_sts": 0.7504582415898822,
|
1031 |
+
"eval_sickr_spearman": 0.6935004202912902,
|
1032 |
+
"eval_stsb_spearman": 0.8074160628884742,
|
1033 |
+
"step": 13000
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.84,
|
1037 |
+
"eval_avg_sts": 0.7504838292265648,
|
1038 |
+
"eval_sickr_spearman": 0.6931516664637482,
|
1039 |
+
"eval_stsb_spearman": 0.8078159919893814,
|
1040 |
+
"step": 13125
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.85,
|
1044 |
+
"eval_avg_sts": 0.7511643537875756,
|
1045 |
+
"eval_sickr_spearman": 0.6905446509130283,
|
1046 |
+
"eval_stsb_spearman": 0.8117840566621228,
|
1047 |
+
"step": 13250
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.86,
|
1051 |
+
"eval_avg_sts": 0.7516853154108011,
|
1052 |
+
"eval_sickr_spearman": 0.6920386417501228,
|
1053 |
+
"eval_stsb_spearman": 0.8113319890714794,
|
1054 |
+
"step": 13375
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"electra_acc": 0.9078,
|
1058 |
+
"electra_fix_acc": 0.9901,
|
1059 |
+
"electra_rep_acc": 0.2307,
|
1060 |
+
"epoch": 0.86,
|
1061 |
+
"learning_rate": 5.680276462306413e-06,
|
1062 |
+
"loss": 0.0011,
|
1063 |
+
"neg_sim": -0.0141,
|
1064 |
+
"pos_sim": 0.7933,
|
1065 |
+
"step": 13500
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.86,
|
1069 |
+
"eval_avg_sts": 0.7513575139583819,
|
1070 |
+
"eval_sickr_spearman": 0.6917417615121337,
|
1071 |
+
"eval_stsb_spearman": 0.8109732664046301,
|
1072 |
+
"step": 13500
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 0.87,
|
1076 |
+
"eval_avg_sts": 0.751417134937681,
|
1077 |
+
"eval_sickr_spearman": 0.6917422418231481,
|
1078 |
+
"eval_stsb_spearman": 0.8110920280522138,
|
1079 |
+
"step": 13625
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 0.88,
|
1083 |
+
"eval_avg_sts": 0.7526199054172857,
|
1084 |
+
"eval_sickr_spearman": 0.6928212605169554,
|
1085 |
+
"eval_stsb_spearman": 0.812418550317616,
|
1086 |
+
"step": 13750
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 0.89,
|
1090 |
+
"eval_avg_sts": 0.7532239951741806,
|
1091 |
+
"eval_sickr_spearman": 0.693511563506824,
|
1092 |
+
"eval_stsb_spearman": 0.8129364268415373,
|
1093 |
+
"step": 13875
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"electra_acc": 0.9078,
|
1097 |
+
"electra_fix_acc": 0.9899,
|
1098 |
+
"electra_rep_acc": 0.2332,
|
1099 |
+
"epoch": 0.9,
|
1100 |
+
"learning_rate": 5.520286701651095e-06,
|
1101 |
+
"loss": 0.001,
|
1102 |
+
"neg_sim": -0.0142,
|
1103 |
+
"pos_sim": 0.8032,
|
1104 |
+
"step": 14000
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 0.9,
|
1108 |
+
"eval_avg_sts": 0.7535878459898898,
|
1109 |
+
"eval_sickr_spearman": 0.6938975894690821,
|
1110 |
+
"eval_stsb_spearman": 0.8132781025106975,
|
1111 |
+
"step": 14000
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 0.9,
|
1115 |
+
"eval_avg_sts": 0.7579602803336107,
|
1116 |
+
"eval_sickr_spearman": 0.6938505189896726,
|
1117 |
+
"eval_stsb_spearman": 0.8220700416775488,
|
1118 |
+
"step": 14125
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.91,
|
1122 |
+
"eval_avg_sts": 0.7582493904128486,
|
1123 |
+
"eval_sickr_spearman": 0.6947031190713006,
|
1124 |
+
"eval_stsb_spearman": 0.8217956617543966,
|
1125 |
+
"step": 14250
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.92,
|
1129 |
+
"eval_avg_sts": 0.7585045342871344,
|
1130 |
+
"eval_sickr_spearman": 0.6946038387846281,
|
1131 |
+
"eval_stsb_spearman": 0.8224052297896408,
|
1132 |
+
"step": 14375
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"electra_acc": 0.9081,
|
1136 |
+
"electra_fix_acc": 0.99,
|
1137 |
+
"electra_rep_acc": 0.2354,
|
1138 |
+
"epoch": 0.93,
|
1139 |
+
"learning_rate": 5.3602969409957775e-06,
|
1140 |
+
"loss": 0.001,
|
1141 |
+
"neg_sim": -0.0142,
|
1142 |
+
"pos_sim": 0.8056,
|
1143 |
+
"step": 14500
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.93,
|
1147 |
+
"eval_avg_sts": 0.7586329610292095,
|
1148 |
+
"eval_sickr_spearman": 0.6949082118744413,
|
1149 |
+
"eval_stsb_spearman": 0.8223577101839777,
|
1150 |
+
"step": 14500
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.94,
|
1154 |
+
"eval_avg_sts": 0.7580983862167923,
|
1155 |
+
"eval_sickr_spearman": 0.6947662799696918,
|
1156 |
+
"eval_stsb_spearman": 0.8214304924638928,
|
1157 |
+
"step": 14625
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.94,
|
1161 |
+
"eval_avg_sts": 0.7543501652245072,
|
1162 |
+
"eval_sickr_spearman": 0.6945084970482733,
|
1163 |
+
"eval_stsb_spearman": 0.814191833400741,
|
1164 |
+
"step": 14750
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.95,
|
1168 |
+
"eval_avg_sts": 0.753735401541382,
|
1169 |
+
"eval_sickr_spearman": 0.6931743297643269,
|
1170 |
+
"eval_stsb_spearman": 0.8142964733184371,
|
1171 |
+
"step": 14875
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"electra_acc": 0.9081,
|
1175 |
+
"electra_fix_acc": 0.9899,
|
1176 |
+
"electra_rep_acc": 0.2356,
|
1177 |
+
"epoch": 0.96,
|
1178 |
+
"learning_rate": 5.200307180340458e-06,
|
1179 |
+
"loss": 0.001,
|
1180 |
+
"neg_sim": -0.0142,
|
1181 |
+
"pos_sim": 0.8068,
|
1182 |
+
"step": 15000
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 0.96,
|
1186 |
+
"eval_avg_sts": 0.7565776728970167,
|
1187 |
+
"eval_sickr_spearman": 0.699184805084288,
|
1188 |
+
"eval_stsb_spearman": 0.8139705407097454,
|
1189 |
+
"step": 15000
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 0.97,
|
1193 |
+
"eval_avg_sts": 0.7555687559765775,
|
1194 |
+
"eval_sickr_spearman": 0.6981326357761847,
|
1195 |
+
"eval_stsb_spearman": 0.8130048761769703,
|
1196 |
+
"step": 15125
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.98,
|
1200 |
+
"eval_avg_sts": 0.7607557679069236,
|
1201 |
+
"eval_sickr_spearman": 0.7007437985747662,
|
1202 |
+
"eval_stsb_spearman": 0.8207677372390809,
|
1203 |
+
"step": 15250
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.98,
|
1207 |
+
"eval_avg_sts": 0.7560246287263773,
|
1208 |
+
"eval_sickr_spearman": 0.6948236771359103,
|
1209 |
+
"eval_stsb_spearman": 0.8172255803168443,
|
1210 |
+
"step": 15375
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"electra_acc": 0.9077,
|
1214 |
+
"electra_fix_acc": 0.9897,
|
1215 |
+
"electra_rep_acc": 0.24,
|
1216 |
+
"epoch": 0.99,
|
1217 |
+
"learning_rate": 5.04031741968514e-06,
|
1218 |
+
"loss": 0.0011,
|
1219 |
+
"neg_sim": -0.0141,
|
1220 |
+
"pos_sim": 0.7969,
|
1221 |
+
"step": 15500
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.99,
|
1225 |
+
"eval_avg_sts": 0.7559485354838383,
|
1226 |
+
"eval_sickr_spearman": 0.6950054268237521,
|
1227 |
+
"eval_stsb_spearman": 0.8168916441439246,
|
1228 |
+
"step": 15500
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 1.0,
|
1232 |
+
"eval_avg_sts": 0.7502675969292933,
|
1233 |
+
"eval_sickr_spearman": 0.6866761613989633,
|
1234 |
+
"eval_stsb_spearman": 0.8138590324596235,
|
1235 |
+
"step": 15625
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.01,
|
1239 |
+
"eval_avg_sts": 0.7497139540559181,
|
1240 |
+
"eval_sickr_spearman": 0.6875880798908671,
|
1241 |
+
"eval_stsb_spearman": 0.811839828220969,
|
1242 |
+
"step": 15750
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 1.02,
|
1246 |
+
"eval_avg_sts": 0.7507851484505732,
|
1247 |
+
"eval_sickr_spearman": 0.6884938984328886,
|
1248 |
+
"eval_stsb_spearman": 0.8130763984682579,
|
1249 |
+
"step": 15875
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"electra_acc": 0.9081,
|
1253 |
+
"electra_fix_acc": 0.9898,
|
1254 |
+
"electra_rep_acc": 0.239,
|
1255 |
+
"epoch": 1.02,
|
1256 |
+
"learning_rate": 4.8803276590298225e-06,
|
1257 |
+
"loss": 0.001,
|
1258 |
+
"neg_sim": NaN,
|
1259 |
+
"pos_sim": 0.7953,
|
1260 |
+
"step": 16000
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 1.02,
|
1264 |
+
"eval_avg_sts": 0.7479678946675965,
|
1265 |
+
"eval_sickr_spearman": 0.6853699555953537,
|
1266 |
+
"eval_stsb_spearman": 0.8105658337398391,
|
1267 |
+
"step": 16000
|
1268 |
+
},
|
1269 |
+
{
|
1270 |
+
"epoch": 1.03,
|
1271 |
+
"eval_avg_sts": 0.7479128193954279,
|
1272 |
+
"eval_sickr_spearman": 0.6867578623025095,
|
1273 |
+
"eval_stsb_spearman": 0.8090677764883464,
|
1274 |
+
"step": 16125
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 1.04,
|
1278 |
+
"eval_avg_sts": 0.7487959084542308,
|
1279 |
+
"eval_sickr_spearman": 0.68736439905147,
|
1280 |
+
"eval_stsb_spearman": 0.8102274178569916,
|
1281 |
+
"step": 16250
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.05,
|
1285 |
+
"eval_avg_sts": 0.7500295795078514,
|
1286 |
+
"eval_sickr_spearman": 0.688809030489424,
|
1287 |
+
"eval_stsb_spearman": 0.8112501285262789,
|
1288 |
+
"step": 16375
|
1289 |
+
},
|
1290 |
+
{
|
1291 |
+
"electra_acc": 0.9078,
|
1292 |
+
"electra_fix_acc": 0.9898,
|
1293 |
+
"electra_rep_acc": 0.2379,
|
1294 |
+
"epoch": 1.06,
|
1295 |
+
"learning_rate": 4.720337898374505e-06,
|
1296 |
+
"loss": 0.0011,
|
1297 |
+
"neg_sim": NaN,
|
1298 |
+
"pos_sim": 0.8055,
|
1299 |
+
"step": 16500
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.06,
|
1303 |
+
"eval_avg_sts": 0.7515077711907536,
|
1304 |
+
"eval_sickr_spearman": 0.690066388662871,
|
1305 |
+
"eval_stsb_spearman": 0.8129491537186362,
|
1306 |
+
"step": 16500
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 1.06,
|
1310 |
+
"eval_avg_sts": 0.7490196746582567,
|
1311 |
+
"eval_sickr_spearman": 0.6842396396852107,
|
1312 |
+
"eval_stsb_spearman": 0.8137997096313027,
|
1313 |
+
"step": 16625
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 1.07,
|
1317 |
+
"eval_avg_sts": 0.7500539670025419,
|
1318 |
+
"eval_sickr_spearman": 0.6851718753330229,
|
1319 |
+
"eval_stsb_spearman": 0.8149360586720608,
|
1320 |
+
"step": 16750
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 1.08,
|
1324 |
+
"eval_avg_sts": 0.7490200514710061,
|
1325 |
+
"eval_sickr_spearman": 0.6843091406889915,
|
1326 |
+
"eval_stsb_spearman": 0.8137309622530207,
|
1327 |
+
"step": 16875
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"electra_acc": 0.9084,
|
1331 |
+
"electra_fix_acc": 0.9895,
|
1332 |
+
"electra_rep_acc": 0.2437,
|
1333 |
+
"epoch": 1.09,
|
1334 |
+
"learning_rate": 4.560348137719187e-06,
|
1335 |
+
"loss": 0.001,
|
1336 |
+
"neg_sim": NaN,
|
1337 |
+
"pos_sim": 0.8007,
|
1338 |
+
"step": 17000
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 1.09,
|
1342 |
+
"eval_avg_sts": 0.7434034453107932,
|
1343 |
+
"eval_sickr_spearman": 0.677096502310436,
|
1344 |
+
"eval_stsb_spearman": 0.8097103883111502,
|
1345 |
+
"step": 17000
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 1.1,
|
1349 |
+
"eval_avg_sts": 0.7431564820160605,
|
1350 |
+
"eval_sickr_spearman": 0.677125561126806,
|
1351 |
+
"eval_stsb_spearman": 0.8091874029053152,
|
1352 |
+
"step": 17125
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 1.1,
|
1356 |
+
"eval_avg_sts": 0.7442892283774005,
|
1357 |
+
"eval_sickr_spearman": 0.6786750444591996,
|
1358 |
+
"eval_stsb_spearman": 0.8099034122956015,
|
1359 |
+
"step": 17250
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 1.11,
|
1363 |
+
"eval_avg_sts": 0.7452452513650849,
|
1364 |
+
"eval_sickr_spearman": 0.6798861967130629,
|
1365 |
+
"eval_stsb_spearman": 0.8106043060171069,
|
1366 |
+
"step": 17375
|
1367 |
+
},
|
1368 |
+
{
|
1369 |
+
"electra_acc": 0.9085,
|
1370 |
+
"electra_fix_acc": 0.9896,
|
1371 |
+
"electra_rep_acc": 0.2435,
|
1372 |
+
"epoch": 1.12,
|
1373 |
+
"learning_rate": 4.400358377063868e-06,
|
1374 |
+
"loss": 0.001,
|
1375 |
+
"neg_sim": NaN,
|
1376 |
+
"pos_sim": 0.8058,
|
1377 |
+
"step": 17500
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.12,
|
1381 |
+
"eval_avg_sts": 0.7457855940878162,
|
1382 |
+
"eval_sickr_spearman": 0.6806044538039685,
|
1383 |
+
"eval_stsb_spearman": 0.810966734371664,
|
1384 |
+
"step": 17500
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 1.13,
|
1388 |
+
"eval_avg_sts": 0.7416386948034206,
|
1389 |
+
"eval_sickr_spearman": 0.6797112674416254,
|
1390 |
+
"eval_stsb_spearman": 0.8035661221652158,
|
1391 |
+
"step": 17625
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 1.14,
|
1395 |
+
"eval_avg_sts": 0.7423254082827856,
|
1396 |
+
"eval_sickr_spearman": 0.6808730437232104,
|
1397 |
+
"eval_stsb_spearman": 0.8037777728423607,
|
1398 |
+
"step": 17750
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 1.14,
|
1402 |
+
"eval_avg_sts": 0.7413901886271141,
|
1403 |
+
"eval_sickr_spearman": 0.681068914554875,
|
1404 |
+
"eval_stsb_spearman": 0.8017114626993534,
|
1405 |
+
"step": 17875
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"electra_acc": 0.9082,
|
1409 |
+
"electra_fix_acc": 0.9892,
|
1410 |
+
"electra_rep_acc": 0.247,
|
1411 |
+
"epoch": 1.15,
|
1412 |
+
"learning_rate": 4.24036861640855e-06,
|
1413 |
+
"loss": 0.001,
|
1414 |
+
"neg_sim": NaN,
|
1415 |
+
"pos_sim": 0.8062,
|
1416 |
+
"step": 18000
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 1.15,
|
1420 |
+
"eval_avg_sts": 0.7429114158358341,
|
1421 |
+
"eval_sickr_spearman": 0.6825547086467617,
|
1422 |
+
"eval_stsb_spearman": 0.8032681230249066,
|
1423 |
+
"step": 18000
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 1.16,
|
1427 |
+
"eval_avg_sts": 0.7439526113533993,
|
1428 |
+
"eval_sickr_spearman": 0.6837044771529871,
|
1429 |
+
"eval_stsb_spearman": 0.8042007455538115,
|
1430 |
+
"step": 18125
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 1.17,
|
1434 |
+
"eval_avg_sts": 0.7450607408838441,
|
1435 |
+
"eval_sickr_spearman": 0.686960841737187,
|
1436 |
+
"eval_stsb_spearman": 0.8031606400305011,
|
1437 |
+
"step": 18250
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 1.18,
|
1441 |
+
"eval_avg_sts": 0.745855277528227,
|
1442 |
+
"eval_sickr_spearman": 0.6876279457050609,
|
1443 |
+
"eval_stsb_spearman": 0.804082609351393,
|
1444 |
+
"step": 18375
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"electra_acc": 0.9078,
|
1448 |
+
"electra_fix_acc": 0.9895,
|
1449 |
+
"electra_rep_acc": 0.242,
|
1450 |
+
"epoch": 1.18,
|
1451 |
+
"learning_rate": 4.080378855753232e-06,
|
1452 |
+
"loss": 0.0011,
|
1453 |
+
"neg_sim": NaN,
|
1454 |
+
"pos_sim": 0.8079,
|
1455 |
+
"step": 18500
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 1.18,
|
1459 |
+
"eval_avg_sts": 0.7462797427639389,
|
1460 |
+
"eval_sickr_spearman": 0.6877381290517599,
|
1461 |
+
"eval_stsb_spearman": 0.804821356476118,
|
1462 |
+
"step": 18500
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 1.19,
|
1466 |
+
"eval_avg_sts": 0.744680795271585,
|
1467 |
+
"eval_sickr_spearman": 0.6867351916226306,
|
1468 |
+
"eval_stsb_spearman": 0.8026263989205394,
|
1469 |
+
"step": 18625
|
1470 |
+
},
|
1471 |
+
{
|
1472 |
+
"epoch": 1.2,
|
1473 |
+
"eval_avg_sts": 0.7415540412607211,
|
1474 |
+
"eval_sickr_spearman": 0.6830318976395493,
|
1475 |
+
"eval_stsb_spearman": 0.800076184881893,
|
1476 |
+
"step": 18750
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 1.21,
|
1480 |
+
"eval_avg_sts": 0.7426288639389378,
|
1481 |
+
"eval_sickr_spearman": 0.6841978045958581,
|
1482 |
+
"eval_stsb_spearman": 0.8010599232820175,
|
1483 |
+
"step": 18875
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"electra_acc": 0.9088,
|
1487 |
+
"electra_fix_acc": 0.9896,
|
1488 |
+
"electra_rep_acc": 0.2456,
|
1489 |
+
"epoch": 1.22,
|
1490 |
+
"learning_rate": 3.920389095097914e-06,
|
1491 |
+
"loss": 0.001,
|
1492 |
+
"neg_sim": NaN,
|
1493 |
+
"pos_sim": 0.8107,
|
1494 |
+
"step": 19000
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.22,
|
1498 |
+
"eval_avg_sts": 0.7440228503017443,
|
1499 |
+
"eval_sickr_spearman": 0.6852098768089162,
|
1500 |
+
"eval_stsb_spearman": 0.8028358237945724,
|
1501 |
+
"step": 19000
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.22,
|
1505 |
+
"eval_avg_sts": 0.7446803355301828,
|
1506 |
+
"eval_sickr_spearman": 0.6853459400446347,
|
1507 |
+
"eval_stsb_spearman": 0.8040147310157307,
|
1508 |
+
"step": 19125
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.23,
|
1512 |
+
"eval_avg_sts": 0.745178310449073,
|
1513 |
+
"eval_sickr_spearman": 0.685846664277127,
|
1514 |
+
"eval_stsb_spearman": 0.804509956621019,
|
1515 |
+
"step": 19250
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.24,
|
1519 |
+
"eval_avg_sts": 0.7501895198558063,
|
1520 |
+
"eval_sickr_spearman": 0.6936651189381215,
|
1521 |
+
"eval_stsb_spearman": 0.806713920773491,
|
1522 |
+
"step": 19375
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"electra_acc": 0.9087,
|
1526 |
+
"electra_fix_acc": 0.9894,
|
1527 |
+
"electra_rep_acc": 0.2472,
|
1528 |
+
"epoch": 1.25,
|
1529 |
+
"learning_rate": 3.760399334442596e-06,
|
1530 |
+
"loss": 0.001,
|
1531 |
+
"neg_sim": NaN,
|
1532 |
+
"pos_sim": 0.815,
|
1533 |
+
"step": 19500
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 1.25,
|
1537 |
+
"eval_avg_sts": 0.7504868457577191,
|
1538 |
+
"eval_sickr_spearman": 0.693660123703572,
|
1539 |
+
"eval_stsb_spearman": 0.8073135678118661,
|
1540 |
+
"step": 19500
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 1.26,
|
1544 |
+
"eval_avg_sts": 0.7515054770519676,
|
1545 |
+
"eval_sickr_spearman": 0.6934854345876417,
|
1546 |
+
"eval_stsb_spearman": 0.8095255195162936,
|
1547 |
+
"step": 19625
|
1548 |
+
},
|
1549 |
+
{
|
1550 |
+
"epoch": 1.26,
|
1551 |
+
"eval_avg_sts": 0.7519980000949484,
|
1552 |
+
"eval_sickr_spearman": 0.6937166563099646,
|
1553 |
+
"eval_stsb_spearman": 0.8102793438799323,
|
1554 |
+
"step": 19750
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.27,
|
1558 |
+
"eval_avg_sts": 0.7521186477822681,
|
1559 |
+
"eval_sickr_spearman": 0.693651237949806,
|
1560 |
+
"eval_stsb_spearman": 0.8105860576147302,
|
1561 |
+
"step": 19875
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"electra_acc": 0.9094,
|
1565 |
+
"electra_fix_acc": 0.9895,
|
1566 |
+
"electra_rep_acc": 0.2499,
|
1567 |
+
"epoch": 1.28,
|
1568 |
+
"learning_rate": 3.600409573787278e-06,
|
1569 |
+
"loss": 0.001,
|
1570 |
+
"neg_sim": NaN,
|
1571 |
+
"pos_sim": 0.8155,
|
1572 |
+
"step": 20000
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 1.28,
|
1576 |
+
"eval_avg_sts": 0.752341790734355,
|
1577 |
+
"eval_sickr_spearman": 0.6935850991231257,
|
1578 |
+
"eval_stsb_spearman": 0.8110984823455842,
|
1579 |
+
"step": 20000
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 1.29,
|
1583 |
+
"eval_avg_sts": 0.7524918475690561,
|
1584 |
+
"eval_sickr_spearman": 0.6935691527974482,
|
1585 |
+
"eval_stsb_spearman": 0.811414542340664,
|
1586 |
+
"step": 20125
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 1.3,
|
1590 |
+
"eval_avg_sts": 0.7557856359443814,
|
1591 |
+
"eval_sickr_spearman": 0.6970248944837176,
|
1592 |
+
"eval_stsb_spearman": 0.8145463774050452,
|
1593 |
+
"step": 20250
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.3,
|
1597 |
+
"eval_avg_sts": 0.7552826569601827,
|
1598 |
+
"eval_sickr_spearman": 0.6959100445882376,
|
1599 |
+
"eval_stsb_spearman": 0.814655269332128,
|
1600 |
+
"step": 20375
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"electra_acc": 0.9094,
|
1604 |
+
"electra_fix_acc": 0.9895,
|
1605 |
+
"electra_rep_acc": 0.2515,
|
1606 |
+
"epoch": 1.31,
|
1607 |
+
"learning_rate": 3.44041981313196e-06,
|
1608 |
+
"loss": 0.001,
|
1609 |
+
"neg_sim": NaN,
|
1610 |
+
"pos_sim": 0.8179,
|
1611 |
+
"step": 20500
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.31,
|
1615 |
+
"eval_avg_sts": 0.7551388763512048,
|
1616 |
+
"eval_sickr_spearman": 0.6953964480205598,
|
1617 |
+
"eval_stsb_spearman": 0.8148813046818498,
|
1618 |
+
"step": 20500
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 1.32,
|
1622 |
+
"eval_avg_sts": 0.7551894637379806,
|
1623 |
+
"eval_sickr_spearman": 0.6956948652537948,
|
1624 |
+
"eval_stsb_spearman": 0.8146840622221664,
|
1625 |
+
"step": 20625
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 1.33,
|
1629 |
+
"eval_avg_sts": 0.7549148751641654,
|
1630 |
+
"eval_sickr_spearman": 0.6951038425505989,
|
1631 |
+
"eval_stsb_spearman": 0.8147259077777321,
|
1632 |
+
"step": 20750
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 1.34,
|
1636 |
+
"eval_avg_sts": 0.754268177606626,
|
1637 |
+
"eval_sickr_spearman": 0.6945316000080651,
|
1638 |
+
"eval_stsb_spearman": 0.814004755205187,
|
1639 |
+
"step": 20875
|
1640 |
+
},
|
1641 |
+
{
|
1642 |
+
"electra_acc": 0.9089,
|
1643 |
+
"electra_fix_acc": 0.9891,
|
1644 |
+
"electra_rep_acc": 0.2537,
|
1645 |
+
"epoch": 1.34,
|
1646 |
+
"learning_rate": 3.280430052476642e-06,
|
1647 |
+
"loss": 0.0009,
|
1648 |
+
"neg_sim": NaN,
|
1649 |
+
"pos_sim": 0.8193,
|
1650 |
+
"step": 21000
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 1.34,
|
1654 |
+
"eval_avg_sts": 0.7544681011807751,
|
1655 |
+
"eval_sickr_spearman": 0.6945047025912598,
|
1656 |
+
"eval_stsb_spearman": 0.8144314997702904,
|
1657 |
+
"step": 21000
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 1.35,
|
1661 |
+
"eval_avg_sts": 0.7543169348596496,
|
1662 |
+
"eval_sickr_spearman": 0.694174296644467,
|
1663 |
+
"eval_stsb_spearman": 0.8144595730748322,
|
1664 |
+
"step": 21125
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 1.36,
|
1668 |
+
"eval_avg_sts": 0.7553283942077516,
|
1669 |
+
"eval_sickr_spearman": 0.6958436656060499,
|
1670 |
+
"eval_stsb_spearman": 0.8148131228094532,
|
1671 |
+
"step": 21250
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 1.37,
|
1675 |
+
"eval_avg_sts": 0.7557282247685372,
|
1676 |
+
"eval_sickr_spearman": 0.6962398741618131,
|
1677 |
+
"eval_stsb_spearman": 0.8152165753752613,
|
1678 |
+
"step": 21375
|
1679 |
+
},
|
1680 |
+
{
|
1681 |
+
"electra_acc": 0.9093,
|
1682 |
+
"electra_fix_acc": 0.9893,
|
1683 |
+
"electra_rep_acc": 0.2553,
|
1684 |
+
"epoch": 1.38,
|
1685 |
+
"learning_rate": 3.1204402918213238e-06,
|
1686 |
+
"loss": 0.001,
|
1687 |
+
"neg_sim": NaN,
|
1688 |
+
"pos_sim": 0.822,
|
1689 |
+
"step": 21500
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 1.38,
|
1693 |
+
"eval_avg_sts": 0.7533899213084664,
|
1694 |
+
"eval_sickr_spearman": 0.6928663617212057,
|
1695 |
+
"eval_stsb_spearman": 0.813913480895727,
|
1696 |
+
"step": 21500
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 1.38,
|
1700 |
+
"eval_avg_sts": 0.7534343863779988,
|
1701 |
+
"eval_sickr_spearman": 0.6929559877564893,
|
1702 |
+
"eval_stsb_spearman": 0.8139127849995083,
|
1703 |
+
"step": 21625
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 1.39,
|
1707 |
+
"eval_avg_sts": 0.7539297584804894,
|
1708 |
+
"eval_sickr_spearman": 0.6930869205390096,
|
1709 |
+
"eval_stsb_spearman": 0.8147725964219692,
|
1710 |
+
"step": 21750
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 1.4,
|
1714 |
+
"eval_avg_sts": 0.7523440794130264,
|
1715 |
+
"eval_sickr_spearman": 0.691800551580294,
|
1716 |
+
"eval_stsb_spearman": 0.8128876072457588,
|
1717 |
+
"step": 21875
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"electra_acc": 0.9091,
|
1721 |
+
"electra_fix_acc": 0.9891,
|
1722 |
+
"electra_rep_acc": 0.253,
|
1723 |
+
"epoch": 1.41,
|
1724 |
+
"learning_rate": 2.960450531166006e-06,
|
1725 |
+
"loss": 0.001,
|
1726 |
+
"neg_sim": NaN,
|
1727 |
+
"pos_sim": 0.8192,
|
1728 |
+
"step": 22000
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 1.41,
|
1732 |
+
"eval_avg_sts": 0.7535926716898982,
|
1733 |
+
"eval_sickr_spearman": 0.696256204736302,
|
1734 |
+
"eval_stsb_spearman": 0.8109291386434943,
|
1735 |
+
"step": 22000
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"epoch": 1.42,
|
1739 |
+
"eval_avg_sts": 0.7527606084226345,
|
1740 |
+
"eval_sickr_spearman": 0.6954414051315059,
|
1741 |
+
"eval_stsb_spearman": 0.8100798117137631,
|
1742 |
+
"step": 22125
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 1.42,
|
1746 |
+
"eval_avg_sts": 0.7533114920096069,
|
1747 |
+
"eval_sickr_spearman": 0.695455142026517,
|
1748 |
+
"eval_stsb_spearman": 0.8111678419926969,
|
1749 |
+
"step": 22250
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 1.43,
|
1753 |
+
"eval_avg_sts": 0.7519280470002075,
|
1754 |
+
"eval_sickr_spearman": 0.6946230992563046,
|
1755 |
+
"eval_stsb_spearman": 0.8092329947441105,
|
1756 |
+
"step": 22375
|
1757 |
+
},
|
1758 |
+
{
|
1759 |
+
"electra_acc": 0.9093,
|
1760 |
+
"electra_fix_acc": 0.9893,
|
1761 |
+
"electra_rep_acc": 0.2551,
|
1762 |
+
"epoch": 1.44,
|
1763 |
+
"learning_rate": 2.8004607705106875e-06,
|
1764 |
+
"loss": 0.0011,
|
1765 |
+
"neg_sim": NaN,
|
1766 |
+
"pos_sim": 0.8135,
|
1767 |
+
"step": 22500
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.44,
|
1771 |
+
"eval_avg_sts": 0.7522224828721787,
|
1772 |
+
"eval_sickr_spearman": 0.694889767931489,
|
1773 |
+
"eval_stsb_spearman": 0.8095551978128684,
|
1774 |
+
"step": 22500
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.45,
|
1778 |
+
"eval_avg_sts": 0.7509487345671295,
|
1779 |
+
"eval_sickr_spearman": 0.6947804011135146,
|
1780 |
+
"eval_stsb_spearman": 0.8071170680207445,
|
1781 |
+
"step": 22625
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.46,
|
1785 |
+
"eval_avg_sts": 0.7535117851178551,
|
1786 |
+
"eval_sickr_spearman": 0.6966824807615652,
|
1787 |
+
"eval_stsb_spearman": 0.810341089474145,
|
1788 |
+
"step": 22750
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.46,
|
1792 |
+
"eval_avg_sts": 0.7554057278055278,
|
1793 |
+
"eval_sickr_spearman": 0.6974278273936819,
|
1794 |
+
"eval_stsb_spearman": 0.8133836282173738,
|
1795 |
+
"step": 22875
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"electra_acc": 0.9094,
|
1799 |
+
"electra_fix_acc": 0.9891,
|
1800 |
+
"electra_rep_acc": 0.2557,
|
1801 |
+
"epoch": 1.47,
|
1802 |
+
"learning_rate": 2.640471009855369e-06,
|
1803 |
+
"loss": 0.0012,
|
1804 |
+
"neg_sim": NaN,
|
1805 |
+
"pos_sim": 0.8108,
|
1806 |
+
"step": 23000
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 1.47,
|
1810 |
+
"eval_avg_sts": 0.7573042151426209,
|
1811 |
+
"eval_sickr_spearman": 0.6996995063672988,
|
1812 |
+
"eval_stsb_spearman": 0.814908923917943,
|
1813 |
+
"step": 23000
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 1.48,
|
1817 |
+
"eval_avg_sts": 0.7572778466663158,
|
1818 |
+
"eval_sickr_spearman": 0.699593405664222,
|
1819 |
+
"eval_stsb_spearman": 0.8149622876684096,
|
1820 |
+
"step": 23125
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 1.49,
|
1824 |
+
"eval_avg_sts": 0.7572787295536805,
|
1825 |
+
"eval_sickr_spearman": 0.6995496493308119,
|
1826 |
+
"eval_stsb_spearman": 0.815007809776549,
|
1827 |
+
"step": 23250
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 1.5,
|
1831 |
+
"eval_avg_sts": 0.7578655158883527,
|
1832 |
+
"eval_sickr_spearman": 0.7004442285950968,
|
1833 |
+
"eval_stsb_spearman": 0.8152868031816085,
|
1834 |
+
"step": 23375
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"electra_acc": 0.9093,
|
1838 |
+
"electra_fix_acc": 0.9889,
|
1839 |
+
"electra_rep_acc": 0.2565,
|
1840 |
+
"epoch": 1.5,
|
1841 |
+
"learning_rate": 2.4804812492000513e-06,
|
1842 |
+
"loss": 0.001,
|
1843 |
+
"neg_sim": NaN,
|
1844 |
+
"pos_sim": 0.8119,
|
1845 |
+
"step": 23500
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 1.5,
|
1849 |
+
"eval_avg_sts": 0.7580453272234033,
|
1850 |
+
"eval_sickr_spearman": 0.700563201633359,
|
1851 |
+
"eval_stsb_spearman": 0.8155274528134476,
|
1852 |
+
"step": 23500
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"epoch": 1.51,
|
1856 |
+
"eval_avg_sts": 0.7589489492705888,
|
1857 |
+
"eval_sickr_spearman": 0.7011428889966156,
|
1858 |
+
"eval_stsb_spearman": 0.8167550095445619,
|
1859 |
+
"step": 23625
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 1.52,
|
1863 |
+
"eval_avg_sts": 0.759282090184078,
|
1864 |
+
"eval_sickr_spearman": 0.7009553275454997,
|
1865 |
+
"eval_stsb_spearman": 0.8176088528226563,
|
1866 |
+
"step": 23750
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 1.53,
|
1870 |
+
"eval_avg_sts": 0.7594355007785425,
|
1871 |
+
"eval_sickr_spearman": 0.7010773265431525,
|
1872 |
+
"eval_stsb_spearman": 0.8177936750139324,
|
1873 |
+
"step": 23875
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"electra_acc": 0.9092,
|
1877 |
+
"electra_fix_acc": 0.989,
|
1878 |
+
"electra_rep_acc": 0.2555,
|
1879 |
+
"epoch": 1.54,
|
1880 |
+
"learning_rate": 2.3204914885447333e-06,
|
1881 |
+
"loss": 0.001,
|
1882 |
+
"neg_sim": NaN,
|
1883 |
+
"pos_sim": 0.8149,
|
1884 |
+
"step": 24000
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 1.54,
|
1888 |
+
"eval_avg_sts": 0.7594249307434521,
|
1889 |
+
"eval_sickr_spearman": 0.7010194490659197,
|
1890 |
+
"eval_stsb_spearman": 0.8178304124209844,
|
1891 |
+
"step": 24000
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 1.54,
|
1895 |
+
"eval_avg_sts": 0.7594551033154371,
|
1896 |
+
"eval_sickr_spearman": 0.7012371740487385,
|
1897 |
+
"eval_stsb_spearman": 0.8176730325821358,
|
1898 |
+
"step": 24125
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 1.55,
|
1902 |
+
"eval_avg_sts": 0.7589237357383787,
|
1903 |
+
"eval_sickr_spearman": 0.7005038351919814,
|
1904 |
+
"eval_stsb_spearman": 0.8173436362847759,
|
1905 |
+
"step": 24250
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 1.56,
|
1909 |
+
"eval_avg_sts": 0.7588819689189907,
|
1910 |
+
"eval_sickr_spearman": 0.7008921666471086,
|
1911 |
+
"eval_stsb_spearman": 0.816871771190873,
|
1912 |
+
"step": 24375
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"electra_acc": 0.9094,
|
1916 |
+
"electra_fix_acc": 0.989,
|
1917 |
+
"electra_rep_acc": 0.2584,
|
1918 |
+
"epoch": 1.57,
|
1919 |
+
"learning_rate": 2.1605017278894154e-06,
|
1920 |
+
"loss": 0.001,
|
1921 |
+
"neg_sim": NaN,
|
1922 |
+
"pos_sim": 0.8167,
|
1923 |
+
"step": 24500
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 1.57,
|
1927 |
+
"eval_avg_sts": 0.7589559409437466,
|
1928 |
+
"eval_sickr_spearman": 0.7010030224292277,
|
1929 |
+
"eval_stsb_spearman": 0.8169088594582655,
|
1930 |
+
"step": 24500
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 1.58,
|
1934 |
+
"eval_avg_sts": 0.7589222814938349,
|
1935 |
+
"eval_sickr_spearman": 0.7009486992535012,
|
1936 |
+
"eval_stsb_spearman": 0.8168958637341686,
|
1937 |
+
"step": 24625
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 1.58,
|
1941 |
+
"eval_avg_sts": 0.7574752410333385,
|
1942 |
+
"eval_sickr_spearman": 0.6996315903898653,
|
1943 |
+
"eval_stsb_spearman": 0.8153188916768117,
|
1944 |
+
"step": 24750
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 1.59,
|
1948 |
+
"eval_avg_sts": 0.7564910076346855,
|
1949 |
+
"eval_sickr_spearman": 0.6992222213123084,
|
1950 |
+
"eval_stsb_spearman": 0.8137597939570625,
|
1951 |
+
"step": 24875
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"electra_acc": 0.9093,
|
1955 |
+
"electra_fix_acc": 0.9891,
|
1956 |
+
"electra_rep_acc": 0.2566,
|
1957 |
+
"epoch": 1.6,
|
1958 |
+
"learning_rate": 2.000511967234097e-06,
|
1959 |
+
"loss": 0.0011,
|
1960 |
+
"neg_sim": NaN,
|
1961 |
+
"pos_sim": 0.8178,
|
1962 |
+
"step": 25000
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 1.6,
|
1966 |
+
"eval_avg_sts": 0.754858122417589,
|
1967 |
+
"eval_sickr_spearman": 0.6972444446483912,
|
1968 |
+
"eval_stsb_spearman": 0.8124718001867869,
|
1969 |
+
"step": 25000
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 1.61,
|
1973 |
+
"eval_avg_sts": 0.7550451133191622,
|
1974 |
+
"eval_sickr_spearman": 0.6974792206722207,
|
1975 |
+
"eval_stsb_spearman": 0.8126110059661038,
|
1976 |
+
"step": 25125
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 1.62,
|
1980 |
+
"eval_avg_sts": 0.754828720368155,
|
1981 |
+
"eval_sickr_spearman": 0.6962917477513663,
|
1982 |
+
"eval_stsb_spearman": 0.8133656929849435,
|
1983 |
+
"step": 25250
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.62,
|
1987 |
+
"eval_avg_sts": 0.7548476950408536,
|
1988 |
+
"eval_sickr_spearman": 0.6961924674646935,
|
1989 |
+
"eval_stsb_spearman": 0.8135029226170137,
|
1990 |
+
"step": 25375
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"electra_acc": 0.9096,
|
1994 |
+
"electra_fix_acc": 0.9892,
|
1995 |
+
"electra_rep_acc": 0.2585,
|
1996 |
+
"epoch": 1.63,
|
1997 |
+
"learning_rate": 1.8405222065787792e-06,
|
1998 |
+
"loss": 0.0011,
|
1999 |
+
"neg_sim": NaN,
|
2000 |
+
"pos_sim": 0.8169,
|
2001 |
+
"step": 25500
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 1.63,
|
2005 |
+
"eval_avg_sts": 0.7530610693683093,
|
2006 |
+
"eval_sickr_spearman": 0.6936729960387574,
|
2007 |
+
"eval_stsb_spearman": 0.8124491426978612,
|
2008 |
+
"step": 25500
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 1.64,
|
2012 |
+
"eval_avg_sts": 0.7537427601811764,
|
2013 |
+
"eval_sickr_spearman": 0.6928838450421292,
|
2014 |
+
"eval_stsb_spearman": 0.8146016753202237,
|
2015 |
+
"step": 25625
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 1.65,
|
2019 |
+
"eval_avg_sts": 0.7538542984125725,
|
2020 |
+
"eval_sickr_spearman": 0.6928155928469857,
|
2021 |
+
"eval_stsb_spearman": 0.8148930039781592,
|
2022 |
+
"step": 25750
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.66,
|
2026 |
+
"eval_avg_sts": 0.7539219581746606,
|
2027 |
+
"eval_sickr_spearman": 0.6929616554264589,
|
2028 |
+
"eval_stsb_spearman": 0.8148822609228621,
|
2029 |
+
"step": 25875
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"electra_acc": 0.9096,
|
2033 |
+
"electra_fix_acc": 0.9892,
|
2034 |
+
"electra_rep_acc": 0.2568,
|
2035 |
+
"epoch": 1.66,
|
2036 |
+
"learning_rate": 1.6805324459234608e-06,
|
2037 |
+
"loss": 0.001,
|
2038 |
+
"neg_sim": NaN,
|
2039 |
+
"pos_sim": 0.8191,
|
2040 |
+
"step": 26000
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.66,
|
2044 |
+
"eval_avg_sts": 0.7537628256146356,
|
2045 |
+
"eval_sickr_spearman": 0.6923114103751897,
|
2046 |
+
"eval_stsb_spearman": 0.8152142408540815,
|
2047 |
+
"step": 26000
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 1.67,
|
2051 |
+
"eval_avg_sts": 0.754620615839658,
|
2052 |
+
"eval_sickr_spearman": 0.6932064219193875,
|
2053 |
+
"eval_stsb_spearman": 0.8160348097599284,
|
2054 |
+
"step": 26125
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.68,
|
2058 |
+
"eval_avg_sts": 0.7518830889314513,
|
2059 |
+
"eval_sickr_spearman": 0.690710149515446,
|
2060 |
+
"eval_stsb_spearman": 0.8130560283474566,
|
2061 |
+
"step": 26250
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.69,
|
2065 |
+
"eval_avg_sts": 0.7509225404957667,
|
2066 |
+
"eval_sickr_spearman": 0.6898265693733905,
|
2067 |
+
"eval_stsb_spearman": 0.8120185116181428,
|
2068 |
+
"step": 26375
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"electra_acc": 0.9096,
|
2072 |
+
"electra_fix_acc": 0.9892,
|
2073 |
+
"electra_rep_acc": 0.256,
|
2074 |
+
"epoch": 1.7,
|
2075 |
+
"learning_rate": 1.520542685268143e-06,
|
2076 |
+
"loss": 0.0011,
|
2077 |
+
"neg_sim": NaN,
|
2078 |
+
"pos_sim": 0.8194,
|
2079 |
+
"step": 26500
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 1.7,
|
2083 |
+
"eval_avg_sts": 0.7509117147704546,
|
2084 |
+
"eval_sickr_spearman": 0.690458994886026,
|
2085 |
+
"eval_stsb_spearman": 0.8113644346548832,
|
2086 |
+
"step": 26500
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 1.7,
|
2090 |
+
"eval_avg_sts": 0.751325870403242,
|
2091 |
+
"eval_sickr_spearman": 0.6910303728687339,
|
2092 |
+
"eval_stsb_spearman": 0.8116213679377499,
|
2093 |
+
"step": 26625
|
2094 |
+
},
|
2095 |
+
{
|
2096 |
+
"epoch": 1.71,
|
2097 |
+
"eval_avg_sts": 0.7505685715846826,
|
2098 |
+
"eval_sickr_spearman": 0.6889766590334431,
|
2099 |
+
"eval_stsb_spearman": 0.812160484135922,
|
2100 |
+
"step": 26750
|
2101 |
+
},
|
2102 |
+
{
|
2103 |
+
"epoch": 1.72,
|
2104 |
+
"eval_avg_sts": 0.7505717215143468,
|
2105 |
+
"eval_sickr_spearman": 0.6889912124571789,
|
2106 |
+
"eval_stsb_spearman": 0.8121522305715146,
|
2107 |
+
"step": 26875
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"electra_acc": 0.9097,
|
2111 |
+
"electra_fix_acc": 0.989,
|
2112 |
+
"electra_rep_acc": 0.2597,
|
2113 |
+
"epoch": 1.73,
|
2114 |
+
"learning_rate": 1.3605529246128248e-06,
|
2115 |
+
"loss": 0.001,
|
2116 |
+
"neg_sim": NaN,
|
2117 |
+
"pos_sim": 0.8193,
|
2118 |
+
"step": 27000
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"epoch": 1.73,
|
2122 |
+
"eval_avg_sts": 0.7506556450635647,
|
2123 |
+
"eval_sickr_spearman": 0.6890205594601575,
|
2124 |
+
"eval_stsb_spearman": 0.812290730666972,
|
2125 |
+
"step": 27000
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 1.74,
|
2129 |
+
"eval_avg_sts": 0.7509018804381178,
|
2130 |
+
"eval_sickr_spearman": 0.6900798373712735,
|
2131 |
+
"eval_stsb_spearman": 0.811723923504962,
|
2132 |
+
"step": 27125
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 1.74,
|
2136 |
+
"eval_avg_sts": 0.7500895498195226,
|
2137 |
+
"eval_sickr_spearman": 0.6892968343556296,
|
2138 |
+
"eval_stsb_spearman": 0.8108822652834156,
|
2139 |
+
"step": 27250
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 1.75,
|
2143 |
+
"eval_avg_sts": 0.7506787202343813,
|
2144 |
+
"eval_sickr_spearman": 0.6893182081957694,
|
2145 |
+
"eval_stsb_spearman": 0.8120392322729932,
|
2146 |
+
"step": 27375
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"electra_acc": 0.9101,
|
2150 |
+
"electra_fix_acc": 0.989,
|
2151 |
+
"electra_rep_acc": 0.262,
|
2152 |
+
"epoch": 1.76,
|
2153 |
+
"learning_rate": 1.2005631639575069e-06,
|
2154 |
+
"loss": 0.001,
|
2155 |
+
"neg_sim": NaN,
|
2156 |
+
"pos_sim": 0.8192,
|
2157 |
+
"step": 27500
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 1.76,
|
2161 |
+
"eval_avg_sts": 0.7507236365099843,
|
2162 |
+
"eval_sickr_spearman": 0.689373636086829,
|
2163 |
+
"eval_stsb_spearman": 0.8120736369331395,
|
2164 |
+
"step": 27500
|
2165 |
+
},
|
2166 |
+
{
|
2167 |
+
"epoch": 1.77,
|
2168 |
+
"eval_avg_sts": 0.7507778777687245,
|
2169 |
+
"eval_sickr_spearman": 0.6893403025024311,
|
2170 |
+
"eval_stsb_spearman": 0.812215453035018,
|
2171 |
+
"step": 27625
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 1.78,
|
2175 |
+
"eval_avg_sts": 0.7508593494865333,
|
2176 |
+
"eval_sickr_spearman": 0.6894537519640278,
|
2177 |
+
"eval_stsb_spearman": 0.8122649470090388,
|
2178 |
+
"step": 27750
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 1.78,
|
2182 |
+
"eval_avg_sts": 0.7509704306691856,
|
2183 |
+
"eval_sickr_spearman": 0.6894628778733011,
|
2184 |
+
"eval_stsb_spearman": 0.8124779834650699,
|
2185 |
+
"step": 27875
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"electra_acc": 0.9101,
|
2189 |
+
"electra_fix_acc": 0.9891,
|
2190 |
+
"electra_rep_acc": 0.2586,
|
2191 |
+
"epoch": 1.79,
|
2192 |
+
"learning_rate": 1.0405734033021888e-06,
|
2193 |
+
"loss": 0.001,
|
2194 |
+
"neg_sim": NaN,
|
2195 |
+
"pos_sim": 0.8201,
|
2196 |
+
"step": 28000
|
2197 |
+
},
|
2198 |
+
{
|
2199 |
+
"epoch": 1.79,
|
2200 |
+
"eval_avg_sts": 0.7509106758642159,
|
2201 |
+
"eval_sickr_spearman": 0.6893112436860609,
|
2202 |
+
"eval_stsb_spearman": 0.812510108042371,
|
2203 |
+
"step": 28000
|
2204 |
+
},
|
2205 |
+
{
|
2206 |
+
"epoch": 1.8,
|
2207 |
+
"eval_avg_sts": 0.7508459705581159,
|
2208 |
+
"eval_sickr_spearman": 0.6899334385740902,
|
2209 |
+
"eval_stsb_spearman": 0.8117585025421415,
|
2210 |
+
"step": 28125
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 1.81,
|
2214 |
+
"eval_avg_sts": 0.7510477486103114,
|
2215 |
+
"eval_sickr_spearman": 0.6902538540517839,
|
2216 |
+
"eval_stsb_spearman": 0.811841643168839,
|
2217 |
+
"step": 28250
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 1.82,
|
2221 |
+
"eval_avg_sts": 0.7507757787312187,
|
2222 |
+
"eval_sickr_spearman": 0.6898934766976937,
|
2223 |
+
"eval_stsb_spearman": 0.8116580807647437,
|
2224 |
+
"step": 28375
|
2225 |
+
},
|
2226 |
+
{
|
2227 |
+
"electra_acc": 0.9098,
|
2228 |
+
"electra_fix_acc": 0.989,
|
2229 |
+
"electra_rep_acc": 0.2594,
|
2230 |
+
"epoch": 1.82,
|
2231 |
+
"learning_rate": 8.805836426468707e-07,
|
2232 |
+
"loss": 0.0011,
|
2233 |
+
"neg_sim": NaN,
|
2234 |
+
"pos_sim": 0.8208,
|
2235 |
+
"step": 28500
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 1.82,
|
2239 |
+
"eval_avg_sts": 0.7507727971903551,
|
2240 |
+
"eval_sickr_spearman": 0.6899099993965885,
|
2241 |
+
"eval_stsb_spearman": 0.8116355949841215,
|
2242 |
+
"step": 28500
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 1.83,
|
2246 |
+
"eval_avg_sts": 0.7508146549871678,
|
2247 |
+
"eval_sickr_spearman": 0.6899898270871786,
|
2248 |
+
"eval_stsb_spearman": 0.811639482887157,
|
2249 |
+
"step": 28625
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 1.84,
|
2253 |
+
"eval_avg_sts": 0.7506882515044668,
|
2254 |
+
"eval_sickr_spearman": 0.6898797398026825,
|
2255 |
+
"eval_stsb_spearman": 0.8114967632062512,
|
2256 |
+
"step": 28750
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 1.85,
|
2260 |
+
"eval_avg_sts": 0.7507604828702781,
|
2261 |
+
"eval_sickr_spearman": 0.6899782035606307,
|
2262 |
+
"eval_stsb_spearman": 0.8115427621799256,
|
2263 |
+
"step": 28875
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"electra_acc": 0.9101,
|
2267 |
+
"electra_fix_acc": 0.989,
|
2268 |
+
"electra_rep_acc": 0.2588,
|
2269 |
+
"epoch": 1.86,
|
2270 |
+
"learning_rate": 7.205938819915525e-07,
|
2271 |
+
"loss": 0.0009,
|
2272 |
+
"neg_sim": NaN,
|
2273 |
+
"pos_sim": 0.821,
|
2274 |
+
"step": 29000
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 1.86,
|
2278 |
+
"eval_avg_sts": 0.7507686428892963,
|
2279 |
+
"eval_sickr_spearman": 0.6899909798336131,
|
2280 |
+
"eval_stsb_spearman": 0.8115463059449796,
|
2281 |
+
"step": 29000
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 1.86,
|
2285 |
+
"eval_avg_sts": 0.7509200158436065,
|
2286 |
+
"eval_sickr_spearman": 0.6902724420880404,
|
2287 |
+
"eval_stsb_spearman": 0.8115675895991724,
|
2288 |
+
"step": 29125
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 1.87,
|
2292 |
+
"eval_avg_sts": 0.7507926487881307,
|
2293 |
+
"eval_sickr_spearman": 0.690199482844956,
|
2294 |
+
"eval_stsb_spearman": 0.8113858147313052,
|
2295 |
+
"step": 29250
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 1.88,
|
2299 |
+
"eval_avg_sts": 0.7510272796849722,
|
2300 |
+
"eval_sickr_spearman": 0.6903056796102356,
|
2301 |
+
"eval_stsb_spearman": 0.8117488797597087,
|
2302 |
+
"step": 29375
|
2303 |
+
},
|
2304 |
+
{
|
2305 |
+
"electra_acc": 0.91,
|
2306 |
+
"electra_fix_acc": 0.9889,
|
2307 |
+
"electra_rep_acc": 0.2628,
|
2308 |
+
"epoch": 1.89,
|
2309 |
+
"learning_rate": 5.606041213362345e-07,
|
2310 |
+
"loss": 0.001,
|
2311 |
+
"neg_sim": NaN,
|
2312 |
+
"pos_sim": 0.8219,
|
2313 |
+
"step": 29500
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 1.89,
|
2317 |
+
"eval_avg_sts": 0.7516619765140928,
|
2318 |
+
"eval_sickr_spearman": 0.6907379114920772,
|
2319 |
+
"eval_stsb_spearman": 0.8125860415361085,
|
2320 |
+
"step": 29500
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.9,
|
2324 |
+
"eval_avg_sts": 0.7516247721458812,
|
2325 |
+
"eval_sickr_spearman": 0.6906019834750073,
|
2326 |
+
"eval_stsb_spearman": 0.812647560816755,
|
2327 |
+
"step": 29625
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 1.9,
|
2331 |
+
"eval_avg_sts": 0.7515302759169064,
|
2332 |
+
"eval_sickr_spearman": 0.6904020780308219,
|
2333 |
+
"eval_stsb_spearman": 0.8126584738029908,
|
2334 |
+
"step": 29750
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.91,
|
2338 |
+
"eval_avg_sts": 0.7512737585285767,
|
2339 |
+
"eval_sickr_spearman": 0.6900924695509518,
|
2340 |
+
"eval_stsb_spearman": 0.8124550475062015,
|
2341 |
+
"step": 29875
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"electra_acc": 0.9095,
|
2345 |
+
"electra_fix_acc": 0.9889,
|
2346 |
+
"electra_rep_acc": 0.2603,
|
2347 |
+
"epoch": 1.92,
|
2348 |
+
"learning_rate": 4.0061436068091647e-07,
|
2349 |
+
"loss": 0.001,
|
2350 |
+
"neg_sim": NaN,
|
2351 |
+
"pos_sim": 0.8219,
|
2352 |
+
"step": 30000
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 1.92,
|
2356 |
+
"eval_avg_sts": 0.751445438691633,
|
2357 |
+
"eval_sickr_spearman": 0.6902850742677187,
|
2358 |
+
"eval_stsb_spearman": 0.8126058031155474,
|
2359 |
+
"step": 30000
|
2360 |
+
},
|
2361 |
+
{
|
2362 |
+
"epoch": 1.93,
|
2363 |
+
"eval_avg_sts": 0.7514690784500874,
|
2364 |
+
"eval_sickr_spearman": 0.6903169188879721,
|
2365 |
+
"eval_stsb_spearman": 0.8126212380122027,
|
2366 |
+
"step": 30125
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 1.94,
|
2370 |
+
"eval_avg_sts": 0.7513646557354139,
|
2371 |
+
"eval_sickr_spearman": 0.6901293094057549,
|
2372 |
+
"eval_stsb_spearman": 0.812600002065073,
|
2373 |
+
"step": 30250
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 1.94,
|
2377 |
+
"eval_avg_sts": 0.7513546637483999,
|
2378 |
+
"eval_sickr_spearman": 0.6900938624528935,
|
2379 |
+
"eval_stsb_spearman": 0.8126154650439061,
|
2380 |
+
"step": 30375
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"electra_acc": 0.9098,
|
2384 |
+
"electra_fix_acc": 0.989,
|
2385 |
+
"electra_rep_acc": 0.2615,
|
2386 |
+
"epoch": 1.95,
|
2387 |
+
"learning_rate": 2.4062460002559835e-07,
|
2388 |
+
"loss": 0.0009,
|
2389 |
+
"neg_sim": NaN,
|
2390 |
+
"pos_sim": 0.8227,
|
2391 |
+
"step": 30500
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.95,
|
2395 |
+
"eval_avg_sts": 0.7513856383156294,
|
2396 |
+
"eval_sickr_spearman": 0.6901277243794074,
|
2397 |
+
"eval_stsb_spearman": 0.8126435522518516,
|
2398 |
+
"step": 30500
|
2399 |
+
},
|
2400 |
+
{
|
2401 |
+
"epoch": 1.96,
|
2402 |
+
"eval_avg_sts": 0.7514646471464337,
|
2403 |
+
"eval_sickr_spearman": 0.6902287818168333,
|
2404 |
+
"eval_stsb_spearman": 0.8127005124760341,
|
2405 |
+
"step": 30625
|
2406 |
+
},
|
2407 |
+
{
|
2408 |
+
"epoch": 1.97,
|
2409 |
+
"eval_avg_sts": 0.7515241048574239,
|
2410 |
+
"eval_sickr_spearman": 0.6903239314287821,
|
2411 |
+
"eval_stsb_spearman": 0.8127242782860657,
|
2412 |
+
"step": 30750
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 1.98,
|
2416 |
+
"eval_avg_sts": 0.7517451176255749,
|
2417 |
+
"eval_sickr_spearman": 0.6905863253359386,
|
2418 |
+
"eval_stsb_spearman": 0.8129039099152112,
|
2419 |
+
"step": 30875
|
2420 |
+
},
|
2421 |
+
{
|
2422 |
+
"electra_acc": 0.9096,
|
2423 |
+
"electra_fix_acc": 0.989,
|
2424 |
+
"electra_rep_acc": 0.2613,
|
2425 |
+
"epoch": 1.98,
|
2426 |
+
"learning_rate": 8.06348393702803e-08,
|
2427 |
+
"loss": 0.001,
|
2428 |
+
"neg_sim": NaN,
|
2429 |
+
"pos_sim": 0.8228,
|
2430 |
+
"step": 31000
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 1.98,
|
2434 |
+
"eval_avg_sts": 0.7517585752042792,
|
2435 |
+
"eval_sickr_spearman": 0.6906067865851512,
|
2436 |
+
"eval_stsb_spearman": 0.8129103638234072,
|
2437 |
+
"step": 31000
|
2438 |
+
},
|
2439 |
+
{
|
2440 |
+
"epoch": 1.99,
|
2441 |
+
"eval_avg_sts": 0.7517603113599198,
|
2442 |
+
"eval_sickr_spearman": 0.6906109172598749,
|
2443 |
+
"eval_stsb_spearman": 0.8129097054599647,
|
2444 |
+
"step": 31125
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 2.0,
|
2448 |
+
"eval_avg_sts": 0.7517610887734341,
|
2449 |
+
"eval_sickr_spearman": 0.6906109172598749,
|
2450 |
+
"eval_stsb_spearman": 0.8129112602869931,
|
2451 |
+
"step": 31250
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 2.0,
|
2455 |
+
"step": 31252,
|
2456 |
+
"train_runtime": 14642.7016,
|
2457 |
+
"train_samples_per_second": 2.134
|
2458 |
+
}
|
2459 |
+
],
|
2460 |
+
"max_steps": 31252,
|
2461 |
+
"num_train_epochs": 2,
|
2462 |
+
"total_flos": 571223595241308000,
|
2463 |
+
"trial_name": null,
|
2464 |
+
"trial_params": null
|
2465 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|