root
commited on
Commit
·
defdc43
1
Parent(s):
8760845
init
Browse files- config.json +24 -0
- eval_results.txt +12 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +2144 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "result/InfoCSE-bert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.2.1",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 2.0
|
| 2 |
+
eval_CR = 86.12
|
| 3 |
+
eval_MPQA = 88.54
|
| 4 |
+
eval_MR = 80.36
|
| 5 |
+
eval_MRPC = 76.47
|
| 6 |
+
eval_SST2 = 85.09
|
| 7 |
+
eval_SUBJ = 94.51
|
| 8 |
+
eval_TREC = 76.56
|
| 9 |
+
eval_avg_sts = 0.7971707208949131
|
| 10 |
+
eval_avg_transfer = 83.95
|
| 11 |
+
eval_sickr_spearman = 0.7394768953031847
|
| 12 |
+
eval_stsb_spearman = 0.8548645464866416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53f47da17ed2ada9ae824d2ce702076569a68b9ae094398ec9c8954df7ca6260
|
| 3 |
+
size 1196096701
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd0be8b7ed404f338b790e3623c72aa0ef134f0538b039ca3dc841ac84e94562
|
| 3 |
+
size 868460138
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5a0f01036523adf2016804a5243334cddb8516f3fe42e9200cb1f26e90f83e3
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "name_or_path": "/mmu_nlp/wuxing/wuxing/nlp/SimCSE/condenser", "special_tokens_map_file": "/mmu_nlp/wuxing/wuxing/nlp/SimCSE/condenser/special_tokens_map.json"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 2.0
|
| 2 |
+
train_runtime = 9641.8618
|
| 3 |
+
train_samples_per_second = 3.241
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8548645464866416,
|
| 3 |
+
"best_model_checkpoint": "result/InfoCSE-bert-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 |
+
"epoch": 0.01,
|
| 12 |
+
"eval_avg_sts": 0.645032772395593,
|
| 13 |
+
"eval_sickr_spearman": 0.6463705264094609,
|
| 14 |
+
"eval_stsb_spearman": 0.643695018381725,
|
| 15 |
+
"step": 125
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_avg_sts": 0.685240727331801,
|
| 20 |
+
"eval_sickr_spearman": 0.669725073110526,
|
| 21 |
+
"eval_stsb_spearman": 0.700756381553076,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.02,
|
| 26 |
+
"eval_avg_sts": 0.7027556246143734,
|
| 27 |
+
"eval_sickr_spearman": 0.6818145493736003,
|
| 28 |
+
"eval_stsb_spearman": 0.7236966998551464,
|
| 29 |
+
"step": 375
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 6.888007167541277e-06,
|
| 34 |
+
"loss": 0.0008,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.03,
|
| 39 |
+
"eval_avg_sts": 0.7085517582757557,
|
| 40 |
+
"eval_sickr_spearman": 0.6868034438177743,
|
| 41 |
+
"eval_stsb_spearman": 0.730300072733737,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"eval_avg_sts": 0.7152446421256347,
|
| 47 |
+
"eval_sickr_spearman": 0.6908805158322469,
|
| 48 |
+
"eval_stsb_spearman": 0.7396087684190223,
|
| 49 |
+
"step": 625
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_avg_sts": 0.744333698385975,
|
| 54 |
+
"eval_sickr_spearman": 0.7107611650906991,
|
| 55 |
+
"eval_stsb_spearman": 0.7779062316812507,
|
| 56 |
+
"step": 750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_avg_sts": 0.749906268768782,
|
| 61 |
+
"eval_sickr_spearman": 0.7164115438638786,
|
| 62 |
+
"eval_stsb_spearman": 0.7834009936736853,
|
| 63 |
+
"step": 875
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 6.776014335082554e-06,
|
| 68 |
+
"loss": 0.0003,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"eval_avg_sts": 0.7527465185576756,
|
| 74 |
+
"eval_sickr_spearman": 0.7194187230938174,
|
| 75 |
+
"eval_stsb_spearman": 0.7860743140215339,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_avg_sts": 0.7563795190354858,
|
| 81 |
+
"eval_sickr_spearman": 0.7197145466475747,
|
| 82 |
+
"eval_stsb_spearman": 0.793044491423397,
|
| 83 |
+
"step": 1125
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_avg_sts": 0.7577088125126856,
|
| 88 |
+
"eval_sickr_spearman": 0.7209790134240346,
|
| 89 |
+
"eval_stsb_spearman": 0.7944386116013368,
|
| 90 |
+
"step": 1250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09,
|
| 94 |
+
"eval_avg_sts": 0.7618327362445115,
|
| 95 |
+
"eval_sickr_spearman": 0.7205304029366025,
|
| 96 |
+
"eval_stsb_spearman": 0.8031350695524205,
|
| 97 |
+
"step": 1375
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1,
|
| 101 |
+
"learning_rate": 6.6640215026238325e-06,
|
| 102 |
+
"loss": 0.0004,
|
| 103 |
+
"step": 1500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.1,
|
| 107 |
+
"eval_avg_sts": 0.7526454517508075,
|
| 108 |
+
"eval_sickr_spearman": 0.7131317881332785,
|
| 109 |
+
"eval_stsb_spearman": 0.7921591153683366,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1,
|
| 114 |
+
"eval_avg_sts": 0.7584465941723788,
|
| 115 |
+
"eval_sickr_spearman": 0.7183862465373038,
|
| 116 |
+
"eval_stsb_spearman": 0.798506941807454,
|
| 117 |
+
"step": 1625
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_avg_sts": 0.7600830398569421,
|
| 122 |
+
"eval_sickr_spearman": 0.7199089285150947,
|
| 123 |
+
"eval_stsb_spearman": 0.8002571511987896,
|
| 124 |
+
"step": 1750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12,
|
| 128 |
+
"eval_avg_sts": 0.753643480678329,
|
| 129 |
+
"eval_sickr_spearman": 0.7154178764373269,
|
| 130 |
+
"eval_stsb_spearman": 0.7918690849193311,
|
| 131 |
+
"step": 1875
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.13,
|
| 135 |
+
"learning_rate": 6.55202867016511e-06,
|
| 136 |
+
"loss": 0.0002,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.13,
|
| 141 |
+
"eval_avg_sts": 0.7563852037282979,
|
| 142 |
+
"eval_sickr_spearman": 0.7193429780468495,
|
| 143 |
+
"eval_stsb_spearman": 0.7934274294097461,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"eval_avg_sts": 0.7664707372188553,
|
| 149 |
+
"eval_sickr_spearman": 0.7240147231282276,
|
| 150 |
+
"eval_stsb_spearman": 0.8089267513094829,
|
| 151 |
+
"step": 2125
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.14,
|
| 155 |
+
"eval_avg_sts": 0.7706419135337745,
|
| 156 |
+
"eval_sickr_spearman": 0.7288192261739805,
|
| 157 |
+
"eval_stsb_spearman": 0.8124646008935686,
|
| 158 |
+
"step": 2250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"eval_avg_sts": 0.7712663844837009,
|
| 163 |
+
"eval_sickr_spearman": 0.7299219242007967,
|
| 164 |
+
"eval_stsb_spearman": 0.8126108447666052,
|
| 165 |
+
"step": 2375
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 6.440035837706387e-06,
|
| 170 |
+
"loss": 0.0002,
|
| 171 |
+
"step": 2500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"eval_avg_sts": 0.7728606127631258,
|
| 176 |
+
"eval_sickr_spearman": 0.7312590620337324,
|
| 177 |
+
"eval_stsb_spearman": 0.8144621634925192,
|
| 178 |
+
"step": 2500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"eval_avg_sts": 0.7729813550763709,
|
| 183 |
+
"eval_sickr_spearman": 0.7313422519014231,
|
| 184 |
+
"eval_stsb_spearman": 0.8146204582513188,
|
| 185 |
+
"step": 2625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.18,
|
| 189 |
+
"eval_avg_sts": 0.7754932728462534,
|
| 190 |
+
"eval_sickr_spearman": 0.7312568526030662,
|
| 191 |
+
"eval_stsb_spearman": 0.8197296930894405,
|
| 192 |
+
"step": 2750
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18,
|
| 196 |
+
"eval_avg_sts": 0.7712885427125948,
|
| 197 |
+
"eval_sickr_spearman": 0.7266254056157947,
|
| 198 |
+
"eval_stsb_spearman": 0.8159516798093949,
|
| 199 |
+
"step": 2875
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.19,
|
| 203 |
+
"learning_rate": 6.328043005247664e-06,
|
| 204 |
+
"loss": 0.0002,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"eval_avg_sts": 0.7716849957034901,
|
| 210 |
+
"eval_sickr_spearman": 0.7262548936993011,
|
| 211 |
+
"eval_stsb_spearman": 0.8171150977076791,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"eval_avg_sts": 0.7711561198226983,
|
| 217 |
+
"eval_sickr_spearman": 0.7262503241591916,
|
| 218 |
+
"eval_stsb_spearman": 0.816061915486205,
|
| 219 |
+
"step": 3125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"eval_avg_sts": 0.7783568816799603,
|
| 224 |
+
"eval_sickr_spearman": 0.7303159233258935,
|
| 225 |
+
"eval_stsb_spearman": 0.8263978400340272,
|
| 226 |
+
"step": 3250
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22,
|
| 230 |
+
"eval_avg_sts": 0.7809228297940308,
|
| 231 |
+
"eval_sickr_spearman": 0.7337628272894983,
|
| 232 |
+
"eval_stsb_spearman": 0.8280828322985634,
|
| 233 |
+
"step": 3375
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 6.2160501727889415e-06,
|
| 238 |
+
"loss": 0.0001,
|
| 239 |
+
"step": 3500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_avg_sts": 0.7797812899347809,
|
| 244 |
+
"eval_sickr_spearman": 0.7324181485736369,
|
| 245 |
+
"eval_stsb_spearman": 0.8271444312959251,
|
| 246 |
+
"step": 3500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23,
|
| 250 |
+
"eval_avg_sts": 0.780044187865891,
|
| 251 |
+
"eval_sickr_spearman": 0.7338939041653229,
|
| 252 |
+
"eval_stsb_spearman": 0.8261944715664592,
|
| 253 |
+
"step": 3625
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.24,
|
| 257 |
+
"eval_avg_sts": 0.7787673562775448,
|
| 258 |
+
"eval_sickr_spearman": 0.7328702653314738,
|
| 259 |
+
"eval_stsb_spearman": 0.8246644472236156,
|
| 260 |
+
"step": 3750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"eval_avg_sts": 0.779541327716536,
|
| 265 |
+
"eval_sickr_spearman": 0.7329598913667574,
|
| 266 |
+
"eval_stsb_spearman": 0.8261227640663145,
|
| 267 |
+
"step": 3875
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 6.104057340330219e-06,
|
| 272 |
+
"loss": 0.0003,
|
| 273 |
+
"step": 4000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_avg_sts": 0.7747719384340315,
|
| 278 |
+
"eval_sickr_spearman": 0.7285930957484098,
|
| 279 |
+
"eval_stsb_spearman": 0.8209507811196531,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.26,
|
| 284 |
+
"eval_avg_sts": 0.7765396311685044,
|
| 285 |
+
"eval_sickr_spearman": 0.7301922912707919,
|
| 286 |
+
"eval_stsb_spearman": 0.8228869710662171,
|
| 287 |
+
"step": 4125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27,
|
| 291 |
+
"eval_avg_sts": 0.7728155845030844,
|
| 292 |
+
"eval_sickr_spearman": 0.7257823156922516,
|
| 293 |
+
"eval_stsb_spearman": 0.8198488533139171,
|
| 294 |
+
"step": 4250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.28,
|
| 298 |
+
"eval_avg_sts": 0.7734186821765212,
|
| 299 |
+
"eval_sickr_spearman": 0.7266760303967105,
|
| 300 |
+
"eval_stsb_spearman": 0.8201613339563318,
|
| 301 |
+
"step": 4375
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.29,
|
| 305 |
+
"learning_rate": 5.992064507871497e-06,
|
| 306 |
+
"loss": 0.0004,
|
| 307 |
+
"step": 4500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.29,
|
| 311 |
+
"eval_avg_sts": 0.7731296739509669,
|
| 312 |
+
"eval_sickr_spearman": 0.7214541370794603,
|
| 313 |
+
"eval_stsb_spearman": 0.8248052108224735,
|
| 314 |
+
"step": 4500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"eval_avg_sts": 0.7728203601265164,
|
| 319 |
+
"eval_sickr_spearman": 0.7219969845879138,
|
| 320 |
+
"eval_stsb_spearman": 0.8236437356651191,
|
| 321 |
+
"step": 4625
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"eval_avg_sts": 0.773140320693449,
|
| 326 |
+
"eval_sickr_spearman": 0.7226297943493609,
|
| 327 |
+
"eval_stsb_spearman": 0.823650847037537,
|
| 328 |
+
"step": 4750
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"eval_avg_sts": 0.7776841987101548,
|
| 333 |
+
"eval_sickr_spearman": 0.7260857761911376,
|
| 334 |
+
"eval_stsb_spearman": 0.8292826212291721,
|
| 335 |
+
"step": 4875
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.32,
|
| 339 |
+
"learning_rate": 5.880071675412773e-06,
|
| 340 |
+
"loss": 0.0001,
|
| 341 |
+
"step": 5000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.32,
|
| 345 |
+
"eval_avg_sts": 0.7787697170418183,
|
| 346 |
+
"eval_sickr_spearman": 0.7268813633553585,
|
| 347 |
+
"eval_stsb_spearman": 0.8306580707282781,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"eval_avg_sts": 0.7794054673251014,
|
| 353 |
+
"eval_sickr_spearman": 0.727022190544775,
|
| 354 |
+
"eval_stsb_spearman": 0.8317887441054277,
|
| 355 |
+
"step": 5125
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.34,
|
| 359 |
+
"eval_avg_sts": 0.7794784586068343,
|
| 360 |
+
"eval_sickr_spearman": 0.7302013691489637,
|
| 361 |
+
"eval_stsb_spearman": 0.8287555480647049,
|
| 362 |
+
"step": 5250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.34,
|
| 366 |
+
"eval_avg_sts": 0.7771717407788259,
|
| 367 |
+
"eval_sickr_spearman": 0.7244288472848269,
|
| 368 |
+
"eval_stsb_spearman": 0.829914634272825,
|
| 369 |
+
"step": 5375
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.35,
|
| 373 |
+
"learning_rate": 5.7680788429540505e-06,
|
| 374 |
+
"loss": 0.0003,
|
| 375 |
+
"step": 5500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.35,
|
| 379 |
+
"eval_avg_sts": 0.778478777290903,
|
| 380 |
+
"eval_sickr_spearman": 0.7256252059594475,
|
| 381 |
+
"eval_stsb_spearman": 0.8313323486223586,
|
| 382 |
+
"step": 5500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36,
|
| 386 |
+
"eval_avg_sts": 0.7793214110914728,
|
| 387 |
+
"eval_sickr_spearman": 0.726303453142855,
|
| 388 |
+
"eval_stsb_spearman": 0.8323393690400904,
|
| 389 |
+
"step": 5625
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.37,
|
| 393 |
+
"eval_avg_sts": 0.7791715295390024,
|
| 394 |
+
"eval_sickr_spearman": 0.7257507592586067,
|
| 395 |
+
"eval_stsb_spearman": 0.8325922998193981,
|
| 396 |
+
"step": 5750
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38,
|
| 400 |
+
"eval_avg_sts": 0.7800081020871235,
|
| 401 |
+
"eval_sickr_spearman": 0.726603503433539,
|
| 402 |
+
"eval_stsb_spearman": 0.8334127007407081,
|
| 403 |
+
"step": 5875
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.38,
|
| 407 |
+
"learning_rate": 5.656086010495328e-06,
|
| 408 |
+
"loss": 0.0001,
|
| 409 |
+
"step": 6000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.38,
|
| 413 |
+
"eval_avg_sts": 0.7802662913925068,
|
| 414 |
+
"eval_sickr_spearman": 0.7272382344390437,
|
| 415 |
+
"eval_stsb_spearman": 0.8332943483459699,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.39,
|
| 420 |
+
"eval_avg_sts": 0.7788831909074992,
|
| 421 |
+
"eval_sickr_spearman": 0.7254892779423776,
|
| 422 |
+
"eval_stsb_spearman": 0.8322771038726209,
|
| 423 |
+
"step": 6125
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4,
|
| 427 |
+
"eval_avg_sts": 0.7790896526834474,
|
| 428 |
+
"eval_sickr_spearman": 0.7246235173389557,
|
| 429 |
+
"eval_stsb_spearman": 0.8335557880279391,
|
| 430 |
+
"step": 6250
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.41,
|
| 434 |
+
"eval_avg_sts": 0.7811606337604482,
|
| 435 |
+
"eval_sickr_spearman": 0.7249414832304759,
|
| 436 |
+
"eval_stsb_spearman": 0.8373797842904204,
|
| 437 |
+
"step": 6375
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.42,
|
| 441 |
+
"learning_rate": 5.544093178036605e-06,
|
| 442 |
+
"loss": 0.0001,
|
| 443 |
+
"step": 6500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.42,
|
| 447 |
+
"eval_avg_sts": 0.7814213566702608,
|
| 448 |
+
"eval_sickr_spearman": 0.7254279422258411,
|
| 449 |
+
"eval_stsb_spearman": 0.8374147711146805,
|
| 450 |
+
"step": 6500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.42,
|
| 454 |
+
"eval_avg_sts": 0.7818500804137162,
|
| 455 |
+
"eval_sickr_spearman": 0.726220023119657,
|
| 456 |
+
"eval_stsb_spearman": 0.8374801377077753,
|
| 457 |
+
"step": 6625
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.43,
|
| 461 |
+
"eval_avg_sts": 0.7832040571269738,
|
| 462 |
+
"eval_sickr_spearman": 0.7301835015792287,
|
| 463 |
+
"eval_stsb_spearman": 0.8362246126747188,
|
| 464 |
+
"step": 6750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"eval_avg_sts": 0.7841900708722672,
|
| 469 |
+
"eval_sickr_spearman": 0.731056755034475,
|
| 470 |
+
"eval_stsb_spearman": 0.8373233867100595,
|
| 471 |
+
"step": 6875
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.45,
|
| 475 |
+
"learning_rate": 5.432100345577883e-06,
|
| 476 |
+
"loss": 0.0001,
|
| 477 |
+
"step": 7000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.45,
|
| 481 |
+
"eval_avg_sts": 0.7862472754964975,
|
| 482 |
+
"eval_sickr_spearman": 0.7333967342343369,
|
| 483 |
+
"eval_stsb_spearman": 0.839097816758658,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"eval_avg_sts": 0.7859634761320248,
|
| 489 |
+
"eval_sickr_spearman": 0.7330241089493801,
|
| 490 |
+
"eval_stsb_spearman": 0.8389028433146695,
|
| 491 |
+
"step": 7125
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"eval_avg_sts": 0.7821803440191185,
|
| 496 |
+
"eval_sickr_spearman": 0.7303841755210372,
|
| 497 |
+
"eval_stsb_spearman": 0.8339765125171998,
|
| 498 |
+
"step": 7250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"eval_avg_sts": 0.7825744125697178,
|
| 503 |
+
"eval_sickr_spearman": 0.7306357624303699,
|
| 504 |
+
"eval_stsb_spearman": 0.8345130627090659,
|
| 505 |
+
"step": 7375
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.48,
|
| 509 |
+
"learning_rate": 5.32010751311916e-06,
|
| 510 |
+
"loss": 0.0001,
|
| 511 |
+
"step": 7500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.48,
|
| 515 |
+
"eval_avg_sts": 0.78116110534451,
|
| 516 |
+
"eval_sickr_spearman": 0.7276775268927966,
|
| 517 |
+
"eval_stsb_spearman": 0.8346446837962234,
|
| 518 |
+
"step": 7500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.49,
|
| 522 |
+
"eval_avg_sts": 0.7799908773501631,
|
| 523 |
+
"eval_sickr_spearman": 0.7237501678215064,
|
| 524 |
+
"eval_stsb_spearman": 0.83623158687882,
|
| 525 |
+
"step": 7625
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5,
|
| 529 |
+
"eval_avg_sts": 0.780269211830304,
|
| 530 |
+
"eval_sickr_spearman": 0.7244608359983847,
|
| 531 |
+
"eval_stsb_spearman": 0.8360775876622232,
|
| 532 |
+
"step": 7750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5,
|
| 536 |
+
"eval_avg_sts": 0.7807594418954099,
|
| 537 |
+
"eval_sickr_spearman": 0.7247573319875622,
|
| 538 |
+
"eval_stsb_spearman": 0.8367615518032576,
|
| 539 |
+
"step": 7875
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.51,
|
| 543 |
+
"learning_rate": 5.2081146806604376e-06,
|
| 544 |
+
"loss": 0.0001,
|
| 545 |
+
"step": 8000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.51,
|
| 549 |
+
"eval_avg_sts": 0.7809657512161441,
|
| 550 |
+
"eval_sickr_spearman": 0.7257775125821077,
|
| 551 |
+
"eval_stsb_spearman": 0.8361539898501805,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.52,
|
| 556 |
+
"eval_avg_sts": 0.7808305047079998,
|
| 557 |
+
"eval_sickr_spearman": 0.7258256397457487,
|
| 558 |
+
"eval_stsb_spearman": 0.8358353696702507,
|
| 559 |
+
"step": 8125
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.53,
|
| 563 |
+
"eval_avg_sts": 0.7808244974473546,
|
| 564 |
+
"eval_sickr_spearman": 0.7260765061885599,
|
| 565 |
+
"eval_stsb_spearman": 0.8355724887061494,
|
| 566 |
+
"step": 8250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.54,
|
| 570 |
+
"eval_avg_sts": 0.7807531331871759,
|
| 571 |
+
"eval_sickr_spearman": 0.725998455648723,
|
| 572 |
+
"eval_stsb_spearman": 0.8355078107256287,
|
| 573 |
+
"step": 8375
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.54,
|
| 577 |
+
"learning_rate": 5.096121848201715e-06,
|
| 578 |
+
"loss": 0.0001,
|
| 579 |
+
"step": 8500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.54,
|
| 583 |
+
"eval_avg_sts": 0.7805553727181309,
|
| 584 |
+
"eval_sickr_spearman": 0.7259074847425994,
|
| 585 |
+
"eval_stsb_spearman": 0.8352032606936624,
|
| 586 |
+
"step": 8500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.55,
|
| 590 |
+
"eval_avg_sts": 0.7840901636781107,
|
| 591 |
+
"eval_sickr_spearman": 0.727197936344937,
|
| 592 |
+
"eval_stsb_spearman": 0.8409823910112844,
|
| 593 |
+
"step": 8625
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.56,
|
| 597 |
+
"eval_avg_sts": 0.7841336470257416,
|
| 598 |
+
"eval_sickr_spearman": 0.7241774524998998,
|
| 599 |
+
"eval_stsb_spearman": 0.8440898415515834,
|
| 600 |
+
"step": 8750
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.57,
|
| 604 |
+
"eval_avg_sts": 0.7848770188208263,
|
| 605 |
+
"eval_sickr_spearman": 0.7246812987539857,
|
| 606 |
+
"eval_stsb_spearman": 0.8450727388876668,
|
| 607 |
+
"step": 8875
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.58,
|
| 611 |
+
"learning_rate": 4.984129015742992e-06,
|
| 612 |
+
"loss": 0.0001,
|
| 613 |
+
"step": 9000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.58,
|
| 617 |
+
"eval_avg_sts": 0.7851602291221325,
|
| 618 |
+
"eval_sickr_spearman": 0.7257603654788943,
|
| 619 |
+
"eval_stsb_spearman": 0.8445600927653706,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.58,
|
| 624 |
+
"eval_avg_sts": 0.7881113225894085,
|
| 625 |
+
"eval_sickr_spearman": 0.7297208179790754,
|
| 626 |
+
"eval_stsb_spearman": 0.8465018271997418,
|
| 627 |
+
"step": 9125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.59,
|
| 631 |
+
"eval_avg_sts": 0.7883865180777926,
|
| 632 |
+
"eval_sickr_spearman": 0.7305029084037921,
|
| 633 |
+
"eval_stsb_spearman": 0.8462701277517931,
|
| 634 |
+
"step": 9250
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6,
|
| 638 |
+
"eval_avg_sts": 0.7905936766250409,
|
| 639 |
+
"eval_sickr_spearman": 0.7318727073857056,
|
| 640 |
+
"eval_stsb_spearman": 0.8493146458643761,
|
| 641 |
+
"step": 9375
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.61,
|
| 645 |
+
"learning_rate": 4.872136183284269e-06,
|
| 646 |
+
"loss": 0.0002,
|
| 647 |
+
"step": 9500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.61,
|
| 651 |
+
"eval_avg_sts": 0.7894195399749903,
|
| 652 |
+
"eval_sickr_spearman": 0.7297918559781024,
|
| 653 |
+
"eval_stsb_spearman": 0.8490472239718782,
|
| 654 |
+
"step": 9500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.62,
|
| 658 |
+
"eval_avg_sts": 0.7888302258840285,
|
| 659 |
+
"eval_sickr_spearman": 0.7290175946229199,
|
| 660 |
+
"eval_stsb_spearman": 0.848642857145137,
|
| 661 |
+
"step": 9625
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.62,
|
| 665 |
+
"eval_avg_sts": 0.7898168606884958,
|
| 666 |
+
"eval_sickr_spearman": 0.7311126152054476,
|
| 667 |
+
"eval_stsb_spearman": 0.848521106171544,
|
| 668 |
+
"step": 9750
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.63,
|
| 672 |
+
"eval_avg_sts": 0.7916780015304804,
|
| 673 |
+
"eval_sickr_spearman": 0.7336695508905056,
|
| 674 |
+
"eval_stsb_spearman": 0.8496864521704552,
|
| 675 |
+
"step": 9875
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.64,
|
| 679 |
+
"learning_rate": 4.760143350825547e-06,
|
| 680 |
+
"loss": 0.0001,
|
| 681 |
+
"step": 10000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.64,
|
| 685 |
+
"eval_avg_sts": 0.7916349913886156,
|
| 686 |
+
"eval_sickr_spearman": 0.7339293030870828,
|
| 687 |
+
"eval_stsb_spearman": 0.8493406796901484,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.65,
|
| 692 |
+
"eval_avg_sts": 0.791507759549186,
|
| 693 |
+
"eval_sickr_spearman": 0.7339989962152694,
|
| 694 |
+
"eval_stsb_spearman": 0.8490165228831026,
|
| 695 |
+
"step": 10125
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.66,
|
| 699 |
+
"eval_avg_sts": 0.789931989918206,
|
| 700 |
+
"eval_sickr_spearman": 0.7311775052234905,
|
| 701 |
+
"eval_stsb_spearman": 0.8486864746129216,
|
| 702 |
+
"step": 10250
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.66,
|
| 706 |
+
"eval_avg_sts": 0.7899616736779131,
|
| 707 |
+
"eval_sickr_spearman": 0.7317643492208613,
|
| 708 |
+
"eval_stsb_spearman": 0.8481589981349649,
|
| 709 |
+
"step": 10375
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.67,
|
| 713 |
+
"learning_rate": 4.648150518366825e-06,
|
| 714 |
+
"loss": 0.0001,
|
| 715 |
+
"step": 10500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.67,
|
| 719 |
+
"eval_avg_sts": 0.7926863693434811,
|
| 720 |
+
"eval_sickr_spearman": 0.7347004424206716,
|
| 721 |
+
"eval_stsb_spearman": 0.8506722962662906,
|
| 722 |
+
"step": 10500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.68,
|
| 726 |
+
"eval_avg_sts": 0.7925310701894714,
|
| 727 |
+
"eval_sickr_spearman": 0.7345030826248625,
|
| 728 |
+
"eval_stsb_spearman": 0.8505590577540805,
|
| 729 |
+
"step": 10625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.69,
|
| 733 |
+
"eval_avg_sts": 0.7921847237714013,
|
| 734 |
+
"eval_sickr_spearman": 0.734286503995874,
|
| 735 |
+
"eval_stsb_spearman": 0.8500829435469286,
|
| 736 |
+
"step": 10750
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7,
|
| 740 |
+
"eval_avg_sts": 0.792045037000692,
|
| 741 |
+
"eval_sickr_spearman": 0.7345833425953655,
|
| 742 |
+
"eval_stsb_spearman": 0.8495067314060183,
|
| 743 |
+
"step": 10875
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7,
|
| 747 |
+
"learning_rate": 4.536157685908102e-06,
|
| 748 |
+
"loss": 0.0001,
|
| 749 |
+
"step": 11000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.7,
|
| 753 |
+
"eval_avg_sts": 0.7924996456713199,
|
| 754 |
+
"eval_sickr_spearman": 0.7354074602338407,
|
| 755 |
+
"eval_stsb_spearman": 0.8495918311087991,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.71,
|
| 760 |
+
"eval_avg_sts": 0.7924266596358673,
|
| 761 |
+
"eval_sickr_spearman": 0.7356516503535521,
|
| 762 |
+
"eval_stsb_spearman": 0.8492016689181826,
|
| 763 |
+
"step": 11125
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.72,
|
| 767 |
+
"eval_avg_sts": 0.7926706111519558,
|
| 768 |
+
"eval_sickr_spearman": 0.7358917097985398,
|
| 769 |
+
"eval_stsb_spearman": 0.8494495125053718,
|
| 770 |
+
"step": 11250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.73,
|
| 774 |
+
"eval_avg_sts": 0.7930288164708986,
|
| 775 |
+
"eval_sickr_spearman": 0.7354914185991545,
|
| 776 |
+
"eval_stsb_spearman": 0.8505662143426428,
|
| 777 |
+
"step": 11375
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.74,
|
| 781 |
+
"learning_rate": 4.424164853449379e-06,
|
| 782 |
+
"loss": 0.0002,
|
| 783 |
+
"step": 11500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.74,
|
| 787 |
+
"eval_avg_sts": 0.7926251189281965,
|
| 788 |
+
"eval_sickr_spearman": 0.7351442017668584,
|
| 789 |
+
"eval_stsb_spearman": 0.8501060360895348,
|
| 790 |
+
"step": 11500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.74,
|
| 794 |
+
"eval_avg_sts": 0.7932695687388167,
|
| 795 |
+
"eval_sickr_spearman": 0.7365684199867013,
|
| 796 |
+
"eval_stsb_spearman": 0.8499707174909322,
|
| 797 |
+
"step": 11625
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.75,
|
| 801 |
+
"eval_avg_sts": 0.7935921856407616,
|
| 802 |
+
"eval_sickr_spearman": 0.7367729844477262,
|
| 803 |
+
"eval_stsb_spearman": 0.850411386833797,
|
| 804 |
+
"step": 11750
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.76,
|
| 808 |
+
"eval_avg_sts": 0.794782209944985,
|
| 809 |
+
"eval_sickr_spearman": 0.7389587838119719,
|
| 810 |
+
"eval_stsb_spearman": 0.8506056360779983,
|
| 811 |
+
"step": 11875
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.77,
|
| 815 |
+
"learning_rate": 4.312172020990656e-06,
|
| 816 |
+
"loss": 0.0002,
|
| 817 |
+
"step": 12000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.77,
|
| 821 |
+
"eval_avg_sts": 0.7971707208949131,
|
| 822 |
+
"eval_sickr_spearman": 0.7394768953031847,
|
| 823 |
+
"eval_stsb_spearman": 0.8548645464866416,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.78,
|
| 828 |
+
"eval_avg_sts": 0.797638118412404,
|
| 829 |
+
"eval_sickr_spearman": 0.7421029957743136,
|
| 830 |
+
"eval_stsb_spearman": 0.8531732410504944,
|
| 831 |
+
"step": 12125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.78,
|
| 835 |
+
"eval_avg_sts": 0.7969091025343611,
|
| 836 |
+
"eval_sickr_spearman": 0.741429359576644,
|
| 837 |
+
"eval_stsb_spearman": 0.8523888454920783,
|
| 838 |
+
"step": 12250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.79,
|
| 842 |
+
"eval_avg_sts": 0.7919648350492454,
|
| 843 |
+
"eval_sickr_spearman": 0.7347034683800623,
|
| 844 |
+
"eval_stsb_spearman": 0.8492262017184287,
|
| 845 |
+
"step": 12375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8,
|
| 849 |
+
"learning_rate": 4.2001791885319345e-06,
|
| 850 |
+
"loss": 0.0005,
|
| 851 |
+
"step": 12500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8,
|
| 855 |
+
"eval_avg_sts": 0.7921636059370547,
|
| 856 |
+
"eval_sickr_spearman": 0.7353516480939697,
|
| 857 |
+
"eval_stsb_spearman": 0.8489755637801396,
|
| 858 |
+
"step": 12500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.81,
|
| 862 |
+
"eval_avg_sts": 0.7924202367929077,
|
| 863 |
+
"eval_sickr_spearman": 0.736975675695795,
|
| 864 |
+
"eval_stsb_spearman": 0.8478647978900204,
|
| 865 |
+
"step": 12625
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.82,
|
| 869 |
+
"eval_avg_sts": 0.7890475112371416,
|
| 870 |
+
"eval_sickr_spearman": 0.7355575093947334,
|
| 871 |
+
"eval_stsb_spearman": 0.8425375130795496,
|
| 872 |
+
"step": 12750
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.82,
|
| 876 |
+
"eval_avg_sts": 0.7892144058224184,
|
| 877 |
+
"eval_sickr_spearman": 0.7356575101479275,
|
| 878 |
+
"eval_stsb_spearman": 0.8427713014969095,
|
| 879 |
+
"step": 12875
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.83,
|
| 883 |
+
"learning_rate": 4.088186356073212e-06,
|
| 884 |
+
"loss": 0.0002,
|
| 885 |
+
"step": 13000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.83,
|
| 889 |
+
"eval_avg_sts": 0.7908518455947956,
|
| 890 |
+
"eval_sickr_spearman": 0.73698621219475,
|
| 891 |
+
"eval_stsb_spearman": 0.8447174789948412,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.84,
|
| 896 |
+
"eval_avg_sts": 0.7910358332545967,
|
| 897 |
+
"eval_sickr_spearman": 0.7372511340625426,
|
| 898 |
+
"eval_stsb_spearman": 0.8448205324466508,
|
| 899 |
+
"step": 13125
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.85,
|
| 903 |
+
"eval_avg_sts": 0.7910819619646265,
|
| 904 |
+
"eval_sickr_spearman": 0.7366442130647706,
|
| 905 |
+
"eval_stsb_spearman": 0.8455197108644826,
|
| 906 |
+
"step": 13250
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.86,
|
| 910 |
+
"eval_avg_sts": 0.7913313391681369,
|
| 911 |
+
"eval_sickr_spearman": 0.7369983463756739,
|
| 912 |
+
"eval_stsb_spearman": 0.8456643319606,
|
| 913 |
+
"step": 13375
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.86,
|
| 917 |
+
"learning_rate": 3.976193523614489e-06,
|
| 918 |
+
"loss": 0.0002,
|
| 919 |
+
"step": 13500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.86,
|
| 923 |
+
"eval_avg_sts": 0.7912515138401426,
|
| 924 |
+
"eval_sickr_spearman": 0.7371570411348254,
|
| 925 |
+
"eval_stsb_spearman": 0.8453459865454599,
|
| 926 |
+
"step": 13500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.87,
|
| 930 |
+
"eval_avg_sts": 0.7912798783058242,
|
| 931 |
+
"eval_sickr_spearman": 0.7375416261640404,
|
| 932 |
+
"eval_stsb_spearman": 0.8450181304476081,
|
| 933 |
+
"step": 13625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.88,
|
| 937 |
+
"eval_avg_sts": 0.7915843291718891,
|
| 938 |
+
"eval_sickr_spearman": 0.7376919154804402,
|
| 939 |
+
"eval_stsb_spearman": 0.845476742863338,
|
| 940 |
+
"step": 13750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.89,
|
| 944 |
+
"eval_avg_sts": 0.7917255539871094,
|
| 945 |
+
"eval_sickr_spearman": 0.7381062797925467,
|
| 946 |
+
"eval_stsb_spearman": 0.8453448281816721,
|
| 947 |
+
"step": 13875
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9,
|
| 951 |
+
"learning_rate": 3.864200691155766e-06,
|
| 952 |
+
"loss": 0.0001,
|
| 953 |
+
"step": 14000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.9,
|
| 957 |
+
"eval_avg_sts": 0.7916416194141285,
|
| 958 |
+
"eval_sickr_spearman": 0.7380577683800943,
|
| 959 |
+
"eval_stsb_spearman": 0.8452254704481627,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9,
|
| 964 |
+
"eval_avg_sts": 0.7924269371428458,
|
| 965 |
+
"eval_sickr_spearman": 0.738714977941072,
|
| 966 |
+
"eval_stsb_spearman": 0.8461388963446196,
|
| 967 |
+
"step": 14125
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.91,
|
| 971 |
+
"eval_avg_sts": 0.7923356777507629,
|
| 972 |
+
"eval_sickr_spearman": 0.7386597902055195,
|
| 973 |
+
"eval_stsb_spearman": 0.8460115652960062,
|
| 974 |
+
"step": 14250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.92,
|
| 978 |
+
"eval_avg_sts": 0.7922805942330418,
|
| 979 |
+
"eval_sickr_spearman": 0.7387613759850612,
|
| 980 |
+
"eval_stsb_spearman": 0.8457998124810223,
|
| 981 |
+
"step": 14375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.93,
|
| 985 |
+
"learning_rate": 3.7522078586970435e-06,
|
| 986 |
+
"loss": 0.0001,
|
| 987 |
+
"step": 14500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.93,
|
| 991 |
+
"eval_avg_sts": 0.7934966210957259,
|
| 992 |
+
"eval_sickr_spearman": 0.7397510568301936,
|
| 993 |
+
"eval_stsb_spearman": 0.8472421853612582,
|
| 994 |
+
"step": 14500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.94,
|
| 998 |
+
"eval_avg_sts": 0.7930449265696451,
|
| 999 |
+
"eval_sickr_spearman": 0.7393639741837038,
|
| 1000 |
+
"eval_stsb_spearman": 0.8467258789555864,
|
| 1001 |
+
"step": 14625
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.94,
|
| 1005 |
+
"eval_avg_sts": 0.7924737714972381,
|
| 1006 |
+
"eval_sickr_spearman": 0.7393996612920722,
|
| 1007 |
+
"eval_stsb_spearman": 0.845547881702404,
|
| 1008 |
+
"step": 14750
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.95,
|
| 1012 |
+
"eval_avg_sts": 0.792308440851152,
|
| 1013 |
+
"eval_sickr_spearman": 0.739175211955052,
|
| 1014 |
+
"eval_stsb_spearman": 0.845441669747252,
|
| 1015 |
+
"step": 14875
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.96,
|
| 1019 |
+
"learning_rate": 3.6402150262383203e-06,
|
| 1020 |
+
"loss": 0.0001,
|
| 1021 |
+
"step": 15000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.96,
|
| 1025 |
+
"eval_avg_sts": 0.7932488441451628,
|
| 1026 |
+
"eval_sickr_spearman": 0.7404715713828667,
|
| 1027 |
+
"eval_stsb_spearman": 0.8460261169074589,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.97,
|
| 1032 |
+
"eval_avg_sts": 0.7931158785146848,
|
| 1033 |
+
"eval_sickr_spearman": 0.7406130710077032,
|
| 1034 |
+
"eval_stsb_spearman": 0.8456186860216665,
|
| 1035 |
+
"step": 15125
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.98,
|
| 1039 |
+
"eval_avg_sts": 0.7945903311020877,
|
| 1040 |
+
"eval_sickr_spearman": 0.7431428210893474,
|
| 1041 |
+
"eval_stsb_spearman": 0.8460378411148278,
|
| 1042 |
+
"step": 15250
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.98,
|
| 1046 |
+
"eval_avg_sts": 0.7948596387785098,
|
| 1047 |
+
"eval_sickr_spearman": 0.7440196288461001,
|
| 1048 |
+
"eval_stsb_spearman": 0.8456996487109196,
|
| 1049 |
+
"step": 15375
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.99,
|
| 1053 |
+
"learning_rate": 3.5282221937795976e-06,
|
| 1054 |
+
"loss": 0.0002,
|
| 1055 |
+
"step": 15500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.99,
|
| 1059 |
+
"eval_avg_sts": 0.7948372805541641,
|
| 1060 |
+
"eval_sickr_spearman": 0.744097679385937,
|
| 1061 |
+
"eval_stsb_spearman": 0.8455768817223914,
|
| 1062 |
+
"step": 15500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.0,
|
| 1066 |
+
"eval_avg_sts": 0.7937246352478757,
|
| 1067 |
+
"eval_sickr_spearman": 0.7439027691763012,
|
| 1068 |
+
"eval_stsb_spearman": 0.8435465013194503,
|
| 1069 |
+
"step": 15625
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.01,
|
| 1073 |
+
"eval_avg_sts": 0.7937099307469273,
|
| 1074 |
+
"eval_sickr_spearman": 0.7440485435691657,
|
| 1075 |
+
"eval_stsb_spearman": 0.8433713179246888,
|
| 1076 |
+
"step": 15750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.02,
|
| 1080 |
+
"eval_avg_sts": 0.7935877720189825,
|
| 1081 |
+
"eval_sickr_spearman": 0.7440728953375949,
|
| 1082 |
+
"eval_stsb_spearman": 0.84310264870037,
|
| 1083 |
+
"step": 15875
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.02,
|
| 1087 |
+
"learning_rate": 3.4162293613208757e-06,
|
| 1088 |
+
"loss": 0.0001,
|
| 1089 |
+
"step": 16000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.02,
|
| 1093 |
+
"eval_avg_sts": 0.7935863758797379,
|
| 1094 |
+
"eval_sickr_spearman": 0.744390621073608,
|
| 1095 |
+
"eval_stsb_spearman": 0.8427821306858677,
|
| 1096 |
+
"step": 16000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.03,
|
| 1100 |
+
"eval_avg_sts": 0.7937197747425322,
|
| 1101 |
+
"eval_sickr_spearman": 0.7444404293257993,
|
| 1102 |
+
"eval_stsb_spearman": 0.8429991201592651,
|
| 1103 |
+
"step": 16125
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.04,
|
| 1107 |
+
"eval_avg_sts": 0.7924446512199308,
|
| 1108 |
+
"eval_sickr_spearman": 0.7440353830473717,
|
| 1109 |
+
"eval_stsb_spearman": 0.8408539193924898,
|
| 1110 |
+
"step": 16250
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.05,
|
| 1114 |
+
"eval_avg_sts": 0.7905555822474897,
|
| 1115 |
+
"eval_sickr_spearman": 0.7383070017654566,
|
| 1116 |
+
"eval_stsb_spearman": 0.8428041627295226,
|
| 1117 |
+
"step": 16375
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.06,
|
| 1121 |
+
"learning_rate": 3.304236528862153e-06,
|
| 1122 |
+
"loss": 0.0001,
|
| 1123 |
+
"step": 16500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.06,
|
| 1127 |
+
"eval_avg_sts": 0.7899406430528368,
|
| 1128 |
+
"eval_sickr_spearman": 0.737816219970962,
|
| 1129 |
+
"eval_stsb_spearman": 0.8420650661347118,
|
| 1130 |
+
"step": 16500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.06,
|
| 1134 |
+
"eval_avg_sts": 0.7921524290697161,
|
| 1135 |
+
"eval_sickr_spearman": 0.7417105816755641,
|
| 1136 |
+
"eval_stsb_spearman": 0.842594276463868,
|
| 1137 |
+
"step": 16625
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.07,
|
| 1141 |
+
"eval_avg_sts": 0.7909061020892134,
|
| 1142 |
+
"eval_sickr_spearman": 0.7410022670226564,
|
| 1143 |
+
"eval_stsb_spearman": 0.8408099371557706,
|
| 1144 |
+
"step": 16750
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.08,
|
| 1148 |
+
"eval_avg_sts": 0.7911860344103485,
|
| 1149 |
+
"eval_sickr_spearman": 0.7404902554813262,
|
| 1150 |
+
"eval_stsb_spearman": 0.841881813339371,
|
| 1151 |
+
"step": 16875
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.09,
|
| 1155 |
+
"learning_rate": 3.19224369640343e-06,
|
| 1156 |
+
"loss": 0.0002,
|
| 1157 |
+
"step": 17000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.09,
|
| 1161 |
+
"eval_avg_sts": 0.7912332320403954,
|
| 1162 |
+
"eval_sickr_spearman": 0.7405556258103834,
|
| 1163 |
+
"eval_stsb_spearman": 0.8419108382704075,
|
| 1164 |
+
"step": 17000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.1,
|
| 1168 |
+
"eval_avg_sts": 0.791745368257589,
|
| 1169 |
+
"eval_sickr_spearman": 0.7407413620796446,
|
| 1170 |
+
"eval_stsb_spearman": 0.8427493744355335,
|
| 1171 |
+
"step": 17125
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.1,
|
| 1175 |
+
"eval_avg_sts": 0.7936116457907827,
|
| 1176 |
+
"eval_sickr_spearman": 0.7417212926111849,
|
| 1177 |
+
"eval_stsb_spearman": 0.8455019989703806,
|
| 1178 |
+
"step": 17250
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.11,
|
| 1182 |
+
"eval_avg_sts": 0.7936037695250758,
|
| 1183 |
+
"eval_sickr_spearman": 0.7418167304097425,
|
| 1184 |
+
"eval_stsb_spearman": 0.8453908086404092,
|
| 1185 |
+
"step": 17375
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.12,
|
| 1189 |
+
"learning_rate": 3.0802508639447074e-06,
|
| 1190 |
+
"loss": 0.0002,
|
| 1191 |
+
"step": 17500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.12,
|
| 1195 |
+
"eval_avg_sts": 0.792413452164604,
|
| 1196 |
+
"eval_sickr_spearman": 0.7425937295377067,
|
| 1197 |
+
"eval_stsb_spearman": 0.8422331747915013,
|
| 1198 |
+
"step": 17500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.13,
|
| 1202 |
+
"eval_avg_sts": 0.7927184217670188,
|
| 1203 |
+
"eval_sickr_spearman": 0.7428243748868126,
|
| 1204 |
+
"eval_stsb_spearman": 0.8426124686472249,
|
| 1205 |
+
"step": 17625
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.14,
|
| 1209 |
+
"eval_avg_sts": 0.7926960182448954,
|
| 1210 |
+
"eval_sickr_spearman": 0.742725526880053,
|
| 1211 |
+
"eval_stsb_spearman": 0.842666509609738,
|
| 1212 |
+
"step": 17750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 1.14,
|
| 1216 |
+
"eval_avg_sts": 0.7927521207425385,
|
| 1217 |
+
"eval_sickr_spearman": 0.7428051144151359,
|
| 1218 |
+
"eval_stsb_spearman": 0.8426991270699412,
|
| 1219 |
+
"step": 17875
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.15,
|
| 1223 |
+
"learning_rate": 2.9682580314859847e-06,
|
| 1224 |
+
"loss": 0.0,
|
| 1225 |
+
"step": 18000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.15,
|
| 1229 |
+
"eval_avg_sts": 0.7928433137943678,
|
| 1230 |
+
"eval_sickr_spearman": 0.7426588116801555,
|
| 1231 |
+
"eval_stsb_spearman": 0.8430278159085801,
|
| 1232 |
+
"step": 18000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.16,
|
| 1236 |
+
"eval_avg_sts": 0.792833492411573,
|
| 1237 |
+
"eval_sickr_spearman": 0.7426310977346257,
|
| 1238 |
+
"eval_stsb_spearman": 0.8430358870885203,
|
| 1239 |
+
"step": 18125
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.17,
|
| 1243 |
+
"eval_avg_sts": 0.7928841848486375,
|
| 1244 |
+
"eval_sickr_spearman": 0.742908285221025,
|
| 1245 |
+
"eval_stsb_spearman": 0.84286008447625,
|
| 1246 |
+
"step": 18250
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.18,
|
| 1250 |
+
"eval_avg_sts": 0.7925150543842555,
|
| 1251 |
+
"eval_sickr_spearman": 0.743895084200071,
|
| 1252 |
+
"eval_stsb_spearman": 0.84113502456844,
|
| 1253 |
+
"step": 18375
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.18,
|
| 1257 |
+
"learning_rate": 2.8562651990272623e-06,
|
| 1258 |
+
"loss": 0.0001,
|
| 1259 |
+
"step": 18500
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.18,
|
| 1263 |
+
"eval_avg_sts": 0.7919487675309846,
|
| 1264 |
+
"eval_sickr_spearman": 0.7431525714029392,
|
| 1265 |
+
"eval_stsb_spearman": 0.84074496365903,
|
| 1266 |
+
"step": 18500
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.19,
|
| 1270 |
+
"eval_avg_sts": 0.7919787220051326,
|
| 1271 |
+
"eval_sickr_spearman": 0.7432353770218185,
|
| 1272 |
+
"eval_stsb_spearman": 0.8407220669884469,
|
| 1273 |
+
"step": 18625
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.2,
|
| 1277 |
+
"eval_avg_sts": 0.7920516311468476,
|
| 1278 |
+
"eval_sickr_spearman": 0.7433836010008565,
|
| 1279 |
+
"eval_stsb_spearman": 0.8407196612928387,
|
| 1280 |
+
"step": 18750
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.21,
|
| 1284 |
+
"eval_avg_sts": 0.79208040900112,
|
| 1285 |
+
"eval_sickr_spearman": 0.7434916709790923,
|
| 1286 |
+
"eval_stsb_spearman": 0.8406691470231478,
|
| 1287 |
+
"step": 18875
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.22,
|
| 1291 |
+
"learning_rate": 2.7442723665685396e-06,
|
| 1292 |
+
"loss": 0.0001,
|
| 1293 |
+
"step": 19000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.22,
|
| 1297 |
+
"eval_avg_sts": 0.7915679899923007,
|
| 1298 |
+
"eval_sickr_spearman": 0.7422913257230525,
|
| 1299 |
+
"eval_stsb_spearman": 0.8408446542615489,
|
| 1300 |
+
"step": 19000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.22,
|
| 1304 |
+
"eval_avg_sts": 0.7924488788916606,
|
| 1305 |
+
"eval_sickr_spearman": 0.7431180370410052,
|
| 1306 |
+
"eval_stsb_spearman": 0.8417797207423161,
|
| 1307 |
+
"step": 19125
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.23,
|
| 1311 |
+
"eval_avg_sts": 0.7925131080137356,
|
| 1312 |
+
"eval_sickr_spearman": 0.7439811559338482,
|
| 1313 |
+
"eval_stsb_spearman": 0.8410450600936231,
|
| 1314 |
+
"step": 19250
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.24,
|
| 1318 |
+
"eval_avg_sts": 0.7923092664958495,
|
| 1319 |
+
"eval_sickr_spearman": 0.7438394641846057,
|
| 1320 |
+
"eval_stsb_spearman": 0.8407790688070933,
|
| 1321 |
+
"step": 19375
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.25,
|
| 1325 |
+
"learning_rate": 2.632279534109817e-06,
|
| 1326 |
+
"loss": 0.0002,
|
| 1327 |
+
"step": 19500
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.25,
|
| 1331 |
+
"eval_avg_sts": 0.7915084313605771,
|
| 1332 |
+
"eval_sickr_spearman": 0.7429506966835948,
|
| 1333 |
+
"eval_stsb_spearman": 0.8400661660375595,
|
| 1334 |
+
"step": 19500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.26,
|
| 1338 |
+
"eval_avg_sts": 0.7914848286255316,
|
| 1339 |
+
"eval_sickr_spearman": 0.7429546352339128,
|
| 1340 |
+
"eval_stsb_spearman": 0.8400150220171504,
|
| 1341 |
+
"step": 19625
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.26,
|
| 1345 |
+
"eval_avg_sts": 0.7919444499131418,
|
| 1346 |
+
"eval_sickr_spearman": 0.7435056960607123,
|
| 1347 |
+
"eval_stsb_spearman": 0.8403832037655713,
|
| 1348 |
+
"step": 19750
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.27,
|
| 1352 |
+
"eval_avg_sts": 0.7918604283998938,
|
| 1353 |
+
"eval_sickr_spearman": 0.7430511777478034,
|
| 1354 |
+
"eval_stsb_spearman": 0.8406696790519842,
|
| 1355 |
+
"step": 19875
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.28,
|
| 1359 |
+
"learning_rate": 2.5202867016510945e-06,
|
| 1360 |
+
"loss": 0.0001,
|
| 1361 |
+
"step": 20000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.28,
|
| 1365 |
+
"eval_avg_sts": 0.7901084692338984,
|
| 1366 |
+
"eval_sickr_spearman": 0.7411617302794309,
|
| 1367 |
+
"eval_stsb_spearman": 0.839055208188366,
|
| 1368 |
+
"step": 20000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.29,
|
| 1372 |
+
"eval_avg_sts": 0.789757862825201,
|
| 1373 |
+
"eval_sickr_spearman": 0.7407969340640084,
|
| 1374 |
+
"eval_stsb_spearman": 0.8387187915863936,
|
| 1375 |
+
"step": 20125
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.3,
|
| 1379 |
+
"eval_avg_sts": 0.7898529068915039,
|
| 1380 |
+
"eval_sickr_spearman": 0.7409771947877056,
|
| 1381 |
+
"eval_stsb_spearman": 0.8387286189953022,
|
| 1382 |
+
"step": 20250
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3,
|
| 1386 |
+
"eval_avg_sts": 0.789768082574833,
|
| 1387 |
+
"eval_sickr_spearman": 0.74083372588771,
|
| 1388 |
+
"eval_stsb_spearman": 0.838702439261956,
|
| 1389 |
+
"step": 20375
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.31,
|
| 1393 |
+
"learning_rate": 2.4082938691923718e-06,
|
| 1394 |
+
"loss": 0.0,
|
| 1395 |
+
"step": 20500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.31,
|
| 1399 |
+
"eval_avg_sts": 0.7897954058339804,
|
| 1400 |
+
"eval_sickr_spearman": 0.7408093260881794,
|
| 1401 |
+
"eval_stsb_spearman": 0.8387814855797816,
|
| 1402 |
+
"step": 20500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.32,
|
| 1406 |
+
"eval_avg_sts": 0.7899947832336973,
|
| 1407 |
+
"eval_sickr_spearman": 0.7409338707342086,
|
| 1408 |
+
"eval_stsb_spearman": 0.8390556957331861,
|
| 1409 |
+
"step": 20625
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.33,
|
| 1413 |
+
"eval_avg_sts": 0.790202509592782,
|
| 1414 |
+
"eval_sickr_spearman": 0.7411228731183674,
|
| 1415 |
+
"eval_stsb_spearman": 0.8392821460671965,
|
| 1416 |
+
"step": 20750
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.34,
|
| 1420 |
+
"eval_avg_sts": 0.7901906011266497,
|
| 1421 |
+
"eval_sickr_spearman": 0.7410648995789316,
|
| 1422 |
+
"eval_stsb_spearman": 0.839316302674368,
|
| 1423 |
+
"step": 20875
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.34,
|
| 1427 |
+
"learning_rate": 2.296301036733649e-06,
|
| 1428 |
+
"loss": 0.0,
|
| 1429 |
+
"step": 21000
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.34,
|
| 1433 |
+
"eval_avg_sts": 0.7902077356957227,
|
| 1434 |
+
"eval_sickr_spearman": 0.7411439107407973,
|
| 1435 |
+
"eval_stsb_spearman": 0.839271560650648,
|
| 1436 |
+
"step": 21000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.35,
|
| 1440 |
+
"eval_avg_sts": 0.7901431265829444,
|
| 1441 |
+
"eval_sickr_spearman": 0.7410307494658092,
|
| 1442 |
+
"eval_stsb_spearman": 0.8392555037000796,
|
| 1443 |
+
"step": 21125
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.36,
|
| 1447 |
+
"eval_avg_sts": 0.7921962350985728,
|
| 1448 |
+
"eval_sickr_spearman": 0.7434804797324572,
|
| 1449 |
+
"eval_stsb_spearman": 0.8409119904646885,
|
| 1450 |
+
"step": 21250
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.37,
|
| 1454 |
+
"eval_avg_sts": 0.7922085580785473,
|
| 1455 |
+
"eval_sickr_spearman": 0.7434956095294102,
|
| 1456 |
+
"eval_stsb_spearman": 0.8409215066276844,
|
| 1457 |
+
"step": 21375
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.38,
|
| 1461 |
+
"learning_rate": 2.1843082042749267e-06,
|
| 1462 |
+
"loss": 0.0001,
|
| 1463 |
+
"step": 21500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.38,
|
| 1467 |
+
"eval_avg_sts": 0.7922422656604595,
|
| 1468 |
+
"eval_sickr_spearman": 0.7434714018542854,
|
| 1469 |
+
"eval_stsb_spearman": 0.8410131294666336,
|
| 1470 |
+
"step": 21500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.38,
|
| 1474 |
+
"eval_avg_sts": 0.7922953172658802,
|
| 1475 |
+
"eval_sickr_spearman": 0.7435230833194328,
|
| 1476 |
+
"eval_stsb_spearman": 0.8410675512123275,
|
| 1477 |
+
"step": 21625
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.39,
|
| 1481 |
+
"eval_avg_sts": 0.7920827130593174,
|
| 1482 |
+
"eval_sickr_spearman": 0.7432143393993886,
|
| 1483 |
+
"eval_stsb_spearman": 0.8409510867192462,
|
| 1484 |
+
"step": 21750
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.4,
|
| 1488 |
+
"eval_avg_sts": 0.7893982619162593,
|
| 1489 |
+
"eval_sickr_spearman": 0.7409595673734778,
|
| 1490 |
+
"eval_stsb_spearman": 0.8378369564590408,
|
| 1491 |
+
"step": 21875
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.41,
|
| 1495 |
+
"learning_rate": 2.072315371816204e-06,
|
| 1496 |
+
"loss": 0.0002,
|
| 1497 |
+
"step": 22000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.41,
|
| 1501 |
+
"eval_avg_sts": 0.7906089294600861,
|
| 1502 |
+
"eval_sickr_spearman": 0.7422200475685182,
|
| 1503 |
+
"eval_stsb_spearman": 0.838997811351654,
|
| 1504 |
+
"step": 22000
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.42,
|
| 1508 |
+
"eval_avg_sts": 0.7914097742253603,
|
| 1509 |
+
"eval_sickr_spearman": 0.7423016043787602,
|
| 1510 |
+
"eval_stsb_spearman": 0.8405179440719603,
|
| 1511 |
+
"step": 22125
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.42,
|
| 1515 |
+
"eval_avg_sts": 0.791727396078017,
|
| 1516 |
+
"eval_sickr_spearman": 0.7433686633283093,
|
| 1517 |
+
"eval_stsb_spearman": 0.8400861288277247,
|
| 1518 |
+
"step": 22250
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.43,
|
| 1522 |
+
"eval_avg_sts": 0.7914842385018235,
|
| 1523 |
+
"eval_sickr_spearman": 0.7423251876495663,
|
| 1524 |
+
"eval_stsb_spearman": 0.8406432893540806,
|
| 1525 |
+
"step": 22375
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 1.44,
|
| 1529 |
+
"learning_rate": 1.9603225393574807e-06,
|
| 1530 |
+
"loss": 0.0001,
|
| 1531 |
+
"step": 22500
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 1.44,
|
| 1535 |
+
"eval_avg_sts": 0.7915202710875588,
|
| 1536 |
+
"eval_sickr_spearman": 0.7422767242682152,
|
| 1537 |
+
"eval_stsb_spearman": 0.8407638179069024,
|
| 1538 |
+
"step": 22500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.45,
|
| 1542 |
+
"eval_avg_sts": 0.7918702583757414,
|
| 1543 |
+
"eval_sickr_spearman": 0.7429271614438903,
|
| 1544 |
+
"eval_stsb_spearman": 0.8408133553075926,
|
| 1545 |
+
"step": 22625
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.46,
|
| 1549 |
+
"eval_avg_sts": 0.7916045718347005,
|
| 1550 |
+
"eval_sickr_spearman": 0.7425266300889978,
|
| 1551 |
+
"eval_stsb_spearman": 0.840682513580403,
|
| 1552 |
+
"step": 22750
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 1.46,
|
| 1556 |
+
"eval_avg_sts": 0.7915999641875153,
|
| 1557 |
+
"eval_sickr_spearman": 0.7422474733274393,
|
| 1558 |
+
"eval_stsb_spearman": 0.8409524550475914,
|
| 1559 |
+
"step": 22875
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 1.47,
|
| 1563 |
+
"learning_rate": 1.8483297068987584e-06,
|
| 1564 |
+
"loss": 0.0002,
|
| 1565 |
+
"step": 23000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.47,
|
| 1569 |
+
"eval_avg_sts": 0.792815682844469,
|
| 1570 |
+
"eval_sickr_spearman": 0.7426967562502915,
|
| 1571 |
+
"eval_stsb_spearman": 0.8429346094386464,
|
| 1572 |
+
"step": 23000
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.48,
|
| 1576 |
+
"eval_avg_sts": 0.7927916857497739,
|
| 1577 |
+
"eval_sickr_spearman": 0.7425698100491905,
|
| 1578 |
+
"eval_stsb_spearman": 0.8430135614503571,
|
| 1579 |
+
"step": 23125
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.49,
|
| 1583 |
+
"eval_avg_sts": 0.7928345271530053,
|
| 1584 |
+
"eval_sickr_spearman": 0.7425940177243154,
|
| 1585 |
+
"eval_stsb_spearman": 0.8430750365816952,
|
| 1586 |
+
"step": 23250
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.5,
|
| 1590 |
+
"eval_avg_sts": 0.7930442205998951,
|
| 1591 |
+
"eval_sickr_spearman": 0.7427970932211958,
|
| 1592 |
+
"eval_stsb_spearman": 0.8432913479785945,
|
| 1593 |
+
"step": 23375
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.5,
|
| 1597 |
+
"learning_rate": 1.7363368744400357e-06,
|
| 1598 |
+
"loss": 0.0,
|
| 1599 |
+
"step": 23500
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.5,
|
| 1603 |
+
"eval_avg_sts": 0.793033132084566,
|
| 1604 |
+
"eval_sickr_spearman": 0.7428263441619716,
|
| 1605 |
+
"eval_stsb_spearman": 0.8432399200071605,
|
| 1606 |
+
"step": 23500
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.51,
|
| 1610 |
+
"eval_avg_sts": 0.7929242651260953,
|
| 1611 |
+
"eval_sickr_spearman": 0.7427599171486827,
|
| 1612 |
+
"eval_stsb_spearman": 0.8430886131035079,
|
| 1613 |
+
"step": 23625
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.52,
|
| 1617 |
+
"eval_avg_sts": 0.7936208486615127,
|
| 1618 |
+
"eval_sickr_spearman": 0.7430878254782006,
|
| 1619 |
+
"eval_stsb_spearman": 0.8441538718448248,
|
| 1620 |
+
"step": 23750
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.53,
|
| 1624 |
+
"eval_avg_sts": 0.7935886289185006,
|
| 1625 |
+
"eval_sickr_spearman": 0.7430728878056534,
|
| 1626 |
+
"eval_stsb_spearman": 0.8441043700313476,
|
| 1627 |
+
"step": 23875
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.54,
|
| 1631 |
+
"learning_rate": 1.6243440419813131e-06,
|
| 1632 |
+
"loss": 0.0001,
|
| 1633 |
+
"step": 24000
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.54,
|
| 1637 |
+
"eval_avg_sts": 0.7935571381985222,
|
| 1638 |
+
"eval_sickr_spearman": 0.7430181323500139,
|
| 1639 |
+
"eval_stsb_spearman": 0.8440961440470305,
|
| 1640 |
+
"step": 24000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.54,
|
| 1644 |
+
"eval_avg_sts": 0.7935492855380204,
|
| 1645 |
+
"eval_sickr_spearman": 0.7430870569805776,
|
| 1646 |
+
"eval_stsb_spearman": 0.8440115140954632,
|
| 1647 |
+
"step": 24125
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.55,
|
| 1651 |
+
"eval_avg_sts": 0.7936128430055818,
|
| 1652 |
+
"eval_sickr_spearman": 0.7431491611947371,
|
| 1653 |
+
"eval_stsb_spearman": 0.8440765248164266,
|
| 1654 |
+
"step": 24250
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.56,
|
| 1658 |
+
"eval_avg_sts": 0.7936605492215507,
|
| 1659 |
+
"eval_sickr_spearman": 0.7432605933500736,
|
| 1660 |
+
"eval_stsb_spearman": 0.844060505093028,
|
| 1661 |
+
"step": 24375
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.57,
|
| 1665 |
+
"learning_rate": 1.5123512095225906e-06,
|
| 1666 |
+
"loss": 0.0,
|
| 1667 |
+
"step": 24500
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.57,
|
| 1671 |
+
"eval_avg_sts": 0.793667841726459,
|
| 1672 |
+
"eval_sickr_spearman": 0.7432775483288812,
|
| 1673 |
+
"eval_stsb_spearman": 0.8440581351240368,
|
| 1674 |
+
"step": 24500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.58,
|
| 1678 |
+
"eval_avg_sts": 0.7948942597846932,
|
| 1679 |
+
"eval_sickr_spearman": 0.744056468700903,
|
| 1680 |
+
"eval_stsb_spearman": 0.8457320508684834,
|
| 1681 |
+
"step": 24625
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.58,
|
| 1685 |
+
"eval_avg_sts": 0.7948721522573494,
|
| 1686 |
+
"eval_sickr_spearman": 0.7440626647129885,
|
| 1687 |
+
"eval_stsb_spearman": 0.8456816398017104,
|
| 1688 |
+
"step": 24750
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 1.59,
|
| 1692 |
+
"eval_avg_sts": 0.7945095949089607,
|
| 1693 |
+
"eval_sickr_spearman": 0.7443504190417043,
|
| 1694 |
+
"eval_stsb_spearman": 0.8446687707762169,
|
| 1695 |
+
"step": 24875
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.6,
|
| 1699 |
+
"learning_rate": 1.4003583770638678e-06,
|
| 1700 |
+
"loss": 0.0001,
|
| 1701 |
+
"step": 25000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.6,
|
| 1705 |
+
"eval_avg_sts": 0.7947724077574231,
|
| 1706 |
+
"eval_sickr_spearman": 0.7446924004839437,
|
| 1707 |
+
"eval_stsb_spearman": 0.8448524150309025,
|
| 1708 |
+
"step": 25000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.61,
|
| 1712 |
+
"eval_avg_sts": 0.7959915253602992,
|
| 1713 |
+
"eval_sickr_spearman": 0.7461332854959857,
|
| 1714 |
+
"eval_stsb_spearman": 0.8458497652246126,
|
| 1715 |
+
"step": 25125
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.62,
|
| 1719 |
+
"eval_avg_sts": 0.7955281876289857,
|
| 1720 |
+
"eval_sickr_spearman": 0.7458754244134463,
|
| 1721 |
+
"eval_stsb_spearman": 0.845180950844525,
|
| 1722 |
+
"step": 25250
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.62,
|
| 1726 |
+
"eval_avg_sts": 0.79543745522762,
|
| 1727 |
+
"eval_sickr_spearman": 0.7456630610129066,
|
| 1728 |
+
"eval_stsb_spearman": 0.8452118494423333,
|
| 1729 |
+
"step": 25375
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.63,
|
| 1733 |
+
"learning_rate": 1.2883655446051453e-06,
|
| 1734 |
+
"loss": 0.0001,
|
| 1735 |
+
"step": 25500
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 1.63,
|
| 1739 |
+
"eval_avg_sts": 0.795353488562289,
|
| 1740 |
+
"eval_sickr_spearman": 0.7455269408714309,
|
| 1741 |
+
"eval_stsb_spearman": 0.8451800362531473,
|
| 1742 |
+
"step": 25500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 1.64,
|
| 1746 |
+
"eval_avg_sts": 0.7953584932327289,
|
| 1747 |
+
"eval_sickr_spearman": 0.745271175256273,
|
| 1748 |
+
"eval_stsb_spearman": 0.8454458112091847,
|
| 1749 |
+
"step": 25625
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.65,
|
| 1753 |
+
"eval_avg_sts": 0.7953254322370598,
|
| 1754 |
+
"eval_sickr_spearman": 0.7452719917849974,
|
| 1755 |
+
"eval_stsb_spearman": 0.8453788726891222,
|
| 1756 |
+
"step": 25750
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 1.66,
|
| 1760 |
+
"eval_avg_sts": 0.7952872018869009,
|
| 1761 |
+
"eval_sickr_spearman": 0.7452931735007315,
|
| 1762 |
+
"eval_stsb_spearman": 0.8452812302730703,
|
| 1763 |
+
"step": 25875
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 1.66,
|
| 1767 |
+
"learning_rate": 1.1763727121464225e-06,
|
| 1768 |
+
"loss": 0.0001,
|
| 1769 |
+
"step": 26000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.66,
|
| 1773 |
+
"eval_avg_sts": 0.7952607086010879,
|
| 1774 |
+
"eval_sickr_spearman": 0.7453110410704665,
|
| 1775 |
+
"eval_stsb_spearman": 0.8452103761317094,
|
| 1776 |
+
"step": 26000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.67,
|
| 1780 |
+
"eval_avg_sts": 0.7950903508557705,
|
| 1781 |
+
"eval_sickr_spearman": 0.7449656494200251,
|
| 1782 |
+
"eval_stsb_spearman": 0.8452150522915161,
|
| 1783 |
+
"step": 26125
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.68,
|
| 1787 |
+
"eval_avg_sts": 0.7950105822340711,
|
| 1788 |
+
"eval_sickr_spearman": 0.7448497023411534,
|
| 1789 |
+
"eval_stsb_spearman": 0.8451714621269887,
|
| 1790 |
+
"step": 26250
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.69,
|
| 1794 |
+
"eval_avg_sts": 0.7950131323560599,
|
| 1795 |
+
"eval_sickr_spearman": 0.744852055865124,
|
| 1796 |
+
"eval_stsb_spearman": 0.8451742088469958,
|
| 1797 |
+
"step": 26375
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 1.7,
|
| 1801 |
+
"learning_rate": 1.0643798796877e-06,
|
| 1802 |
+
"loss": 0.0001,
|
| 1803 |
+
"step": 26500
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.7,
|
| 1807 |
+
"eval_avg_sts": 0.7950484138603111,
|
| 1808 |
+
"eval_sickr_spearman": 0.7455690161162907,
|
| 1809 |
+
"eval_stsb_spearman": 0.8445278116043317,
|
| 1810 |
+
"step": 26500
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.7,
|
| 1814 |
+
"eval_avg_sts": 0.7950041615346236,
|
| 1815 |
+
"eval_sickr_spearman": 0.7455438958502385,
|
| 1816 |
+
"eval_stsb_spearman": 0.8444644272190087,
|
| 1817 |
+
"step": 26625
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.71,
|
| 1821 |
+
"eval_avg_sts": 0.7946972455858132,
|
| 1822 |
+
"eval_sickr_spearman": 0.745472569664603,
|
| 1823 |
+
"eval_stsb_spearman": 0.8439219215070236,
|
| 1824 |
+
"step": 26750
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.72,
|
| 1828 |
+
"eval_avg_sts": 0.7944591743219949,
|
| 1829 |
+
"eval_sickr_spearman": 0.7454866427773243,
|
| 1830 |
+
"eval_stsb_spearman": 0.8434317058666653,
|
| 1831 |
+
"step": 26875
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.73,
|
| 1835 |
+
"learning_rate": 9.523870472289774e-07,
|
| 1836 |
+
"loss": 0.0001,
|
| 1837 |
+
"step": 27000
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.73,
|
| 1841 |
+
"eval_avg_sts": 0.7944066177099748,
|
| 1842 |
+
"eval_sickr_spearman": 0.7454395722979149,
|
| 1843 |
+
"eval_stsb_spearman": 0.8433736631220347,
|
| 1844 |
+
"step": 27000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.74,
|
| 1848 |
+
"eval_avg_sts": 0.7944436945207991,
|
| 1849 |
+
"eval_sickr_spearman": 0.7455328006658063,
|
| 1850 |
+
"eval_stsb_spearman": 0.8433545883757919,
|
| 1851 |
+
"step": 27125
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.74,
|
| 1855 |
+
"eval_avg_sts": 0.7944797298738457,
|
| 1856 |
+
"eval_sickr_spearman": 0.7455790065853898,
|
| 1857 |
+
"eval_stsb_spearman": 0.8433804531623017,
|
| 1858 |
+
"step": 27250
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.75,
|
| 1862 |
+
"eval_avg_sts": 0.7944698737687554,
|
| 1863 |
+
"eval_sickr_spearman": 0.7455735310398258,
|
| 1864 |
+
"eval_stsb_spearman": 0.8433662164976851,
|
| 1865 |
+
"step": 27375
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.76,
|
| 1869 |
+
"learning_rate": 8.403942147702547e-07,
|
| 1870 |
+
"loss": 0.0001,
|
| 1871 |
+
"step": 27500
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.76,
|
| 1875 |
+
"eval_avg_sts": 0.7942514496393891,
|
| 1876 |
+
"eval_sickr_spearman": 0.74535724699005,
|
| 1877 |
+
"eval_stsb_spearman": 0.8431456522887281,
|
| 1878 |
+
"step": 27500
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.77,
|
| 1882 |
+
"eval_avg_sts": 0.7944530448391101,
|
| 1883 |
+
"eval_sickr_spearman": 0.7454611862935621,
|
| 1884 |
+
"eval_stsb_spearman": 0.8434449033846582,
|
| 1885 |
+
"step": 27625
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.78,
|
| 1889 |
+
"eval_avg_sts": 0.7944670140899726,
|
| 1890 |
+
"eval_sickr_spearman": 0.7455168063090274,
|
| 1891 |
+
"eval_stsb_spearman": 0.8434172218709176,
|
| 1892 |
+
"step": 27750
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.78,
|
| 1896 |
+
"eval_avg_sts": 0.7944968856863333,
|
| 1897 |
+
"eval_sickr_spearman": 0.7455487469914838,
|
| 1898 |
+
"eval_stsb_spearman": 0.8434450243811827,
|
| 1899 |
+
"step": 27875
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.79,
|
| 1903 |
+
"learning_rate": 7.284013823115321e-07,
|
| 1904 |
+
"loss": 0.0001,
|
| 1905 |
+
"step": 28000
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.79,
|
| 1909 |
+
"eval_avg_sts": 0.7944813522912897,
|
| 1910 |
+
"eval_sickr_spearman": 0.7459449555472468,
|
| 1911 |
+
"eval_stsb_spearman": 0.8430177490353326,
|
| 1912 |
+
"step": 28000
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 1.8,
|
| 1916 |
+
"eval_avg_sts": 0.7944717848510598,
|
| 1917 |
+
"eval_sickr_spearman": 0.7458816025244499,
|
| 1918 |
+
"eval_stsb_spearman": 0.8430619671776697,
|
| 1919 |
+
"step": 28125
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.81,
|
| 1923 |
+
"eval_avg_sts": 0.7943252967954475,
|
| 1924 |
+
"eval_sickr_spearman": 0.7455355384385883,
|
| 1925 |
+
"eval_stsb_spearman": 0.8431150551523066,
|
| 1926 |
+
"step": 28250
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.82,
|
| 1930 |
+
"eval_avg_sts": 0.7945802673668048,
|
| 1931 |
+
"eval_sickr_spearman": 0.7459384233174512,
|
| 1932 |
+
"eval_stsb_spearman": 0.8432221114161584,
|
| 1933 |
+
"step": 28375
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.82,
|
| 1937 |
+
"learning_rate": 6.164085498528094e-07,
|
| 1938 |
+
"loss": 0.0001,
|
| 1939 |
+
"step": 28500
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.82,
|
| 1943 |
+
"eval_avg_sts": 0.7945695711998493,
|
| 1944 |
+
"eval_sickr_spearman": 0.7459346288604376,
|
| 1945 |
+
"eval_stsb_spearman": 0.843204513539261,
|
| 1946 |
+
"step": 28500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.83,
|
| 1950 |
+
"eval_avg_sts": 0.7945396361578374,
|
| 1951 |
+
"eval_sickr_spearman": 0.7462354956798459,
|
| 1952 |
+
"eval_stsb_spearman": 0.8428437766358288,
|
| 1953 |
+
"step": 28625
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.84,
|
| 1957 |
+
"eval_avg_sts": 0.7944409539151067,
|
| 1958 |
+
"eval_sickr_spearman": 0.7461240814315593,
|
| 1959 |
+
"eval_stsb_spearman": 0.8427578263986542,
|
| 1960 |
+
"step": 28750
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.85,
|
| 1964 |
+
"eval_avg_sts": 0.7940565976087757,
|
| 1965 |
+
"eval_sickr_spearman": 0.7457283833108623,
|
| 1966 |
+
"eval_stsb_spearman": 0.8423848119066891,
|
| 1967 |
+
"step": 28875
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.86,
|
| 1971 |
+
"learning_rate": 5.044157173940868e-07,
|
| 1972 |
+
"loss": 0.0002,
|
| 1973 |
+
"step": 29000
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 1.86,
|
| 1977 |
+
"eval_avg_sts": 0.7940545279108154,
|
| 1978 |
+
"eval_sickr_spearman": 0.7457486524356691,
|
| 1979 |
+
"eval_stsb_spearman": 0.8423604033859617,
|
| 1980 |
+
"step": 29000
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 1.86,
|
| 1984 |
+
"eval_avg_sts": 0.7940541798236898,
|
| 1985 |
+
"eval_sickr_spearman": 0.7457327061099918,
|
| 1986 |
+
"eval_stsb_spearman": 0.8423756535373876,
|
| 1987 |
+
"step": 29125
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 1.87,
|
| 1991 |
+
"eval_avg_sts": 0.794045870127827,
|
| 1992 |
+
"eval_sickr_spearman": 0.7457254534136746,
|
| 1993 |
+
"eval_stsb_spearman": 0.8423662868419793,
|
| 1994 |
+
"step": 29250
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.88,
|
| 1998 |
+
"eval_avg_sts": 0.7939439159521589,
|
| 1999 |
+
"eval_sickr_spearman": 0.7456850112262637,
|
| 2000 |
+
"eval_stsb_spearman": 0.8422028206780539,
|
| 2001 |
+
"step": 29375
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 1.89,
|
| 2005 |
+
"learning_rate": 3.9242288493536413e-07,
|
| 2006 |
+
"loss": 0.0001,
|
| 2007 |
+
"step": 29500
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 1.89,
|
| 2011 |
+
"eval_avg_sts": 0.7938843170635432,
|
| 2012 |
+
"eval_sickr_spearman": 0.7456857797238867,
|
| 2013 |
+
"eval_stsb_spearman": 0.8420828544031996,
|
| 2014 |
+
"step": 29500
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 1.9,
|
| 2018 |
+
"eval_avg_sts": 0.7938335370035037,
|
| 2019 |
+
"eval_sickr_spearman": 0.7456398619909119,
|
| 2020 |
+
"eval_stsb_spearman": 0.8420272120160953,
|
| 2021 |
+
"step": 29625
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 1.9,
|
| 2025 |
+
"eval_avg_sts": 0.7937791099281831,
|
| 2026 |
+
"eval_sickr_spearman": 0.7455667765481975,
|
| 2027 |
+
"eval_stsb_spearman": 0.8419914433081688,
|
| 2028 |
+
"step": 29750
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 1.91,
|
| 2032 |
+
"eval_avg_sts": 0.7937599626397398,
|
| 2033 |
+
"eval_sickr_spearman": 0.7455335691634293,
|
| 2034 |
+
"eval_stsb_spearman": 0.8419863561160503,
|
| 2035 |
+
"step": 29875
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 1.92,
|
| 2039 |
+
"learning_rate": 2.804300524766415e-07,
|
| 2040 |
+
"loss": 0.0001,
|
| 2041 |
+
"step": 30000
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.92,
|
| 2045 |
+
"eval_avg_sts": 0.7937406443684292,
|
| 2046 |
+
"eval_sickr_spearman": 0.7454874593060488,
|
| 2047 |
+
"eval_stsb_spearman": 0.8419938294308097,
|
| 2048 |
+
"step": 30000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.93,
|
| 2052 |
+
"eval_avg_sts": 0.7939020781683644,
|
| 2053 |
+
"eval_sickr_spearman": 0.7457190652771832,
|
| 2054 |
+
"eval_stsb_spearman": 0.8420850910595457,
|
| 2055 |
+
"step": 30125
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.94,
|
| 2059 |
+
"eval_avg_sts": 0.7938812791358627,
|
| 2060 |
+
"eval_sickr_spearman": 0.7456977394681448,
|
| 2061 |
+
"eval_stsb_spearman": 0.8420648188035805,
|
| 2062 |
+
"step": 30250
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 1.94,
|
| 2066 |
+
"eval_avg_sts": 0.7937378630658074,
|
| 2067 |
+
"eval_sickr_spearman": 0.7454741066598489,
|
| 2068 |
+
"eval_stsb_spearman": 0.842001619471766,
|
| 2069 |
+
"step": 30375
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 1.95,
|
| 2073 |
+
"learning_rate": 1.6843722001791884e-07,
|
| 2074 |
+
"loss": 0.0002,
|
| 2075 |
+
"step": 30500
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.95,
|
| 2079 |
+
"eval_avg_sts": 0.7937467005092009,
|
| 2080 |
+
"eval_sickr_spearman": 0.7454940875980473,
|
| 2081 |
+
"eval_stsb_spearman": 0.8419993134203545,
|
| 2082 |
+
"step": 30500
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.96,
|
| 2086 |
+
"eval_avg_sts": 0.7937544654414969,
|
| 2087 |
+
"eval_sickr_spearman": 0.7454804467652388,
|
| 2088 |
+
"eval_stsb_spearman": 0.8420284841177549,
|
| 2089 |
+
"step": 30625
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.97,
|
| 2093 |
+
"eval_avg_sts": 0.7937753802718709,
|
| 2094 |
+
"eval_sickr_spearman": 0.7455158937181001,
|
| 2095 |
+
"eval_stsb_spearman": 0.8420348668256417,
|
| 2096 |
+
"step": 30750
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.98,
|
| 2100 |
+
"eval_avg_sts": 0.7937608907538469,
|
| 2101 |
+
"eval_sickr_spearman": 0.745488035679266,
|
| 2102 |
+
"eval_stsb_spearman": 0.8420337458284277,
|
| 2103 |
+
"step": 30875
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.98,
|
| 2107 |
+
"learning_rate": 5.64443875591962e-08,
|
| 2108 |
+
"loss": 0.0001,
|
| 2109 |
+
"step": 31000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.98,
|
| 2113 |
+
"eval_avg_sts": 0.7937471629995045,
|
| 2114 |
+
"eval_sickr_spearman": 0.7454658933415031,
|
| 2115 |
+
"eval_stsb_spearman": 0.8420284326575058,
|
| 2116 |
+
"step": 31000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.99,
|
| 2120 |
+
"eval_avg_sts": 0.7937690011247767,
|
| 2121 |
+
"eval_sickr_spearman": 0.7455096977060146,
|
| 2122 |
+
"eval_stsb_spearman": 0.8420283045435387,
|
| 2123 |
+
"step": 31125
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.0,
|
| 2127 |
+
"eval_avg_sts": 0.7937804647459197,
|
| 2128 |
+
"eval_sickr_spearman": 0.7455530217595118,
|
| 2129 |
+
"eval_stsb_spearman": 0.8420079077323277,
|
| 2130 |
+
"step": 31250
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.0,
|
| 2134 |
+
"step": 31252,
|
| 2135 |
+
"train_runtime": 9641.8618,
|
| 2136 |
+
"train_samples_per_second": 3.241
|
| 2137 |
+
}
|
| 2138 |
+
],
|
| 2139 |
+
"max_steps": 31252,
|
| 2140 |
+
"num_train_epochs": 2,
|
| 2141 |
+
"total_flos": 333421219511531712,
|
| 2142 |
+
"trial_name": null,
|
| 2143 |
+
"trial_params": null
|
| 2144 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd6299686d84f474535ca08a886bbd4d20abccf6142fc2008bd13a750366200
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|