root
commited on
Commit
·
6f1955c
1
Parent(s):
6fc0b70
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 +1083 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "result/my-unsup-simcse-bert-base-uncased-d0.2-rs192-std0.5-t0.05",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.2,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.2,
|
| 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 = 1.0
|
| 2 |
+
eval_CR = 86.48
|
| 3 |
+
eval_MPQA = 88.48
|
| 4 |
+
eval_MR = 80.51
|
| 5 |
+
eval_MRPC = 74.78
|
| 6 |
+
eval_SST2 = 86.47
|
| 7 |
+
eval_SUBJ = 94.68
|
| 8 |
+
eval_TREC = 80.85
|
| 9 |
+
eval_avg_sts = 0.7844981403056908
|
| 10 |
+
eval_avg_transfer = 84.60714285714286
|
| 11 |
+
eval_sickr_spearman = 0.7469667211681398
|
| 12 |
+
eval_stsb_spearman = 0.8220295594432419
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ce43b34e68ad6002a5a61eefc0235da308d7e6e96f2aed6f16c7c538bb2b30
|
| 3 |
+
size 875982829
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21b51f01073f693d2b1510f5129a236c4a239fcb8f69f7aba88e39b0b065b961
|
| 3 |
+
size 440380809
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de07a7b75aafbc3da5fcc7ae75922d18d221d773d539659658f2e7691050e4b3
|
| 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, "model_max_length": 512, "name_or_path": "bert-base-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 1.0
|
| 2 |
+
train_runtime = 3834.5201
|
| 3 |
+
train_samples_per_second = 4.075
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8220295594432419,
|
| 3 |
+
"best_model_checkpoint": "result/my-unsup-simcse-bert-base-uncased-d0.2-rs192-std0.5-t0.05",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 15626,
|
| 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": 0.7039632579138562,
|
| 13 |
+
"eval_sickr_spearman": 0.6894170562025291,
|
| 14 |
+
"eval_stsb_spearman": 0.7185094596251831,
|
| 15 |
+
"step": 125
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_avg_sts": 0.7320830312686424,
|
| 20 |
+
"eval_sickr_spearman": 0.7157956410501377,
|
| 21 |
+
"eval_stsb_spearman": 0.7483704214871472,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.02,
|
| 26 |
+
"eval_avg_sts": 0.7306267531474842,
|
| 27 |
+
"eval_sickr_spearman": 0.7151454920610715,
|
| 28 |
+
"eval_stsb_spearman": 0.7461080142338968,
|
| 29 |
+
"step": 375
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 2.9040061436068092e-05,
|
| 34 |
+
"loss": 0.0316,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.03,
|
| 39 |
+
"eval_avg_sts": 0.7490673075570297,
|
| 40 |
+
"eval_sickr_spearman": 0.7306142925280271,
|
| 41 |
+
"eval_stsb_spearman": 0.7675203225860322,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"eval_avg_sts": 0.751267358789496,
|
| 47 |
+
"eval_sickr_spearman": 0.7340745011067302,
|
| 48 |
+
"eval_stsb_spearman": 0.7684602164722617,
|
| 49 |
+
"step": 625
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_avg_sts": 0.7786649440391495,
|
| 54 |
+
"eval_sickr_spearman": 0.7455865474683157,
|
| 55 |
+
"eval_stsb_spearman": 0.8117433406099835,
|
| 56 |
+
"step": 750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_avg_sts": 0.7696928806594809,
|
| 61 |
+
"eval_sickr_spearman": 0.7452508100692632,
|
| 62 |
+
"eval_stsb_spearman": 0.7941349512496988,
|
| 63 |
+
"step": 875
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 2.8080122872136184e-05,
|
| 68 |
+
"loss": 0.0008,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"eval_avg_sts": 0.7651441102319789,
|
| 74 |
+
"eval_sickr_spearman": 0.7429110710249084,
|
| 75 |
+
"eval_stsb_spearman": 0.7873771494390496,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_avg_sts": 0.7657607879714892,
|
| 81 |
+
"eval_sickr_spearman": 0.7408295471818849,
|
| 82 |
+
"eval_stsb_spearman": 0.7906920287610936,
|
| 83 |
+
"step": 1125
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_avg_sts": 0.7673800101461663,
|
| 88 |
+
"eval_sickr_spearman": 0.7415319540093158,
|
| 89 |
+
"eval_stsb_spearman": 0.7932280662830168,
|
| 90 |
+
"step": 1250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09,
|
| 94 |
+
"eval_avg_sts": 0.7657849020870391,
|
| 95 |
+
"eval_sickr_spearman": 0.7396460128113483,
|
| 96 |
+
"eval_stsb_spearman": 0.7919237913627298,
|
| 97 |
+
"step": 1375
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1,
|
| 101 |
+
"learning_rate": 2.7120184308204276e-05,
|
| 102 |
+
"loss": 0.0006,
|
| 103 |
+
"step": 1500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.1,
|
| 107 |
+
"eval_avg_sts": 0.7564555230487979,
|
| 108 |
+
"eval_sickr_spearman": 0.7337248346882608,
|
| 109 |
+
"eval_stsb_spearman": 0.7791862114093351,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1,
|
| 114 |
+
"eval_avg_sts": 0.7663342569223988,
|
| 115 |
+
"eval_sickr_spearman": 0.740796117535284,
|
| 116 |
+
"eval_stsb_spearman": 0.7918723963095137,
|
| 117 |
+
"step": 1625
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_avg_sts": 0.7650001912920963,
|
| 122 |
+
"eval_sickr_spearman": 0.7428139521378004,
|
| 123 |
+
"eval_stsb_spearman": 0.787186430446392,
|
| 124 |
+
"step": 1750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12,
|
| 128 |
+
"eval_avg_sts": 0.7697843702026972,
|
| 129 |
+
"eval_sickr_spearman": 0.7472399220731197,
|
| 130 |
+
"eval_stsb_spearman": 0.7923288183322746,
|
| 131 |
+
"step": 1875
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.13,
|
| 135 |
+
"learning_rate": 2.6160245744272367e-05,
|
| 136 |
+
"loss": 0.0004,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.13,
|
| 141 |
+
"eval_avg_sts": 0.772637186091681,
|
| 142 |
+
"eval_sickr_spearman": 0.7453534525330364,
|
| 143 |
+
"eval_stsb_spearman": 0.7999209196503256,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"eval_avg_sts": 0.7844981403056908,
|
| 149 |
+
"eval_sickr_spearman": 0.7469667211681398,
|
| 150 |
+
"eval_stsb_spearman": 0.8220295594432419,
|
| 151 |
+
"step": 2125
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.14,
|
| 155 |
+
"eval_avg_sts": 0.7825301157194102,
|
| 156 |
+
"eval_sickr_spearman": 0.745924590360237,
|
| 157 |
+
"eval_stsb_spearman": 0.8191356410785836,
|
| 158 |
+
"step": 2250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"eval_avg_sts": 0.7786888226299735,
|
| 163 |
+
"eval_sickr_spearman": 0.7462584545463333,
|
| 164 |
+
"eval_stsb_spearman": 0.8111191907136137,
|
| 165 |
+
"step": 2375
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 2.5200307180340456e-05,
|
| 170 |
+
"loss": 0.0004,
|
| 171 |
+
"step": 2500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"eval_avg_sts": 0.7798782002704093,
|
| 176 |
+
"eval_sickr_spearman": 0.7466363632524484,
|
| 177 |
+
"eval_stsb_spearman": 0.8131200372883702,
|
| 178 |
+
"step": 2500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"eval_avg_sts": 0.7751115325157576,
|
| 183 |
+
"eval_sickr_spearman": 0.7426031436335886,
|
| 184 |
+
"eval_stsb_spearman": 0.8076199213979265,
|
| 185 |
+
"step": 2625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.18,
|
| 189 |
+
"eval_avg_sts": 0.7666810908791618,
|
| 190 |
+
"eval_sickr_spearman": 0.7362270149176792,
|
| 191 |
+
"eval_stsb_spearman": 0.7971351668406444,
|
| 192 |
+
"step": 2750
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18,
|
| 196 |
+
"eval_avg_sts": 0.7732616540318422,
|
| 197 |
+
"eval_sickr_spearman": 0.7442702551334042,
|
| 198 |
+
"eval_stsb_spearman": 0.8022530529302804,
|
| 199 |
+
"step": 2875
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.19,
|
| 203 |
+
"learning_rate": 2.424036861640855e-05,
|
| 204 |
+
"loss": 0.0004,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"eval_avg_sts": 0.7733068432231915,
|
| 210 |
+
"eval_sickr_spearman": 0.7420109201528567,
|
| 211 |
+
"eval_stsb_spearman": 0.8046027662935263,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"eval_avg_sts": 0.7672720656943643,
|
| 217 |
+
"eval_sickr_spearman": 0.7361518462439285,
|
| 218 |
+
"eval_stsb_spearman": 0.7983922851448001,
|
| 219 |
+
"step": 3125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"eval_avg_sts": 0.7652170530985714,
|
| 224 |
+
"eval_sickr_spearman": 0.7340480840009392,
|
| 225 |
+
"eval_stsb_spearman": 0.7963860221962036,
|
| 226 |
+
"step": 3250
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22,
|
| 230 |
+
"eval_avg_sts": 0.7769025861727988,
|
| 231 |
+
"eval_sickr_spearman": 0.7457697079566438,
|
| 232 |
+
"eval_stsb_spearman": 0.8080354643889539,
|
| 233 |
+
"step": 3375
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 2.3280430052476642e-05,
|
| 238 |
+
"loss": 0.0003,
|
| 239 |
+
"step": 3500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_avg_sts": 0.7745062864644923,
|
| 244 |
+
"eval_sickr_spearman": 0.743565975093017,
|
| 245 |
+
"eval_stsb_spearman": 0.8054465978359675,
|
| 246 |
+
"step": 3500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23,
|
| 250 |
+
"eval_avg_sts": 0.7713562889079433,
|
| 251 |
+
"eval_sickr_spearman": 0.7430872010738819,
|
| 252 |
+
"eval_stsb_spearman": 0.7996253767420045,
|
| 253 |
+
"step": 3625
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.24,
|
| 257 |
+
"eval_avg_sts": 0.7689988388424054,
|
| 258 |
+
"eval_sickr_spearman": 0.7403553361173865,
|
| 259 |
+
"eval_stsb_spearman": 0.7976423415674243,
|
| 260 |
+
"step": 3750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"eval_avg_sts": 0.7691667949901446,
|
| 265 |
+
"eval_sickr_spearman": 0.7390877953504347,
|
| 266 |
+
"eval_stsb_spearman": 0.7992457946298546,
|
| 267 |
+
"step": 3875
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 2.2320491488544734e-05,
|
| 272 |
+
"loss": 0.0004,
|
| 273 |
+
"step": 4000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_avg_sts": 0.7640678967425198,
|
| 278 |
+
"eval_sickr_spearman": 0.7361696177514606,
|
| 279 |
+
"eval_stsb_spearman": 0.7919661757335791,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.26,
|
| 284 |
+
"eval_avg_sts": 0.7720104233010221,
|
| 285 |
+
"eval_sickr_spearman": 0.7409091347169678,
|
| 286 |
+
"eval_stsb_spearman": 0.8031117118850762,
|
| 287 |
+
"step": 4125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27,
|
| 291 |
+
"eval_avg_sts": 0.7716821019144677,
|
| 292 |
+
"eval_sickr_spearman": 0.7378609849575023,
|
| 293 |
+
"eval_stsb_spearman": 0.8055032188714333,
|
| 294 |
+
"step": 4250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.28,
|
| 298 |
+
"eval_avg_sts": 0.7749099391602485,
|
| 299 |
+
"eval_sickr_spearman": 0.7425721155420596,
|
| 300 |
+
"eval_stsb_spearman": 0.8072477627784373,
|
| 301 |
+
"step": 4375
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.29,
|
| 305 |
+
"learning_rate": 2.1360552924612826e-05,
|
| 306 |
+
"loss": 0.0004,
|
| 307 |
+
"step": 4500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.29,
|
| 311 |
+
"eval_avg_sts": 0.7668234253805365,
|
| 312 |
+
"eval_sickr_spearman": 0.7378467197203752,
|
| 313 |
+
"eval_stsb_spearman": 0.7958001310406978,
|
| 314 |
+
"step": 4500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"eval_avg_sts": 0.7705218895648999,
|
| 319 |
+
"eval_sickr_spearman": 0.7391226659300787,
|
| 320 |
+
"eval_stsb_spearman": 0.801921113199721,
|
| 321 |
+
"step": 4625
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"eval_avg_sts": 0.7678707529208644,
|
| 326 |
+
"eval_sickr_spearman": 0.7376356230295548,
|
| 327 |
+
"eval_stsb_spearman": 0.798105882812174,
|
| 328 |
+
"step": 4750
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"eval_avg_sts": 0.768346434351147,
|
| 333 |
+
"eval_sickr_spearman": 0.7373303853799155,
|
| 334 |
+
"eval_stsb_spearman": 0.7993624833223786,
|
| 335 |
+
"step": 4875
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.32,
|
| 339 |
+
"learning_rate": 2.0400614360680917e-05,
|
| 340 |
+
"loss": 0.0002,
|
| 341 |
+
"step": 5000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.32,
|
| 345 |
+
"eval_avg_sts": 0.7714937923042149,
|
| 346 |
+
"eval_sickr_spearman": 0.7393215146900324,
|
| 347 |
+
"eval_stsb_spearman": 0.8036660699183974,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"eval_avg_sts": 0.7705501211555204,
|
| 353 |
+
"eval_sickr_spearman": 0.7388855363822787,
|
| 354 |
+
"eval_stsb_spearman": 0.802214705928762,
|
| 355 |
+
"step": 5125
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.34,
|
| 359 |
+
"eval_avg_sts": 0.769454128932314,
|
| 360 |
+
"eval_sickr_spearman": 0.7382745327408845,
|
| 361 |
+
"eval_stsb_spearman": 0.8006337251237436,
|
| 362 |
+
"step": 5250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.34,
|
| 366 |
+
"eval_avg_sts": 0.7705108541596231,
|
| 367 |
+
"eval_sickr_spearman": 0.7397600866772639,
|
| 368 |
+
"eval_stsb_spearman": 0.8012616216419822,
|
| 369 |
+
"step": 5375
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.35,
|
| 373 |
+
"learning_rate": 1.944067579674901e-05,
|
| 374 |
+
"loss": 0.0004,
|
| 375 |
+
"step": 5500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.35,
|
| 379 |
+
"eval_avg_sts": 0.767759877044913,
|
| 380 |
+
"eval_sickr_spearman": 0.7378074783105003,
|
| 381 |
+
"eval_stsb_spearman": 0.7977122757793257,
|
| 382 |
+
"step": 5500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36,
|
| 386 |
+
"eval_avg_sts": 0.7698443583732223,
|
| 387 |
+
"eval_sickr_spearman": 0.7391045582048366,
|
| 388 |
+
"eval_stsb_spearman": 0.800584158541608,
|
| 389 |
+
"step": 5625
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.37,
|
| 393 |
+
"eval_avg_sts": 0.7712564343816768,
|
| 394 |
+
"eval_sickr_spearman": 0.741173257743776,
|
| 395 |
+
"eval_stsb_spearman": 0.8013396110195776,
|
| 396 |
+
"step": 5750
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38,
|
| 400 |
+
"eval_avg_sts": 0.7664448809595665,
|
| 401 |
+
"eval_sickr_spearman": 0.739177853665631,
|
| 402 |
+
"eval_stsb_spearman": 0.7937119082535019,
|
| 403 |
+
"step": 5875
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.38,
|
| 407 |
+
"learning_rate": 1.84807372328171e-05,
|
| 408 |
+
"loss": 0.0002,
|
| 409 |
+
"step": 6000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.38,
|
| 413 |
+
"eval_avg_sts": 0.7638769604550799,
|
| 414 |
+
"eval_sickr_spearman": 0.7379414370524111,
|
| 415 |
+
"eval_stsb_spearman": 0.7898124838577486,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.39,
|
| 420 |
+
"eval_avg_sts": 0.766509076179771,
|
| 421 |
+
"eval_sickr_spearman": 0.7385067150852364,
|
| 422 |
+
"eval_stsb_spearman": 0.7945114372743056,
|
| 423 |
+
"step": 6125
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4,
|
| 427 |
+
"eval_avg_sts": 0.7666375164161757,
|
| 428 |
+
"eval_sickr_spearman": 0.7395296334525638,
|
| 429 |
+
"eval_stsb_spearman": 0.7937453993797876,
|
| 430 |
+
"step": 6250
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.41,
|
| 434 |
+
"eval_avg_sts": 0.7675116415394574,
|
| 435 |
+
"eval_sickr_spearman": 0.7385751113736841,
|
| 436 |
+
"eval_stsb_spearman": 0.7964481717052306,
|
| 437 |
+
"step": 6375
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.42,
|
| 441 |
+
"learning_rate": 1.7520798668885192e-05,
|
| 442 |
+
"loss": 0.0003,
|
| 443 |
+
"step": 6500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.42,
|
| 447 |
+
"eval_avg_sts": 0.7676886943660834,
|
| 448 |
+
"eval_sickr_spearman": 0.737567130678904,
|
| 449 |
+
"eval_stsb_spearman": 0.797810258053263,
|
| 450 |
+
"step": 6500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.42,
|
| 454 |
+
"eval_avg_sts": 0.7661323845941221,
|
| 455 |
+
"eval_sickr_spearman": 0.7377277947132145,
|
| 456 |
+
"eval_stsb_spearman": 0.7945369744750297,
|
| 457 |
+
"step": 6625
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.43,
|
| 461 |
+
"eval_avg_sts": 0.7657108387605938,
|
| 462 |
+
"eval_sickr_spearman": 0.7375463332119813,
|
| 463 |
+
"eval_stsb_spearman": 0.7938753443092063,
|
| 464 |
+
"step": 6750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"eval_avg_sts": 0.7634754316352123,
|
| 469 |
+
"eval_sickr_spearman": 0.7353273443566419,
|
| 470 |
+
"eval_stsb_spearman": 0.7916235189137826,
|
| 471 |
+
"step": 6875
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.45,
|
| 475 |
+
"learning_rate": 1.6560860104953284e-05,
|
| 476 |
+
"loss": 0.0002,
|
| 477 |
+
"step": 7000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.45,
|
| 481 |
+
"eval_avg_sts": 0.7659995201775873,
|
| 482 |
+
"eval_sickr_spearman": 0.7410373297267062,
|
| 483 |
+
"eval_stsb_spearman": 0.7909617106284685,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"eval_avg_sts": 0.7603361178127348,
|
| 489 |
+
"eval_sickr_spearman": 0.7367544444425711,
|
| 490 |
+
"eval_stsb_spearman": 0.7839177911828984,
|
| 491 |
+
"step": 7125
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"eval_avg_sts": 0.7697008342068297,
|
| 496 |
+
"eval_sickr_spearman": 0.7388405312402312,
|
| 497 |
+
"eval_stsb_spearman": 0.800561137173428,
|
| 498 |
+
"step": 7250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"eval_avg_sts": 0.7683036722669765,
|
| 503 |
+
"eval_sickr_spearman": 0.7386270810254403,
|
| 504 |
+
"eval_stsb_spearman": 0.7979802635085127,
|
| 505 |
+
"step": 7375
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.48,
|
| 509 |
+
"learning_rate": 1.5600921541021372e-05,
|
| 510 |
+
"loss": 0.0002,
|
| 511 |
+
"step": 7500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.48,
|
| 515 |
+
"eval_avg_sts": 0.7732594696328385,
|
| 516 |
+
"eval_sickr_spearman": 0.7422230254968075,
|
| 517 |
+
"eval_stsb_spearman": 0.8042959137688697,
|
| 518 |
+
"step": 7500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.49,
|
| 522 |
+
"eval_avg_sts": 0.7737749390548014,
|
| 523 |
+
"eval_sickr_spearman": 0.742280086445316,
|
| 524 |
+
"eval_stsb_spearman": 0.8052697916642868,
|
| 525 |
+
"step": 7625
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5,
|
| 529 |
+
"eval_avg_sts": 0.772584123544011,
|
| 530 |
+
"eval_sickr_spearman": 0.741925424792297,
|
| 531 |
+
"eval_stsb_spearman": 0.8032428222957251,
|
| 532 |
+
"step": 7750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5,
|
| 536 |
+
"eval_avg_sts": 0.772843322519777,
|
| 537 |
+
"eval_sickr_spearman": 0.7422232656523147,
|
| 538 |
+
"eval_stsb_spearman": 0.8034633793872396,
|
| 539 |
+
"step": 7875
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.51,
|
| 543 |
+
"learning_rate": 1.4640982977089467e-05,
|
| 544 |
+
"loss": 0.0002,
|
| 545 |
+
"step": 8000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.51,
|
| 549 |
+
"eval_avg_sts": 0.7715935954543726,
|
| 550 |
+
"eval_sickr_spearman": 0.7422030925897106,
|
| 551 |
+
"eval_stsb_spearman": 0.8009840983190345,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.52,
|
| 556 |
+
"eval_avg_sts": 0.7690169428580813,
|
| 557 |
+
"eval_sickr_spearman": 0.7407306511440238,
|
| 558 |
+
"eval_stsb_spearman": 0.7973032345721387,
|
| 559 |
+
"step": 8125
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.53,
|
| 563 |
+
"eval_avg_sts": 0.7675907004689784,
|
| 564 |
+
"eval_sickr_spearman": 0.7394478364868148,
|
| 565 |
+
"eval_stsb_spearman": 0.795733564451142,
|
| 566 |
+
"step": 8250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.54,
|
| 570 |
+
"eval_avg_sts": 0.7677635816632358,
|
| 571 |
+
"eval_sickr_spearman": 0.7398567252533574,
|
| 572 |
+
"eval_stsb_spearman": 0.7956704380731142,
|
| 573 |
+
"step": 8375
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.54,
|
| 577 |
+
"learning_rate": 1.368104441315756e-05,
|
| 578 |
+
"loss": 0.0001,
|
| 579 |
+
"step": 8500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.54,
|
| 583 |
+
"eval_avg_sts": 0.7665064992996365,
|
| 584 |
+
"eval_sickr_spearman": 0.7390165171959004,
|
| 585 |
+
"eval_stsb_spearman": 0.7939964814033726,
|
| 586 |
+
"step": 8500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.55,
|
| 590 |
+
"eval_avg_sts": 0.768501738751435,
|
| 591 |
+
"eval_sickr_spearman": 0.7403488519186923,
|
| 592 |
+
"eval_stsb_spearman": 0.7966546255841779,
|
| 593 |
+
"step": 8625
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.56,
|
| 597 |
+
"eval_avg_sts": 0.7705756275356871,
|
| 598 |
+
"eval_sickr_spearman": 0.7442900919782981,
|
| 599 |
+
"eval_stsb_spearman": 0.7968611630930761,
|
| 600 |
+
"step": 8750
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.57,
|
| 604 |
+
"eval_avg_sts": 0.7708996463902738,
|
| 605 |
+
"eval_sickr_spearman": 0.7443713125708299,
|
| 606 |
+
"eval_stsb_spearman": 0.7974279802097175,
|
| 607 |
+
"step": 8875
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.58,
|
| 611 |
+
"learning_rate": 1.2721105849225649e-05,
|
| 612 |
+
"loss": 0.0002,
|
| 613 |
+
"step": 9000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.58,
|
| 617 |
+
"eval_avg_sts": 0.7690762421498543,
|
| 618 |
+
"eval_sickr_spearman": 0.7437613656136672,
|
| 619 |
+
"eval_stsb_spearman": 0.7943911186860414,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.58,
|
| 624 |
+
"eval_avg_sts": 0.7632497822206319,
|
| 625 |
+
"eval_sickr_spearman": 0.7418991037487088,
|
| 626 |
+
"eval_stsb_spearman": 0.7846004606925551,
|
| 627 |
+
"step": 9125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.59,
|
| 631 |
+
"eval_avg_sts": 0.7661106731884346,
|
| 632 |
+
"eval_sickr_spearman": 0.7425510779196297,
|
| 633 |
+
"eval_stsb_spearman": 0.7896702684572396,
|
| 634 |
+
"step": 9250
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6,
|
| 638 |
+
"eval_avg_sts": 0.7582809505084913,
|
| 639 |
+
"eval_sickr_spearman": 0.734091696241045,
|
| 640 |
+
"eval_stsb_spearman": 0.7824702047759376,
|
| 641 |
+
"step": 9375
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.61,
|
| 645 |
+
"learning_rate": 1.176116728529374e-05,
|
| 646 |
+
"loss": 0.0003,
|
| 647 |
+
"step": 9500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.61,
|
| 651 |
+
"eval_avg_sts": 0.760148082899698,
|
| 652 |
+
"eval_sickr_spearman": 0.735014469761874,
|
| 653 |
+
"eval_stsb_spearman": 0.785281696037522,
|
| 654 |
+
"step": 9500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.62,
|
| 658 |
+
"eval_avg_sts": 0.7629335466481396,
|
| 659 |
+
"eval_sickr_spearman": 0.7371143414856469,
|
| 660 |
+
"eval_stsb_spearman": 0.7887527518106323,
|
| 661 |
+
"step": 9625
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.62,
|
| 665 |
+
"eval_avg_sts": 0.7642452574201212,
|
| 666 |
+
"eval_sickr_spearman": 0.738628137709672,
|
| 667 |
+
"eval_stsb_spearman": 0.7898623771305704,
|
| 668 |
+
"step": 9750
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.63,
|
| 672 |
+
"eval_avg_sts": 0.7661101842825881,
|
| 673 |
+
"eval_sickr_spearman": 0.7410933820220844,
|
| 674 |
+
"eval_stsb_spearman": 0.791126986543092,
|
| 675 |
+
"step": 9875
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.64,
|
| 679 |
+
"learning_rate": 1.0801228721361832e-05,
|
| 680 |
+
"loss": 0.0002,
|
| 681 |
+
"step": 10000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.64,
|
| 685 |
+
"eval_avg_sts": 0.7672844353835271,
|
| 686 |
+
"eval_sickr_spearman": 0.741854819073183,
|
| 687 |
+
"eval_stsb_spearman": 0.7927140516938713,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.65,
|
| 692 |
+
"eval_avg_sts": 0.7695572795608598,
|
| 693 |
+
"eval_sickr_spearman": 0.7413840662479879,
|
| 694 |
+
"eval_stsb_spearman": 0.7977304928737319,
|
| 695 |
+
"step": 10125
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.66,
|
| 699 |
+
"eval_avg_sts": 0.7687590638385537,
|
| 700 |
+
"eval_sickr_spearman": 0.739025354918565,
|
| 701 |
+
"eval_stsb_spearman": 0.7984927727585424,
|
| 702 |
+
"step": 10250
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.66,
|
| 706 |
+
"eval_avg_sts": 0.7669714587155453,
|
| 707 |
+
"eval_sickr_spearman": 0.7381937444282656,
|
| 708 |
+
"eval_stsb_spearman": 0.795749173002825,
|
| 709 |
+
"step": 10375
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.67,
|
| 713 |
+
"learning_rate": 9.841290157429926e-06,
|
| 714 |
+
"loss": 0.0002,
|
| 715 |
+
"step": 10500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.67,
|
| 719 |
+
"eval_avg_sts": 0.7675942026136746,
|
| 720 |
+
"eval_sickr_spearman": 0.7389821269272708,
|
| 721 |
+
"eval_stsb_spearman": 0.7962062783000783,
|
| 722 |
+
"step": 10500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.68,
|
| 726 |
+
"eval_avg_sts": 0.7678054650263499,
|
| 727 |
+
"eval_sickr_spearman": 0.738494515185471,
|
| 728 |
+
"eval_stsb_spearman": 0.7971164148672288,
|
| 729 |
+
"step": 10625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.69,
|
| 733 |
+
"eval_avg_sts": 0.7682414535062771,
|
| 734 |
+
"eval_sickr_spearman": 0.7377959508461551,
|
| 735 |
+
"eval_stsb_spearman": 0.7986869561663991,
|
| 736 |
+
"step": 10750
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7,
|
| 740 |
+
"eval_avg_sts": 0.7680341988448937,
|
| 741 |
+
"eval_sickr_spearman": 0.7380161254151475,
|
| 742 |
+
"eval_stsb_spearman": 0.7980522722746398,
|
| 743 |
+
"step": 10875
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7,
|
| 747 |
+
"learning_rate": 8.881351593498018e-06,
|
| 748 |
+
"loss": 0.0001,
|
| 749 |
+
"step": 11000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.7,
|
| 753 |
+
"eval_avg_sts": 0.7603629068459727,
|
| 754 |
+
"eval_sickr_spearman": 0.7332741588634669,
|
| 755 |
+
"eval_stsb_spearman": 0.7874516548284786,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.71,
|
| 760 |
+
"eval_avg_sts": 0.7621832287379494,
|
| 761 |
+
"eval_sickr_spearman": 0.7349048083795262,
|
| 762 |
+
"eval_stsb_spearman": 0.7894616490963726,
|
| 763 |
+
"step": 11125
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.72,
|
| 767 |
+
"eval_avg_sts": 0.7621016943200358,
|
| 768 |
+
"eval_sickr_spearman": 0.7353910816282503,
|
| 769 |
+
"eval_stsb_spearman": 0.7888123070118214,
|
| 770 |
+
"step": 11250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.73,
|
| 774 |
+
"eval_avg_sts": 0.7610119893777948,
|
| 775 |
+
"eval_sickr_spearman": 0.7316196795433297,
|
| 776 |
+
"eval_stsb_spearman": 0.7904042992122599,
|
| 777 |
+
"step": 11375
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.74,
|
| 781 |
+
"learning_rate": 7.921413029566108e-06,
|
| 782 |
+
"loss": 0.0002,
|
| 783 |
+
"step": 11500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.74,
|
| 787 |
+
"eval_avg_sts": 0.7617757929098798,
|
| 788 |
+
"eval_sickr_spearman": 0.7318357714686997,
|
| 789 |
+
"eval_stsb_spearman": 0.7917158143510601,
|
| 790 |
+
"step": 11500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.74,
|
| 794 |
+
"eval_avg_sts": 0.7611330064890793,
|
| 795 |
+
"eval_sickr_spearman": 0.7338293983960914,
|
| 796 |
+
"eval_stsb_spearman": 0.7884366145820674,
|
| 797 |
+
"step": 11625
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.75,
|
| 801 |
+
"eval_avg_sts": 0.7621633110041289,
|
| 802 |
+
"eval_sickr_spearman": 0.7341784404102422,
|
| 803 |
+
"eval_stsb_spearman": 0.7901481815980157,
|
| 804 |
+
"step": 11750
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.76,
|
| 808 |
+
"eval_avg_sts": 0.7595196438845424,
|
| 809 |
+
"eval_sickr_spearman": 0.7331927461465293,
|
| 810 |
+
"eval_stsb_spearman": 0.7858465416225555,
|
| 811 |
+
"step": 11875
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.77,
|
| 815 |
+
"learning_rate": 6.961474465634199e-06,
|
| 816 |
+
"loss": 0.0003,
|
| 817 |
+
"step": 12000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.77,
|
| 821 |
+
"eval_avg_sts": 0.7635656813674752,
|
| 822 |
+
"eval_sickr_spearman": 0.7330679133138917,
|
| 823 |
+
"eval_stsb_spearman": 0.7940634494210588,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.78,
|
| 828 |
+
"eval_avg_sts": 0.7621975138758124,
|
| 829 |
+
"eval_sickr_spearman": 0.7340756058220633,
|
| 830 |
+
"eval_stsb_spearman": 0.7903194219295613,
|
| 831 |
+
"step": 12125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.78,
|
| 835 |
+
"eval_avg_sts": 0.7631065024648397,
|
| 836 |
+
"eval_sickr_spearman": 0.7321919220858634,
|
| 837 |
+
"eval_stsb_spearman": 0.794021082843816,
|
| 838 |
+
"step": 12250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.79,
|
| 842 |
+
"eval_avg_sts": 0.7628859990174557,
|
| 843 |
+
"eval_sickr_spearman": 0.7333722383726035,
|
| 844 |
+
"eval_stsb_spearman": 0.7923997596623078,
|
| 845 |
+
"step": 12375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8,
|
| 849 |
+
"learning_rate": 6.001535901702292e-06,
|
| 850 |
+
"loss": 0.0003,
|
| 851 |
+
"step": 12500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8,
|
| 855 |
+
"eval_avg_sts": 0.7629723942710446,
|
| 856 |
+
"eval_sickr_spearman": 0.7341199385286906,
|
| 857 |
+
"eval_stsb_spearman": 0.7918248500133985,
|
| 858 |
+
"step": 12500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.81,
|
| 862 |
+
"eval_avg_sts": 0.7576056121896545,
|
| 863 |
+
"eval_sickr_spearman": 0.7317101701384391,
|
| 864 |
+
"eval_stsb_spearman": 0.7835010542408699,
|
| 865 |
+
"step": 12625
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.82,
|
| 869 |
+
"eval_avg_sts": 0.7578230668275763,
|
| 870 |
+
"eval_sickr_spearman": 0.7317774136804525,
|
| 871 |
+
"eval_stsb_spearman": 0.7838687199747002,
|
| 872 |
+
"step": 12750
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.82,
|
| 876 |
+
"eval_avg_sts": 0.7592080133938004,
|
| 877 |
+
"eval_sickr_spearman": 0.7330049445399063,
|
| 878 |
+
"eval_stsb_spearman": 0.7854110822476944,
|
| 879 |
+
"step": 12875
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.83,
|
| 883 |
+
"learning_rate": 5.0415973377703825e-06,
|
| 884 |
+
"loss": 0.0002,
|
| 885 |
+
"step": 13000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.83,
|
| 889 |
+
"eval_avg_sts": 0.7649310794949764,
|
| 890 |
+
"eval_sickr_spearman": 0.7366114078224884,
|
| 891 |
+
"eval_stsb_spearman": 0.7932507511674645,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.84,
|
| 896 |
+
"eval_avg_sts": 0.7663911796944379,
|
| 897 |
+
"eval_sickr_spearman": 0.7376808683271094,
|
| 898 |
+
"eval_stsb_spearman": 0.7951014910617664,
|
| 899 |
+
"step": 13125
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.85,
|
| 903 |
+
"eval_avg_sts": 0.7666777328866676,
|
| 904 |
+
"eval_sickr_spearman": 0.7386608949208526,
|
| 905 |
+
"eval_stsb_spearman": 0.7946945708524826,
|
| 906 |
+
"step": 13250
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.86,
|
| 910 |
+
"eval_avg_sts": 0.767106492489369,
|
| 911 |
+
"eval_sickr_spearman": 0.7391275651024254,
|
| 912 |
+
"eval_stsb_spearman": 0.7950854198763126,
|
| 913 |
+
"step": 13375
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.86,
|
| 917 |
+
"learning_rate": 4.081658773838474e-06,
|
| 918 |
+
"loss": 0.0002,
|
| 919 |
+
"step": 13500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.86,
|
| 923 |
+
"eval_avg_sts": 0.7663641777603831,
|
| 924 |
+
"eval_sickr_spearman": 0.7384899041997329,
|
| 925 |
+
"eval_stsb_spearman": 0.7942384513210333,
|
| 926 |
+
"step": 13500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.87,
|
| 930 |
+
"eval_avg_sts": 0.7662444760718037,
|
| 931 |
+
"eval_sickr_spearman": 0.7383694902284276,
|
| 932 |
+
"eval_stsb_spearman": 0.7941194619151797,
|
| 933 |
+
"step": 13625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.88,
|
| 937 |
+
"eval_avg_sts": 0.766969739589136,
|
| 938 |
+
"eval_sickr_spearman": 0.7386586374590851,
|
| 939 |
+
"eval_stsb_spearman": 0.7952808417191867,
|
| 940 |
+
"step": 13750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.89,
|
| 944 |
+
"eval_avg_sts": 0.766963601043843,
|
| 945 |
+
"eval_sickr_spearman": 0.7385023442550055,
|
| 946 |
+
"eval_stsb_spearman": 0.7954248578326806,
|
| 947 |
+
"step": 13875
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9,
|
| 951 |
+
"learning_rate": 3.121720209906566e-06,
|
| 952 |
+
"loss": 0.0001,
|
| 953 |
+
"step": 14000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.9,
|
| 957 |
+
"eval_avg_sts": 0.7667105573155901,
|
| 958 |
+
"eval_sickr_spearman": 0.7384424975026136,
|
| 959 |
+
"eval_stsb_spearman": 0.7949786171285665,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9,
|
| 964 |
+
"eval_avg_sts": 0.7681149645930665,
|
| 965 |
+
"eval_sickr_spearman": 0.7393782874519323,
|
| 966 |
+
"eval_stsb_spearman": 0.7968516417342008,
|
| 967 |
+
"step": 14125
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.91,
|
| 971 |
+
"eval_avg_sts": 0.7680143099599532,
|
| 972 |
+
"eval_sickr_spearman": 0.7393469231426932,
|
| 973 |
+
"eval_stsb_spearman": 0.7966816967772132,
|
| 974 |
+
"step": 14250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.92,
|
| 978 |
+
"eval_avg_sts": 0.7676174458337446,
|
| 979 |
+
"eval_sickr_spearman": 0.7389574389411316,
|
| 980 |
+
"eval_stsb_spearman": 0.7962774527263575,
|
| 981 |
+
"step": 14375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.93,
|
| 985 |
+
"learning_rate": 2.1617816459746575e-06,
|
| 986 |
+
"loss": 0.0001,
|
| 987 |
+
"step": 14500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.93,
|
| 991 |
+
"eval_avg_sts": 0.7678090950201439,
|
| 992 |
+
"eval_sickr_spearman": 0.7391150770160515,
|
| 993 |
+
"eval_stsb_spearman": 0.7965031130242363,
|
| 994 |
+
"step": 14500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.94,
|
| 998 |
+
"eval_avg_sts": 0.7674776747079344,
|
| 999 |
+
"eval_sickr_spearman": 0.7389988417505713,
|
| 1000 |
+
"eval_stsb_spearman": 0.7959565076652975,
|
| 1001 |
+
"step": 14625
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.94,
|
| 1005 |
+
"eval_avg_sts": 0.7655137295819681,
|
| 1006 |
+
"eval_sickr_spearman": 0.7381747721431975,
|
| 1007 |
+
"eval_stsb_spearman": 0.7928526870207386,
|
| 1008 |
+
"step": 14750
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.95,
|
| 1012 |
+
"eval_avg_sts": 0.7657447555359481,
|
| 1013 |
+
"eval_sickr_spearman": 0.7382629572454379,
|
| 1014 |
+
"eval_stsb_spearman": 0.7932265538264583,
|
| 1015 |
+
"step": 14875
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.96,
|
| 1019 |
+
"learning_rate": 1.2018430820427492e-06,
|
| 1020 |
+
"loss": 0.0002,
|
| 1021 |
+
"step": 15000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.96,
|
| 1025 |
+
"eval_avg_sts": 0.7661720244295546,
|
| 1026 |
+
"eval_sickr_spearman": 0.7381314480897004,
|
| 1027 |
+
"eval_stsb_spearman": 0.7942126007694087,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.97,
|
| 1032 |
+
"eval_avg_sts": 0.7660620762670376,
|
| 1033 |
+
"eval_sickr_spearman": 0.7380774611316839,
|
| 1034 |
+
"eval_stsb_spearman": 0.7940466914023911,
|
| 1035 |
+
"step": 15125
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.98,
|
| 1039 |
+
"eval_avg_sts": 0.766592222198617,
|
| 1040 |
+
"eval_sickr_spearman": 0.738653161913521,
|
| 1041 |
+
"eval_stsb_spearman": 0.794531282483713,
|
| 1042 |
+
"step": 15250
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.98,
|
| 1046 |
+
"eval_avg_sts": 0.766138712195428,
|
| 1047 |
+
"eval_sickr_spearman": 0.7384393754810201,
|
| 1048 |
+
"eval_stsb_spearman": 0.7938380489098358,
|
| 1049 |
+
"step": 15375
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.99,
|
| 1053 |
+
"learning_rate": 2.4190451811084087e-07,
|
| 1054 |
+
"loss": 0.0002,
|
| 1055 |
+
"step": 15500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.99,
|
| 1059 |
+
"eval_avg_sts": 0.7661330517073972,
|
| 1060 |
+
"eval_sickr_spearman": 0.7384201630404448,
|
| 1061 |
+
"eval_stsb_spearman": 0.7938459403743495,
|
| 1062 |
+
"step": 15500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.0,
|
| 1066 |
+
"eval_avg_sts": 0.7660975303030011,
|
| 1067 |
+
"eval_sickr_spearman": 0.7383983569203919,
|
| 1068 |
+
"eval_stsb_spearman": 0.7937967036856103,
|
| 1069 |
+
"step": 15625
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.0,
|
| 1073 |
+
"step": 15626,
|
| 1074 |
+
"train_runtime": 3834.5201,
|
| 1075 |
+
"train_samples_per_second": 4.075
|
| 1076 |
+
}
|
| 1077 |
+
],
|
| 1078 |
+
"max_steps": 15626,
|
| 1079 |
+
"num_train_epochs": 1,
|
| 1080 |
+
"total_flos": 42267980696739840,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe75f29c0b44ce5866741ac63b70d0a788bcb1378b5a9b0e0c0e5a4e1cbcd5d
|
| 3 |
+
size 2159
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|