root
commited on
Commit
·
b46170e
1
Parent(s):
4ac2976
model
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/esimcse-bert-base-uncased-0.1-bpe-0.32-160-bs64",
|
| 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 = 1.0
|
| 2 |
+
eval_CR = 85.45
|
| 3 |
+
eval_MPQA = 87.65
|
| 4 |
+
eval_MR = 79.42
|
| 5 |
+
eval_MRPC = 74.8
|
| 6 |
+
eval_SST2 = 85.67
|
| 7 |
+
eval_SUBJ = 93.58
|
| 8 |
+
eval_TREC = 80.59
|
| 9 |
+
eval_avg_sts = 0.8007774495654907
|
| 10 |
+
eval_avg_transfer = 83.88
|
| 11 |
+
eval_sickr_spearman = 0.7530334335285849
|
| 12 |
+
eval_stsb_spearman = 0.8485214656023966
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f7f26b801f6a02dcc216f733cd609653f6b64e0a9697a1c342893c7fdffe68
|
| 3 |
+
size 875983405
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc1e5ef843c14b07bd7b46a71d0177ac4dc043ca29aa78b597f1d6dde99486ca
|
| 3 |
+
size 878402769
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:032b000ce609f915a2c18c31df114adb1cd8fcc27a455360e357e7fb494712b6
|
| 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 = 4555.3265
|
| 3 |
+
train_samples_per_second = 3.43
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8485214656023966,
|
| 3 |
+
"best_model_checkpoint": "result/esimcse-bert-base-uncased-0.1-bpe-0.32-160-bs64",
|
| 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": 0.6100880461913585,
|
| 13 |
+
"eval_sickr_spearman": 0.5832078028364882,
|
| 14 |
+
"eval_stsb_spearman": 0.6369682895462287,
|
| 15 |
+
"step": 125
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_avg_sts": 0.6397205453652646,
|
| 20 |
+
"eval_sickr_spearman": 0.616963004242962,
|
| 21 |
+
"eval_stsb_spearman": 0.6624780864875672,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.02,
|
| 26 |
+
"eval_avg_sts": 0.6789809731427074,
|
| 27 |
+
"eval_sickr_spearman": 0.6587511191783517,
|
| 28 |
+
"eval_stsb_spearman": 0.6992108271070633,
|
| 29 |
+
"step": 375
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 2.9040061436068092e-05,
|
| 34 |
+
"loss": 0.0108,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.03,
|
| 39 |
+
"eval_avg_sts": 0.7335141964825347,
|
| 40 |
+
"eval_sickr_spearman": 0.7049946471142421,
|
| 41 |
+
"eval_stsb_spearman": 0.7620337458508273,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"eval_avg_sts": 0.7519583861186683,
|
| 47 |
+
"eval_sickr_spearman": 0.7213448663236887,
|
| 48 |
+
"eval_stsb_spearman": 0.782571905913648,
|
| 49 |
+
"step": 625
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_avg_sts": 0.7678435373865832,
|
| 54 |
+
"eval_sickr_spearman": 0.7283978012899625,
|
| 55 |
+
"eval_stsb_spearman": 0.8072892734832039,
|
| 56 |
+
"step": 750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_avg_sts": 0.7606834842782872,
|
| 61 |
+
"eval_sickr_spearman": 0.719232746669049,
|
| 62 |
+
"eval_stsb_spearman": 0.8021342218875254,
|
| 63 |
+
"step": 875
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 2.8080122872136184e-05,
|
| 68 |
+
"loss": 0.0007,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"eval_avg_sts": 0.7725764209069759,
|
| 74 |
+
"eval_sickr_spearman": 0.7352987658512863,
|
| 75 |
+
"eval_stsb_spearman": 0.8098540759626653,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_avg_sts": 0.749297683848744,
|
| 81 |
+
"eval_sickr_spearman": 0.7265425039347125,
|
| 82 |
+
"eval_stsb_spearman": 0.7720528637627754,
|
| 83 |
+
"step": 1125
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_avg_sts": 0.7274946000391853,
|
| 88 |
+
"eval_sickr_spearman": 0.7107656319831328,
|
| 89 |
+
"eval_stsb_spearman": 0.7442235680952377,
|
| 90 |
+
"step": 1250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09,
|
| 94 |
+
"eval_avg_sts": 0.7476475148023185,
|
| 95 |
+
"eval_sickr_spearman": 0.7236732700281041,
|
| 96 |
+
"eval_stsb_spearman": 0.7716217595765328,
|
| 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": 0.7566770100403266,
|
| 108 |
+
"eval_sickr_spearman": 0.7318386053036846,
|
| 109 |
+
"eval_stsb_spearman": 0.7815154147769687,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1,
|
| 114 |
+
"eval_avg_sts": 0.7600955301789452,
|
| 115 |
+
"eval_sickr_spearman": 0.7316815916330834,
|
| 116 |
+
"eval_stsb_spearman": 0.7885094687248068,
|
| 117 |
+
"step": 1625
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_avg_sts": 0.7270610894602345,
|
| 122 |
+
"eval_sickr_spearman": 0.6906233092840458,
|
| 123 |
+
"eval_stsb_spearman": 0.7634988696364233,
|
| 124 |
+
"step": 1750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12,
|
| 128 |
+
"eval_avg_sts": 0.7308078942978946,
|
| 129 |
+
"eval_sickr_spearman": 0.6979846039215525,
|
| 130 |
+
"eval_stsb_spearman": 0.7636311846742367,
|
| 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": 0.7009937398682455,
|
| 142 |
+
"eval_sickr_spearman": 0.676284680633929,
|
| 143 |
+
"eval_stsb_spearman": 0.7257027991025622,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"eval_avg_sts": 0.7145112612407412,
|
| 149 |
+
"eval_sickr_spearman": 0.6811648326644469,
|
| 150 |
+
"eval_stsb_spearman": 0.7478576898170354,
|
| 151 |
+
"step": 2125
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.14,
|
| 155 |
+
"eval_avg_sts": 0.7269807482138698,
|
| 156 |
+
"eval_sickr_spearman": 0.6930580538470452,
|
| 157 |
+
"eval_stsb_spearman": 0.7609034425806944,
|
| 158 |
+
"step": 2250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"eval_avg_sts": 0.7876865693494822,
|
| 163 |
+
"eval_sickr_spearman": 0.7498401337805735,
|
| 164 |
+
"eval_stsb_spearman": 0.825533004918391,
|
| 165 |
+
"step": 2375
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 2.5200307180340456e-05,
|
| 170 |
+
"loss": 0.0006,
|
| 171 |
+
"step": 2500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"eval_avg_sts": 0.7800273423845525,
|
| 176 |
+
"eval_sickr_spearman": 0.7402713297209711,
|
| 177 |
+
"eval_stsb_spearman": 0.8197833550481338,
|
| 178 |
+
"step": 2500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"eval_avg_sts": 0.7774661815337005,
|
| 183 |
+
"eval_sickr_spearman": 0.7407253196917641,
|
| 184 |
+
"eval_stsb_spearman": 0.8142070433756369,
|
| 185 |
+
"step": 2625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.18,
|
| 189 |
+
"eval_avg_sts": 0.795139063492616,
|
| 190 |
+
"eval_sickr_spearman": 0.7583184877442262,
|
| 191 |
+
"eval_stsb_spearman": 0.8319596392410058,
|
| 192 |
+
"step": 2750
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18,
|
| 196 |
+
"eval_avg_sts": 0.8007774495654907,
|
| 197 |
+
"eval_sickr_spearman": 0.7530334335285849,
|
| 198 |
+
"eval_stsb_spearman": 0.8485214656023966,
|
| 199 |
+
"step": 2875
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.19,
|
| 203 |
+
"learning_rate": 2.424036861640855e-05,
|
| 204 |
+
"loss": 0.0005,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"eval_avg_sts": 0.7910581147340385,
|
| 210 |
+
"eval_sickr_spearman": 0.7508507561859327,
|
| 211 |
+
"eval_stsb_spearman": 0.8312654732821445,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"eval_avg_sts": 0.7798469609404326,
|
| 217 |
+
"eval_sickr_spearman": 0.7498414786514137,
|
| 218 |
+
"eval_stsb_spearman": 0.8098524432294515,
|
| 219 |
+
"step": 3125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"eval_avg_sts": 0.7100086424191657,
|
| 224 |
+
"eval_sickr_spearman": 0.6737912900960736,
|
| 225 |
+
"eval_stsb_spearman": 0.7462259947422578,
|
| 226 |
+
"step": 3250
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22,
|
| 230 |
+
"eval_avg_sts": 0.7098691907547254,
|
| 231 |
+
"eval_sickr_spearman": 0.6749191564200434,
|
| 232 |
+
"eval_stsb_spearman": 0.7448192250894073,
|
| 233 |
+
"step": 3375
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 2.3280430052476642e-05,
|
| 238 |
+
"loss": 0.0005,
|
| 239 |
+
"step": 3500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_avg_sts": 0.7558791570716834,
|
| 244 |
+
"eval_sickr_spearman": 0.7183665057546127,
|
| 245 |
+
"eval_stsb_spearman": 0.793391808388754,
|
| 246 |
+
"step": 3500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23,
|
| 250 |
+
"eval_avg_sts": 0.7724894260205434,
|
| 251 |
+
"eval_sickr_spearman": 0.7317967221832306,
|
| 252 |
+
"eval_stsb_spearman": 0.8131821298578562,
|
| 253 |
+
"step": 3625
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.24,
|
| 257 |
+
"eval_avg_sts": 0.7735778094480449,
|
| 258 |
+
"eval_sickr_spearman": 0.7319867332205197,
|
| 259 |
+
"eval_stsb_spearman": 0.8151688856755701,
|
| 260 |
+
"step": 3750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"eval_avg_sts": 0.7753994732757892,
|
| 265 |
+
"eval_sickr_spearman": 0.7344932362490677,
|
| 266 |
+
"eval_stsb_spearman": 0.8163057103025108,
|
| 267 |
+
"step": 3875
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 2.2320491488544734e-05,
|
| 272 |
+
"loss": 0.0005,
|
| 273 |
+
"step": 4000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_avg_sts": 0.7645563589773194,
|
| 278 |
+
"eval_sickr_spearman": 0.7288089955493742,
|
| 279 |
+
"eval_stsb_spearman": 0.8003037224052648,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.26,
|
| 284 |
+
"eval_avg_sts": 0.77217921247597,
|
| 285 |
+
"eval_sickr_spearman": 0.7348872353741646,
|
| 286 |
+
"eval_stsb_spearman": 0.8094711895777754,
|
| 287 |
+
"step": 4125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27,
|
| 291 |
+
"eval_avg_sts": 0.7459204678567914,
|
| 292 |
+
"eval_sickr_spearman": 0.7152080285551439,
|
| 293 |
+
"eval_stsb_spearman": 0.7766329071584389,
|
| 294 |
+
"step": 4250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.28,
|
| 298 |
+
"eval_avg_sts": 0.7630540681359231,
|
| 299 |
+
"eval_sickr_spearman": 0.7283370419466434,
|
| 300 |
+
"eval_stsb_spearman": 0.7977710943252029,
|
| 301 |
+
"step": 4375
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.29,
|
| 305 |
+
"learning_rate": 2.1360552924612826e-05,
|
| 306 |
+
"loss": 0.0005,
|
| 307 |
+
"step": 4500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.29,
|
| 311 |
+
"eval_avg_sts": 0.7261107657045172,
|
| 312 |
+
"eval_sickr_spearman": 0.6958098517106376,
|
| 313 |
+
"eval_stsb_spearman": 0.7564116796983967,
|
| 314 |
+
"step": 4500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"eval_avg_sts": 0.7402966337518628,
|
| 319 |
+
"eval_sickr_spearman": 0.7071302059463835,
|
| 320 |
+
"eval_stsb_spearman": 0.7734630615573422,
|
| 321 |
+
"step": 4625
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"eval_avg_sts": 0.7563164963384006,
|
| 326 |
+
"eval_sickr_spearman": 0.7236546819918475,
|
| 327 |
+
"eval_stsb_spearman": 0.7889783106849536,
|
| 328 |
+
"step": 4750
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"eval_avg_sts": 0.7653071609134422,
|
| 333 |
+
"eval_sickr_spearman": 0.7303088147228807,
|
| 334 |
+
"eval_stsb_spearman": 0.8003055071040037,
|
| 335 |
+
"step": 4875
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.32,
|
| 339 |
+
"learning_rate": 2.0400614360680917e-05,
|
| 340 |
+
"loss": 0.0003,
|
| 341 |
+
"step": 5000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.32,
|
| 345 |
+
"eval_avg_sts": 0.7611963687067248,
|
| 346 |
+
"eval_sickr_spearman": 0.7255880779180358,
|
| 347 |
+
"eval_stsb_spearman": 0.7968046594954138,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"eval_avg_sts": 0.7744538434517783,
|
| 353 |
+
"eval_sickr_spearman": 0.7411195109412667,
|
| 354 |
+
"eval_stsb_spearman": 0.8077881759622897,
|
| 355 |
+
"step": 5125
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.34,
|
| 359 |
+
"eval_avg_sts": 0.7765902002597658,
|
| 360 |
+
"eval_sickr_spearman": 0.7444951367503373,
|
| 361 |
+
"eval_stsb_spearman": 0.8086852637691941,
|
| 362 |
+
"step": 5250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.34,
|
| 366 |
+
"eval_avg_sts": 0.7699546022654327,
|
| 367 |
+
"eval_sickr_spearman": 0.7376793313318634,
|
| 368 |
+
"eval_stsb_spearman": 0.8022298731990021,
|
| 369 |
+
"step": 5375
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.35,
|
| 373 |
+
"learning_rate": 1.944067579674901e-05,
|
| 374 |
+
"loss": 0.0005,
|
| 375 |
+
"step": 5500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.35,
|
| 379 |
+
"eval_avg_sts": 0.7734752595558289,
|
| 380 |
+
"eval_sickr_spearman": 0.7410133141759871,
|
| 381 |
+
"eval_stsb_spearman": 0.8059372049356706,
|
| 382 |
+
"step": 5500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36,
|
| 386 |
+
"eval_avg_sts": 0.7626449726319405,
|
| 387 |
+
"eval_sickr_spearman": 0.7365559319003274,
|
| 388 |
+
"eval_stsb_spearman": 0.7887340133635536,
|
| 389 |
+
"step": 5625
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.37,
|
| 393 |
+
"eval_avg_sts": 0.7687278256378415,
|
| 394 |
+
"eval_sickr_spearman": 0.7398524504853293,
|
| 395 |
+
"eval_stsb_spearman": 0.7976032007903536,
|
| 396 |
+
"step": 5750
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38,
|
| 400 |
+
"eval_avg_sts": 0.7693941323907878,
|
| 401 |
+
"eval_sickr_spearman": 0.7396455325003339,
|
| 402 |
+
"eval_stsb_spearman": 0.7991427322812418,
|
| 403 |
+
"step": 5875
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.38,
|
| 407 |
+
"learning_rate": 1.84807372328171e-05,
|
| 408 |
+
"loss": 0.0005,
|
| 409 |
+
"step": 6000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.38,
|
| 413 |
+
"eval_avg_sts": 0.7574432337471098,
|
| 414 |
+
"eval_sickr_spearman": 0.7347453034694149,
|
| 415 |
+
"eval_stsb_spearman": 0.7801411640248046,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.39,
|
| 420 |
+
"eval_avg_sts": 0.7708101615966496,
|
| 421 |
+
"eval_sickr_spearman": 0.7320090676826885,
|
| 422 |
+
"eval_stsb_spearman": 0.8096112555106109,
|
| 423 |
+
"step": 6125
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4,
|
| 427 |
+
"eval_avg_sts": 0.7635841238166383,
|
| 428 |
+
"eval_sickr_spearman": 0.7288792650507782,
|
| 429 |
+
"eval_stsb_spearman": 0.7982889825824986,
|
| 430 |
+
"step": 6250
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.41,
|
| 434 |
+
"eval_avg_sts": 0.7627376362894998,
|
| 435 |
+
"eval_sickr_spearman": 0.7300567955336349,
|
| 436 |
+
"eval_stsb_spearman": 0.7954184770453646,
|
| 437 |
+
"step": 6375
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.42,
|
| 441 |
+
"learning_rate": 1.7520798668885192e-05,
|
| 442 |
+
"loss": 0.0005,
|
| 443 |
+
"step": 6500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.42,
|
| 447 |
+
"eval_avg_sts": 0.7591781252494068,
|
| 448 |
+
"eval_sickr_spearman": 0.7227859434601362,
|
| 449 |
+
"eval_stsb_spearman": 0.7955703070386773,
|
| 450 |
+
"step": 6500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.42,
|
| 454 |
+
"eval_avg_sts": 0.7527229076746123,
|
| 455 |
+
"eval_sickr_spearman": 0.7119316830327459,
|
| 456 |
+
"eval_stsb_spearman": 0.7935141323164787,
|
| 457 |
+
"step": 6625
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.43,
|
| 461 |
+
"eval_avg_sts": 0.7584939992660324,
|
| 462 |
+
"eval_sickr_spearman": 0.7191479717750108,
|
| 463 |
+
"eval_stsb_spearman": 0.7978400267570542,
|
| 464 |
+
"step": 6750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"eval_avg_sts": 0.7630465793985837,
|
| 469 |
+
"eval_sickr_spearman": 0.7249168913065396,
|
| 470 |
+
"eval_stsb_spearman": 0.8011762674906276,
|
| 471 |
+
"step": 6875
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.45,
|
| 475 |
+
"learning_rate": 1.6560860104953284e-05,
|
| 476 |
+
"loss": 0.0004,
|
| 477 |
+
"step": 7000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.45,
|
| 481 |
+
"eval_avg_sts": 0.7655527346776364,
|
| 482 |
+
"eval_sickr_spearman": 0.7304577591684402,
|
| 483 |
+
"eval_stsb_spearman": 0.8006477101868326,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"eval_avg_sts": 0.7395454013504682,
|
| 489 |
+
"eval_sickr_spearman": 0.7105281181865213,
|
| 490 |
+
"eval_stsb_spearman": 0.7685626845144151,
|
| 491 |
+
"step": 7125
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"eval_avg_sts": 0.7229578267812158,
|
| 496 |
+
"eval_sickr_spearman": 0.6942447582702768,
|
| 497 |
+
"eval_stsb_spearman": 0.7516708952921549,
|
| 498 |
+
"step": 7250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"eval_avg_sts": 0.7452003408688526,
|
| 503 |
+
"eval_sickr_spearman": 0.7146070634139502,
|
| 504 |
+
"eval_stsb_spearman": 0.775793618323755,
|
| 505 |
+
"step": 7375
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.48,
|
| 509 |
+
"learning_rate": 1.5600921541021372e-05,
|
| 510 |
+
"loss": 0.0005,
|
| 511 |
+
"step": 7500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.48,
|
| 515 |
+
"eval_avg_sts": 0.7600508627663232,
|
| 516 |
+
"eval_sickr_spearman": 0.7285831533104121,
|
| 517 |
+
"eval_stsb_spearman": 0.7915185722222341,
|
| 518 |
+
"step": 7500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.49,
|
| 522 |
+
"eval_avg_sts": 0.7674997774484139,
|
| 523 |
+
"eval_sickr_spearman": 0.7341920332119493,
|
| 524 |
+
"eval_stsb_spearman": 0.8008075216848786,
|
| 525 |
+
"step": 7625
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5,
|
| 529 |
+
"eval_avg_sts": 0.7668269678433662,
|
| 530 |
+
"eval_sickr_spearman": 0.7276831399805795,
|
| 531 |
+
"eval_stsb_spearman": 0.8059707957061529,
|
| 532 |
+
"step": 7750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5,
|
| 536 |
+
"eval_avg_sts": 0.7759267074313813,
|
| 537 |
+
"eval_sickr_spearman": 0.7360665910388758,
|
| 538 |
+
"eval_stsb_spearman": 0.8157868238238867,
|
| 539 |
+
"step": 7875
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.51,
|
| 543 |
+
"learning_rate": 1.4640982977089467e-05,
|
| 544 |
+
"loss": 0.0004,
|
| 545 |
+
"step": 8000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.51,
|
| 549 |
+
"eval_avg_sts": 0.7694891376849935,
|
| 550 |
+
"eval_sickr_spearman": 0.7355848390914517,
|
| 551 |
+
"eval_stsb_spearman": 0.8033934362785352,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.52,
|
| 556 |
+
"eval_avg_sts": 0.7612899584011228,
|
| 557 |
+
"eval_sickr_spearman": 0.7261187735578255,
|
| 558 |
+
"eval_stsb_spearman": 0.79646114324442,
|
| 559 |
+
"step": 8125
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.53,
|
| 563 |
+
"eval_avg_sts": 0.7590520798954239,
|
| 564 |
+
"eval_sickr_spearman": 0.7263883721301976,
|
| 565 |
+
"eval_stsb_spearman": 0.7917157876606503,
|
| 566 |
+
"step": 8250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.54,
|
| 570 |
+
"eval_avg_sts": 0.7681689830272878,
|
| 571 |
+
"eval_sickr_spearman": 0.7343635698999812,
|
| 572 |
+
"eval_stsb_spearman": 0.8019743961545942,
|
| 573 |
+
"step": 8375
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.54,
|
| 577 |
+
"learning_rate": 1.368104441315756e-05,
|
| 578 |
+
"loss": 0.0003,
|
| 579 |
+
"step": 8500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.54,
|
| 583 |
+
"eval_avg_sts": 0.7645627255636145,
|
| 584 |
+
"eval_sickr_spearman": 0.7345889622342338,
|
| 585 |
+
"eval_stsb_spearman": 0.7945364888929952,
|
| 586 |
+
"step": 8500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.55,
|
| 590 |
+
"eval_avg_sts": 0.7519813686443279,
|
| 591 |
+
"eval_sickr_spearman": 0.7268361660889052,
|
| 592 |
+
"eval_stsb_spearman": 0.7771265711997505,
|
| 593 |
+
"step": 8625
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.56,
|
| 597 |
+
"eval_avg_sts": 0.7570879059121025,
|
| 598 |
+
"eval_sickr_spearman": 0.7295248030541064,
|
| 599 |
+
"eval_stsb_spearman": 0.7846510087700986,
|
| 600 |
+
"step": 8750
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.57,
|
| 604 |
+
"eval_avg_sts": 0.7651801271677768,
|
| 605 |
+
"eval_sickr_spearman": 0.7324815976586366,
|
| 606 |
+
"eval_stsb_spearman": 0.797878656676917,
|
| 607 |
+
"step": 8875
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.58,
|
| 611 |
+
"learning_rate": 1.2721105849225649e-05,
|
| 612 |
+
"loss": 0.0004,
|
| 613 |
+
"step": 9000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.58,
|
| 617 |
+
"eval_avg_sts": 0.7712013823080692,
|
| 618 |
+
"eval_sickr_spearman": 0.7386502800474348,
|
| 619 |
+
"eval_stsb_spearman": 0.8037524845687036,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.58,
|
| 624 |
+
"eval_avg_sts": 0.7620043628899366,
|
| 625 |
+
"eval_sickr_spearman": 0.7352328191490116,
|
| 626 |
+
"eval_stsb_spearman": 0.7887759066308615,
|
| 627 |
+
"step": 9125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.59,
|
| 631 |
+
"eval_avg_sts": 0.7406795525094927,
|
| 632 |
+
"eval_sickr_spearman": 0.7231166856246392,
|
| 633 |
+
"eval_stsb_spearman": 0.7582424193943462,
|
| 634 |
+
"step": 9250
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6,
|
| 638 |
+
"eval_avg_sts": 0.7653971603316696,
|
| 639 |
+
"eval_sickr_spearman": 0.7354289301361836,
|
| 640 |
+
"eval_stsb_spearman": 0.7953653905271556,
|
| 641 |
+
"step": 9375
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.61,
|
| 645 |
+
"learning_rate": 1.176116728529374e-05,
|
| 646 |
+
"loss": 0.0005,
|
| 647 |
+
"step": 9500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.61,
|
| 651 |
+
"eval_avg_sts": 0.7646069433356613,
|
| 652 |
+
"eval_sickr_spearman": 0.7343778655434133,
|
| 653 |
+
"eval_stsb_spearman": 0.7948360211279091,
|
| 654 |
+
"step": 9500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.62,
|
| 658 |
+
"eval_avg_sts": 0.7593680988773044,
|
| 659 |
+
"eval_sickr_spearman": 0.732813492569574,
|
| 660 |
+
"eval_stsb_spearman": 0.7859227051850348,
|
| 661 |
+
"step": 9625
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.62,
|
| 665 |
+
"eval_avg_sts": 0.7587276133400723,
|
| 666 |
+
"eval_sickr_spearman": 0.7302601592171238,
|
| 667 |
+
"eval_stsb_spearman": 0.7871950674630208,
|
| 668 |
+
"step": 9750
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.63,
|
| 672 |
+
"eval_avg_sts": 0.7470220132260748,
|
| 673 |
+
"eval_sickr_spearman": 0.716697953321754,
|
| 674 |
+
"eval_stsb_spearman": 0.7773460731303955,
|
| 675 |
+
"step": 9875
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.64,
|
| 679 |
+
"learning_rate": 1.0801228721361832e-05,
|
| 680 |
+
"loss": 0.0003,
|
| 681 |
+
"step": 10000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.64,
|
| 685 |
+
"eval_avg_sts": 0.7602204587910995,
|
| 686 |
+
"eval_sickr_spearman": 0.7292309487755081,
|
| 687 |
+
"eval_stsb_spearman": 0.7912099688066908,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.65,
|
| 692 |
+
"eval_avg_sts": 0.7763161485207313,
|
| 693 |
+
"eval_sickr_spearman": 0.7364229337804452,
|
| 694 |
+
"eval_stsb_spearman": 0.8162093632610175,
|
| 695 |
+
"step": 10125
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.66,
|
| 699 |
+
"eval_avg_sts": 0.7776963975561555,
|
| 700 |
+
"eval_sickr_spearman": 0.7362918569046206,
|
| 701 |
+
"eval_stsb_spearman": 0.8191009382076904,
|
| 702 |
+
"step": 10250
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.66,
|
| 706 |
+
"eval_avg_sts": 0.7769543328958908,
|
| 707 |
+
"eval_sickr_spearman": 0.7370006998996443,
|
| 708 |
+
"eval_stsb_spearman": 0.8169079658921373,
|
| 709 |
+
"step": 10375
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.67,
|
| 713 |
+
"learning_rate": 9.841290157429926e-06,
|
| 714 |
+
"loss": 0.0005,
|
| 715 |
+
"step": 10500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.67,
|
| 719 |
+
"eval_avg_sts": 0.7786140293258825,
|
| 720 |
+
"eval_sickr_spearman": 0.7414595711394486,
|
| 721 |
+
"eval_stsb_spearman": 0.8157684875123163,
|
| 722 |
+
"step": 10500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.68,
|
| 726 |
+
"eval_avg_sts": 0.77959121226111,
|
| 727 |
+
"eval_sickr_spearman": 0.7405204670441307,
|
| 728 |
+
"eval_stsb_spearman": 0.8186619574780892,
|
| 729 |
+
"step": 10625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.69,
|
| 733 |
+
"eval_avg_sts": 0.7779319076421938,
|
| 734 |
+
"eval_sickr_spearman": 0.7420048682340755,
|
| 735 |
+
"eval_stsb_spearman": 0.813858947050312,
|
| 736 |
+
"step": 10750
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7,
|
| 740 |
+
"eval_avg_sts": 0.7775449329956121,
|
| 741 |
+
"eval_sickr_spearman": 0.7400306458716649,
|
| 742 |
+
"eval_stsb_spearman": 0.8150592201195593,
|
| 743 |
+
"step": 10875
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7,
|
| 747 |
+
"learning_rate": 8.881351593498018e-06,
|
| 748 |
+
"loss": 0.0004,
|
| 749 |
+
"step": 11000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.7,
|
| 753 |
+
"eval_avg_sts": 0.778286005470163,
|
| 754 |
+
"eval_sickr_spearman": 0.7363517997192154,
|
| 755 |
+
"eval_stsb_spearman": 0.8202202112211106,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.71,
|
| 760 |
+
"eval_avg_sts": 0.777618581685105,
|
| 761 |
+
"eval_sickr_spearman": 0.7384216520045894,
|
| 762 |
+
"eval_stsb_spearman": 0.8168155113656206,
|
| 763 |
+
"step": 11125
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.72,
|
| 767 |
+
"eval_avg_sts": 0.7762628934419535,
|
| 768 |
+
"eval_sickr_spearman": 0.7332475976643716,
|
| 769 |
+
"eval_stsb_spearman": 0.8192781892195354,
|
| 770 |
+
"step": 11250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.73,
|
| 774 |
+
"eval_avg_sts": 0.7770120788854875,
|
| 775 |
+
"eval_sickr_spearman": 0.733883289291905,
|
| 776 |
+
"eval_stsb_spearman": 0.8201408684790699,
|
| 777 |
+
"step": 11375
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.74,
|
| 781 |
+
"learning_rate": 7.921413029566108e-06,
|
| 782 |
+
"loss": 0.0004,
|
| 783 |
+
"step": 11500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.74,
|
| 787 |
+
"eval_avg_sts": 0.7750375125081059,
|
| 788 |
+
"eval_sickr_spearman": 0.7312441243611851,
|
| 789 |
+
"eval_stsb_spearman": 0.8188309006550266,
|
| 790 |
+
"step": 11500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.74,
|
| 794 |
+
"eval_avg_sts": 0.7713758693823137,
|
| 795 |
+
"eval_sickr_spearman": 0.7301794189356065,
|
| 796 |
+
"eval_stsb_spearman": 0.812572319829021,
|
| 797 |
+
"step": 11625
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.75,
|
| 801 |
+
"eval_avg_sts": 0.7729201610115823,
|
| 802 |
+
"eval_sickr_spearman": 0.7338767570621094,
|
| 803 |
+
"eval_stsb_spearman": 0.8119635649610553,
|
| 804 |
+
"step": 11750
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.76,
|
| 808 |
+
"eval_avg_sts": 0.7721840581068564,
|
| 809 |
+
"eval_sickr_spearman": 0.7340904474324076,
|
| 810 |
+
"eval_stsb_spearman": 0.8102776687813052,
|
| 811 |
+
"step": 11875
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.77,
|
| 815 |
+
"learning_rate": 6.961474465634199e-06,
|
| 816 |
+
"loss": 0.0006,
|
| 817 |
+
"step": 12000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.77,
|
| 821 |
+
"eval_avg_sts": 0.762864859686734,
|
| 822 |
+
"eval_sickr_spearman": 0.7334133049643331,
|
| 823 |
+
"eval_stsb_spearman": 0.7923164144091348,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.78,
|
| 828 |
+
"eval_avg_sts": 0.7653804206448536,
|
| 829 |
+
"eval_sickr_spearman": 0.7362588595379327,
|
| 830 |
+
"eval_stsb_spearman": 0.7945019817517746,
|
| 831 |
+
"step": 12125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.78,
|
| 835 |
+
"eval_avg_sts": 0.770245273378219,
|
| 836 |
+
"eval_sickr_spearman": 0.7383542643692718,
|
| 837 |
+
"eval_stsb_spearman": 0.8021362823871663,
|
| 838 |
+
"step": 12250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.79,
|
| 842 |
+
"eval_avg_sts": 0.769823742960263,
|
| 843 |
+
"eval_sickr_spearman": 0.7377583424937291,
|
| 844 |
+
"eval_stsb_spearman": 0.8018891434267971,
|
| 845 |
+
"step": 12375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8,
|
| 849 |
+
"learning_rate": 6.001535901702292e-06,
|
| 850 |
+
"loss": 0.0006,
|
| 851 |
+
"step": 12500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8,
|
| 855 |
+
"eval_avg_sts": 0.7643310786346977,
|
| 856 |
+
"eval_sickr_spearman": 0.7368435421357389,
|
| 857 |
+
"eval_stsb_spearman": 0.7918186151336565,
|
| 858 |
+
"step": 12500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.81,
|
| 862 |
+
"eval_avg_sts": 0.7478178784310427,
|
| 863 |
+
"eval_sickr_spearman": 0.7295915662851054,
|
| 864 |
+
"eval_stsb_spearman": 0.76604419057698,
|
| 865 |
+
"step": 12625
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.82,
|
| 869 |
+
"eval_avg_sts": 0.7521749358657968,
|
| 870 |
+
"eval_sickr_spearman": 0.7287060648989924,
|
| 871 |
+
"eval_stsb_spearman": 0.7756438068326013,
|
| 872 |
+
"step": 12750
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.82,
|
| 876 |
+
"eval_avg_sts": 0.7552169285539614,
|
| 877 |
+
"eval_sickr_spearman": 0.7275865559866728,
|
| 878 |
+
"eval_stsb_spearman": 0.7828473011212499,
|
| 879 |
+
"step": 12875
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.83,
|
| 883 |
+
"learning_rate": 5.0415973377703825e-06,
|
| 884 |
+
"loss": 0.0006,
|
| 885 |
+
"step": 13000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.83,
|
| 889 |
+
"eval_avg_sts": 0.7586663192427485,
|
| 890 |
+
"eval_sickr_spearman": 0.7291622643004515,
|
| 891 |
+
"eval_stsb_spearman": 0.7881703741850457,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.84,
|
| 896 |
+
"eval_avg_sts": 0.7590819682264265,
|
| 897 |
+
"eval_sickr_spearman": 0.7291833019228814,
|
| 898 |
+
"eval_stsb_spearman": 0.7889806345299715,
|
| 899 |
+
"step": 13125
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.85,
|
| 903 |
+
"eval_avg_sts": 0.7599496756491293,
|
| 904 |
+
"eval_sickr_spearman": 0.7258233342528796,
|
| 905 |
+
"eval_stsb_spearman": 0.794076017045379,
|
| 906 |
+
"step": 13250
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.86,
|
| 910 |
+
"eval_avg_sts": 0.7620834946535875,
|
| 911 |
+
"eval_sickr_spearman": 0.7272929418635816,
|
| 912 |
+
"eval_stsb_spearman": 0.7968740474435934,
|
| 913 |
+
"step": 13375
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.86,
|
| 917 |
+
"learning_rate": 4.081658773838474e-06,
|
| 918 |
+
"loss": 0.0005,
|
| 919 |
+
"step": 13500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.86,
|
| 923 |
+
"eval_avg_sts": 0.7638553003387081,
|
| 924 |
+
"eval_sickr_spearman": 0.7278715725426066,
|
| 925 |
+
"eval_stsb_spearman": 0.7998390281348094,
|
| 926 |
+
"step": 13500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.87,
|
| 930 |
+
"eval_avg_sts": 0.764322584988894,
|
| 931 |
+
"eval_sickr_spearman": 0.7266260300201134,
|
| 932 |
+
"eval_stsb_spearman": 0.8020191399576747,
|
| 933 |
+
"step": 13625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.88,
|
| 937 |
+
"eval_avg_sts": 0.7648945618293426,
|
| 938 |
+
"eval_sickr_spearman": 0.7271069174077117,
|
| 939 |
+
"eval_stsb_spearman": 0.8026822062509734,
|
| 940 |
+
"step": 13750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.89,
|
| 944 |
+
"eval_avg_sts": 0.7669716790989545,
|
| 945 |
+
"eval_sickr_spearman": 0.7275461137992619,
|
| 946 |
+
"eval_stsb_spearman": 0.8063972443986471,
|
| 947 |
+
"step": 13875
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9,
|
| 951 |
+
"learning_rate": 3.121720209906566e-06,
|
| 952 |
+
"loss": 0.0004,
|
| 953 |
+
"step": 14000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.9,
|
| 957 |
+
"eval_avg_sts": 0.7674021960316728,
|
| 958 |
+
"eval_sickr_spearman": 0.727724597372206,
|
| 959 |
+
"eval_stsb_spearman": 0.8070797946911397,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9,
|
| 964 |
+
"eval_avg_sts": 0.7683497505006873,
|
| 965 |
+
"eval_sickr_spearman": 0.7281690291538128,
|
| 966 |
+
"eval_stsb_spearman": 0.8085304718475618,
|
| 967 |
+
"step": 14125
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.91,
|
| 971 |
+
"eval_avg_sts": 0.7680069912021876,
|
| 972 |
+
"eval_sickr_spearman": 0.7273477933814239,
|
| 973 |
+
"eval_stsb_spearman": 0.8086661890229514,
|
| 974 |
+
"step": 14250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.92,
|
| 978 |
+
"eval_avg_sts": 0.76821821049172,
|
| 979 |
+
"eval_sickr_spearman": 0.7266917845979821,
|
| 980 |
+
"eval_stsb_spearman": 0.8097446363854579,
|
| 981 |
+
"step": 14375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.93,
|
| 985 |
+
"learning_rate": 2.1617816459746575e-06,
|
| 986 |
+
"loss": 0.0003,
|
| 987 |
+
"step": 14500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.93,
|
| 991 |
+
"eval_avg_sts": 0.7677497628237885,
|
| 992 |
+
"eval_sickr_spearman": 0.7264186797552051,
|
| 993 |
+
"eval_stsb_spearman": 0.8090808458923718,
|
| 994 |
+
"step": 14500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.94,
|
| 998 |
+
"eval_avg_sts": 0.7680442088137338,
|
| 999 |
+
"eval_sickr_spearman": 0.7256543608380205,
|
| 1000 |
+
"eval_stsb_spearman": 0.8104340567894471,
|
| 1001 |
+
"step": 14625
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.94,
|
| 1005 |
+
"eval_avg_sts": 0.7698268910330168,
|
| 1006 |
+
"eval_sickr_spearman": 0.7279500553623565,
|
| 1007 |
+
"eval_stsb_spearman": 0.8117037267036772,
|
| 1008 |
+
"step": 14750
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.95,
|
| 1012 |
+
"eval_avg_sts": 0.7708269865099182,
|
| 1013 |
+
"eval_sickr_spearman": 0.7296867639281557,
|
| 1014 |
+
"eval_stsb_spearman": 0.8119672090916807,
|
| 1015 |
+
"step": 14875
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.96,
|
| 1019 |
+
"learning_rate": 1.2018430820427492e-06,
|
| 1020 |
+
"loss": 0.0007,
|
| 1021 |
+
"step": 15000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.96,
|
| 1025 |
+
"eval_avg_sts": 0.7723124686000136,
|
| 1026 |
+
"eval_sickr_spearman": 0.7316718893505929,
|
| 1027 |
+
"eval_stsb_spearman": 0.8129530478494341,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.97,
|
| 1032 |
+
"eval_avg_sts": 0.7726351825661049,
|
| 1033 |
+
"eval_sickr_spearman": 0.7322496074386905,
|
| 1034 |
+
"eval_stsb_spearman": 0.8130207576935193,
|
| 1035 |
+
"step": 15125
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.98,
|
| 1039 |
+
"eval_avg_sts": 0.7724775113219677,
|
| 1040 |
+
"eval_sickr_spearman": 0.7322382240676497,
|
| 1041 |
+
"eval_stsb_spearman": 0.8127167985762856,
|
| 1042 |
+
"step": 15250
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.98,
|
| 1046 |
+
"eval_avg_sts": 0.7726148952184836,
|
| 1047 |
+
"eval_sickr_spearman": 0.732653981281698,
|
| 1048 |
+
"eval_stsb_spearman": 0.8125758091552692,
|
| 1049 |
+
"step": 15375
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.99,
|
| 1053 |
+
"learning_rate": 2.4190451811084087e-07,
|
| 1054 |
+
"loss": 0.0004,
|
| 1055 |
+
"step": 15500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.99,
|
| 1059 |
+
"eval_avg_sts": 0.7726350099777579,
|
| 1060 |
+
"eval_sickr_spearman": 0.7326541734061037,
|
| 1061 |
+
"eval_stsb_spearman": 0.812615846549412,
|
| 1062 |
+
"step": 15500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.0,
|
| 1066 |
+
"eval_avg_sts": 0.7724457544885928,
|
| 1067 |
+
"eval_sickr_spearman": 0.7325294846667704,
|
| 1068 |
+
"eval_stsb_spearman": 0.8123620243104152,
|
| 1069 |
+
"step": 15625
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.0,
|
| 1073 |
+
"step": 15626,
|
| 1074 |
+
"train_runtime": 4555.3265,
|
| 1075 |
+
"train_samples_per_second": 3.43
|
| 1076 |
+
}
|
| 1077 |
+
],
|
| 1078 |
+
"max_steps": 15626,
|
| 1079 |
+
"num_train_epochs": 1,
|
| 1080 |
+
"total_flos": 107685402744674304,
|
| 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:b81a785d2a105c3a204efef93ade1f3894dc6e5a7a1d5e800bfe288d29257e37
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|