root
commited on
Commit
·
88ed5da
1
Parent(s):
08c390f
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-large",
|
| 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": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 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 = 87.41
|
| 3 |
+
eval_MPQA = 88.32
|
| 4 |
+
eval_MR = 82.33
|
| 5 |
+
eval_MRPC = 74.46
|
| 6 |
+
eval_SST2 = 85.89
|
| 7 |
+
eval_SUBJ = 94.47
|
| 8 |
+
eval_TREC = 78.49
|
| 9 |
+
eval_avg_sts = 0.8280440185035953
|
| 10 |
+
eval_avg_transfer = 84.48142857142857
|
| 11 |
+
eval_sickr_spearman = 0.792904915392188
|
| 12 |
+
eval_stsb_spearman = 0.8631831216150027
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2afce77266babbec70276e8fd7f8995caade957597b6fcfeb8ae1e9c323c911
|
| 3 |
+
size 3166829693
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b63e148b84f2d0a32c514b925b3df7bb291a02a70171effae53a6985a9d95c
|
| 3 |
+
size 2021511594
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e2a1c8e3229d39a2ce8c0c6dc8cc00b29edf00247c2985d3faf45883c6a9783
|
| 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/bert-large-uncased_condenser", "special_tokens_map_file": "/mmu_nlp/wuxing/wuxing/nlp/SimCSE/bert-large-uncased_condenser/special_tokens_map.json"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 2.0
|
| 2 |
+
train_runtime = 21163.9877
|
| 3 |
+
train_samples_per_second = 1.477
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8631831216150027,
|
| 3 |
+
"best_model_checkpoint": "result/InfoCSE-bert-large",
|
| 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": 0.6667446229182062,
|
| 13 |
+
"eval_sickr_spearman": 0.6627723790529534,
|
| 14 |
+
"eval_stsb_spearman": 0.6707168667834591,
|
| 15 |
+
"step": 125
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_avg_sts": 0.7051305088963267,
|
| 20 |
+
"eval_sickr_spearman": 0.6969365172570714,
|
| 21 |
+
"eval_stsb_spearman": 0.713324500535582,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.02,
|
| 26 |
+
"eval_avg_sts": 0.725875395370044,
|
| 27 |
+
"eval_sickr_spearman": 0.716654533206054,
|
| 28 |
+
"eval_stsb_spearman": 0.735096257534034,
|
| 29 |
+
"step": 375
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 6.888007167541277e-06,
|
| 34 |
+
"loss": 0.001,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.03,
|
| 39 |
+
"eval_avg_sts": 0.7357340574594278,
|
| 40 |
+
"eval_sickr_spearman": 0.7235103965631273,
|
| 41 |
+
"eval_stsb_spearman": 0.7479577183557282,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"eval_avg_sts": 0.7464037729944727,
|
| 47 |
+
"eval_sickr_spearman": 0.7301059313504061,
|
| 48 |
+
"eval_stsb_spearman": 0.7627016146385392,
|
| 49 |
+
"step": 625
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_avg_sts": 0.7591284137806686,
|
| 54 |
+
"eval_sickr_spearman": 0.7344878567657066,
|
| 55 |
+
"eval_stsb_spearman": 0.7837689707956308,
|
| 56 |
+
"step": 750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_avg_sts": 0.7608889169495914,
|
| 61 |
+
"eval_sickr_spearman": 0.7373875423906269,
|
| 62 |
+
"eval_stsb_spearman": 0.7843902915085559,
|
| 63 |
+
"step": 875
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 6.776014335082554e-06,
|
| 68 |
+
"loss": 0.0002,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"eval_avg_sts": 0.7633437897321462,
|
| 74 |
+
"eval_sickr_spearman": 0.7394359247736582,
|
| 75 |
+
"eval_stsb_spearman": 0.7872516546906342,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_avg_sts": 0.7689886003242912,
|
| 81 |
+
"eval_sickr_spearman": 0.7459672900094155,
|
| 82 |
+
"eval_stsb_spearman": 0.7920099106391669,
|
| 83 |
+
"step": 1125
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_avg_sts": 0.7695141299706598,
|
| 88 |
+
"eval_sickr_spearman": 0.749662274611948,
|
| 89 |
+
"eval_stsb_spearman": 0.7893659853293715,
|
| 90 |
+
"step": 1250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09,
|
| 94 |
+
"eval_avg_sts": 0.771575990947651,
|
| 95 |
+
"eval_sickr_spearman": 0.7507335602984238,
|
| 96 |
+
"eval_stsb_spearman": 0.7924184215968783,
|
| 97 |
+
"step": 1375
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1,
|
| 101 |
+
"learning_rate": 6.6640215026238325e-06,
|
| 102 |
+
"loss": 0.0003,
|
| 103 |
+
"step": 1500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.1,
|
| 107 |
+
"eval_avg_sts": 0.7721249223821594,
|
| 108 |
+
"eval_sickr_spearman": 0.7508546947362507,
|
| 109 |
+
"eval_stsb_spearman": 0.7933951500280679,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1,
|
| 114 |
+
"eval_avg_sts": 0.7736414601237904,
|
| 115 |
+
"eval_sickr_spearman": 0.7518223773369244,
|
| 116 |
+
"eval_stsb_spearman": 0.7954605429106565,
|
| 117 |
+
"step": 1625
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_avg_sts": 0.7750895970401648,
|
| 122 |
+
"eval_sickr_spearman": 0.7527568224154028,
|
| 123 |
+
"eval_stsb_spearman": 0.7974223716649267,
|
| 124 |
+
"step": 1750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12,
|
| 128 |
+
"eval_avg_sts": 0.7776564224610277,
|
| 129 |
+
"eval_sickr_spearman": 0.7542352378193863,
|
| 130 |
+
"eval_stsb_spearman": 0.8010776071026692,
|
| 131 |
+
"step": 1875
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.13,
|
| 135 |
+
"learning_rate": 6.55202867016511e-06,
|
| 136 |
+
"loss": 0.0001,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.13,
|
| 141 |
+
"eval_avg_sts": 0.7785919822208553,
|
| 142 |
+
"eval_sickr_spearman": 0.7546353668237488,
|
| 143 |
+
"eval_stsb_spearman": 0.802548597617962,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"eval_avg_sts": 0.7804785012417673,
|
| 149 |
+
"eval_sickr_spearman": 0.7560601133857076,
|
| 150 |
+
"eval_stsb_spearman": 0.8048968890978271,
|
| 151 |
+
"step": 2125
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.14,
|
| 155 |
+
"eval_avg_sts": 0.7791958793390172,
|
| 156 |
+
"eval_sickr_spearman": 0.7571627153503209,
|
| 157 |
+
"eval_stsb_spearman": 0.8012290433277136,
|
| 158 |
+
"step": 2250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"eval_avg_sts": 0.7808643358009081,
|
| 163 |
+
"eval_sickr_spearman": 0.757428807652288,
|
| 164 |
+
"eval_stsb_spearman": 0.8042998639495281,
|
| 165 |
+
"step": 2375
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 6.440035837706387e-06,
|
| 170 |
+
"loss": 0.0005,
|
| 171 |
+
"step": 2500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"eval_avg_sts": 0.7997499220712412,
|
| 176 |
+
"eval_sickr_spearman": 0.7682156324132593,
|
| 177 |
+
"eval_stsb_spearman": 0.8312842117292232,
|
| 178 |
+
"step": 2500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"eval_avg_sts": 0.8000945443564438,
|
| 183 |
+
"eval_sickr_spearman": 0.769006603032424,
|
| 184 |
+
"eval_stsb_spearman": 0.8311824856804637,
|
| 185 |
+
"step": 2625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.18,
|
| 189 |
+
"eval_avg_sts": 0.8015655863550484,
|
| 190 |
+
"eval_sickr_spearman": 0.7697635307193054,
|
| 191 |
+
"eval_stsb_spearman": 0.8333676419907914,
|
| 192 |
+
"step": 2750
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18,
|
| 196 |
+
"eval_avg_sts": 0.8020135971999303,
|
| 197 |
+
"eval_sickr_spearman": 0.7738109675441908,
|
| 198 |
+
"eval_stsb_spearman": 0.8302162268556699,
|
| 199 |
+
"step": 2875
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.19,
|
| 203 |
+
"learning_rate": 6.328043005247664e-06,
|
| 204 |
+
"loss": 0.0001,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"eval_avg_sts": 0.8021055052889553,
|
| 210 |
+
"eval_sickr_spearman": 0.7723527913356312,
|
| 211 |
+
"eval_stsb_spearman": 0.8318582192422794,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"eval_avg_sts": 0.8034828561746414,
|
| 217 |
+
"eval_sickr_spearman": 0.7730187425570707,
|
| 218 |
+
"eval_stsb_spearman": 0.8339469697922121,
|
| 219 |
+
"step": 3125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"eval_avg_sts": 0.809294388946485,
|
| 224 |
+
"eval_sickr_spearman": 0.7739637544778655,
|
| 225 |
+
"eval_stsb_spearman": 0.8446250234151045,
|
| 226 |
+
"step": 3250
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22,
|
| 230 |
+
"eval_avg_sts": 0.8095468267478854,
|
| 231 |
+
"eval_sickr_spearman": 0.7742509804644655,
|
| 232 |
+
"eval_stsb_spearman": 0.8448426730313053,
|
| 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": 0.8075109934505635,
|
| 244 |
+
"eval_sickr_spearman": 0.7709388998025974,
|
| 245 |
+
"eval_stsb_spearman": 0.8440830870985296,
|
| 246 |
+
"step": 3500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23,
|
| 250 |
+
"eval_avg_sts": 0.8072613664062491,
|
| 251 |
+
"eval_sickr_spearman": 0.7727868483993274,
|
| 252 |
+
"eval_stsb_spearman": 0.8417358844131708,
|
| 253 |
+
"step": 3625
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.24,
|
| 257 |
+
"eval_avg_sts": 0.8035650181540979,
|
| 258 |
+
"eval_sickr_spearman": 0.7687000741023642,
|
| 259 |
+
"eval_stsb_spearman": 0.8384299622058315,
|
| 260 |
+
"step": 3750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"eval_avg_sts": 0.8060855472554131,
|
| 265 |
+
"eval_sickr_spearman": 0.7709744428176617,
|
| 266 |
+
"eval_stsb_spearman": 0.8411966516931645,
|
| 267 |
+
"step": 3875
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 6.104057340330219e-06,
|
| 272 |
+
"loss": 0.0004,
|
| 273 |
+
"step": 4000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_avg_sts": 0.803351813599069,
|
| 278 |
+
"eval_sickr_spearman": 0.7677387500328843,
|
| 279 |
+
"eval_stsb_spearman": 0.8389648771652538,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.26,
|
| 284 |
+
"eval_avg_sts": 0.802660483963512,
|
| 285 |
+
"eval_sickr_spearman": 0.7673760487601211,
|
| 286 |
+
"eval_stsb_spearman": 0.8379449191669028,
|
| 287 |
+
"step": 4125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27,
|
| 291 |
+
"eval_avg_sts": 0.8047314511229144,
|
| 292 |
+
"eval_sickr_spearman": 0.7691939779184522,
|
| 293 |
+
"eval_stsb_spearman": 0.8402689243273768,
|
| 294 |
+
"step": 4250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.28,
|
| 298 |
+
"eval_avg_sts": 0.8040567267552472,
|
| 299 |
+
"eval_sickr_spearman": 0.7695367278583146,
|
| 300 |
+
"eval_stsb_spearman": 0.8385767256521798,
|
| 301 |
+
"step": 4375
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.29,
|
| 305 |
+
"learning_rate": 5.992064507871497e-06,
|
| 306 |
+
"loss": 0.0003,
|
| 307 |
+
"step": 4500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.29,
|
| 311 |
+
"eval_avg_sts": 0.8031439674900422,
|
| 312 |
+
"eval_sickr_spearman": 0.7708419250087939,
|
| 313 |
+
"eval_stsb_spearman": 0.8354460099712906,
|
| 314 |
+
"step": 4500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"eval_avg_sts": 0.8016452961027151,
|
| 319 |
+
"eval_sickr_spearman": 0.76836294380137,
|
| 320 |
+
"eval_stsb_spearman": 0.8349276484040601,
|
| 321 |
+
"step": 4625
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"eval_avg_sts": 0.8036856358976682,
|
| 326 |
+
"eval_sickr_spearman": 0.7702216513648221,
|
| 327 |
+
"eval_stsb_spearman": 0.8371496204305142,
|
| 328 |
+
"step": 4750
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"eval_avg_sts": 0.8061976413597232,
|
| 333 |
+
"eval_sickr_spearman": 0.7719798778640656,
|
| 334 |
+
"eval_stsb_spearman": 0.8404154048553806,
|
| 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": 0.8067273899585344,
|
| 346 |
+
"eval_sickr_spearman": 0.7723029350523384,
|
| 347 |
+
"eval_stsb_spearman": 0.8411518448647305,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"eval_avg_sts": 0.8078358230567408,
|
| 353 |
+
"eval_sickr_spearman": 0.7726999601368258,
|
| 354 |
+
"eval_stsb_spearman": 0.8429716859766557,
|
| 355 |
+
"step": 5125
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.34,
|
| 359 |
+
"eval_avg_sts": 0.802548441043093,
|
| 360 |
+
"eval_sickr_spearman": 0.7676195664444124,
|
| 361 |
+
"eval_stsb_spearman": 0.8374773156417734,
|
| 362 |
+
"step": 5250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.34,
|
| 366 |
+
"eval_avg_sts": 0.800628830120568,
|
| 367 |
+
"eval_sickr_spearman": 0.7634932625509655,
|
| 368 |
+
"eval_stsb_spearman": 0.8377643976901704,
|
| 369 |
+
"step": 5375
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.35,
|
| 373 |
+
"learning_rate": 5.7680788429540505e-06,
|
| 374 |
+
"loss": 0.0002,
|
| 375 |
+
"step": 5500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.35,
|
| 379 |
+
"eval_avg_sts": 0.8020238168463023,
|
| 380 |
+
"eval_sickr_spearman": 0.7652266089396642,
|
| 381 |
+
"eval_stsb_spearman": 0.8388210247529404,
|
| 382 |
+
"step": 5500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36,
|
| 386 |
+
"eval_avg_sts": 0.8040364434874829,
|
| 387 |
+
"eval_sickr_spearman": 0.7675117846527851,
|
| 388 |
+
"eval_stsb_spearman": 0.8405611023221807,
|
| 389 |
+
"step": 5625
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.37,
|
| 393 |
+
"eval_avg_sts": 0.8016723711497669,
|
| 394 |
+
"eval_sickr_spearman": 0.7650260310600586,
|
| 395 |
+
"eval_stsb_spearman": 0.8383187112394752,
|
| 396 |
+
"step": 5750
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38,
|
| 400 |
+
"eval_avg_sts": 0.8020864629480828,
|
| 401 |
+
"eval_sickr_spearman": 0.7653134972021658,
|
| 402 |
+
"eval_stsb_spearman": 0.8388594286939999,
|
| 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": 0.8028151558848002,
|
| 414 |
+
"eval_sickr_spearman": 0.7671768637824573,
|
| 415 |
+
"eval_stsb_spearman": 0.838453447987143,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.39,
|
| 420 |
+
"eval_avg_sts": 0.8049514040827435,
|
| 421 |
+
"eval_sickr_spearman": 0.7685626571211498,
|
| 422 |
+
"eval_stsb_spearman": 0.8413401510443372,
|
| 423 |
+
"step": 6125
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4,
|
| 427 |
+
"eval_avg_sts": 0.8059812583547672,
|
| 428 |
+
"eval_sickr_spearman": 0.7690958503782142,
|
| 429 |
+
"eval_stsb_spearman": 0.8428666663313202,
|
| 430 |
+
"step": 6250
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.41,
|
| 434 |
+
"eval_avg_sts": 0.8063265220940947,
|
| 435 |
+
"eval_sickr_spearman": 0.7693663135104123,
|
| 436 |
+
"eval_stsb_spearman": 0.8432867306777773,
|
| 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": 0.8061105071256144,
|
| 448 |
+
"eval_sickr_spearman": 0.769672271626573,
|
| 449 |
+
"eval_stsb_spearman": 0.8425487426246557,
|
| 450 |
+
"step": 6500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.42,
|
| 454 |
+
"eval_avg_sts": 0.8069978292318387,
|
| 455 |
+
"eval_sickr_spearman": 0.770697879735581,
|
| 456 |
+
"eval_stsb_spearman": 0.8432977787280964,
|
| 457 |
+
"step": 6625
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.43,
|
| 461 |
+
"eval_avg_sts": 0.8080712074218199,
|
| 462 |
+
"eval_sickr_spearman": 0.7709677664945618,
|
| 463 |
+
"eval_stsb_spearman": 0.8451746483490781,
|
| 464 |
+
"step": 6750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"eval_avg_sts": 0.808918715708319,
|
| 469 |
+
"eval_sickr_spearman": 0.7720352577240238,
|
| 470 |
+
"eval_stsb_spearman": 0.8458021736926141,
|
| 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": 0.8006026057334057,
|
| 482 |
+
"eval_sickr_spearman": 0.7608432425913206,
|
| 483 |
+
"eval_stsb_spearman": 0.8403619688754909,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"eval_avg_sts": 0.8020612965823335,
|
| 489 |
+
"eval_sickr_spearman": 0.7626692409746934,
|
| 490 |
+
"eval_stsb_spearman": 0.8414533521899736,
|
| 491 |
+
"step": 7125
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"eval_avg_sts": 0.810499992265102,
|
| 496 |
+
"eval_sickr_spearman": 0.7673374317545649,
|
| 497 |
+
"eval_stsb_spearman": 0.8536625527756392,
|
| 498 |
+
"step": 7250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"eval_avg_sts": 0.8112538171528675,
|
| 503 |
+
"eval_sickr_spearman": 0.7687574232374812,
|
| 504 |
+
"eval_stsb_spearman": 0.8537502110682538,
|
| 505 |
+
"step": 7375
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.48,
|
| 509 |
+
"learning_rate": 5.32010751311916e-06,
|
| 510 |
+
"loss": 0.0002,
|
| 511 |
+
"step": 7500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.48,
|
| 515 |
+
"eval_avg_sts": 0.8149817134253148,
|
| 516 |
+
"eval_sickr_spearman": 0.7774900538521474,
|
| 517 |
+
"eval_stsb_spearman": 0.852473372998482,
|
| 518 |
+
"step": 7500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.49,
|
| 522 |
+
"eval_avg_sts": 0.8174625453813287,
|
| 523 |
+
"eval_sickr_spearman": 0.7815984901758593,
|
| 524 |
+
"eval_stsb_spearman": 0.8533266005867981,
|
| 525 |
+
"step": 7625
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5,
|
| 529 |
+
"eval_avg_sts": 0.8176977199916579,
|
| 530 |
+
"eval_sickr_spearman": 0.782115160734029,
|
| 531 |
+
"eval_stsb_spearman": 0.8532802792492867,
|
| 532 |
+
"step": 7750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5,
|
| 536 |
+
"eval_avg_sts": 0.8178800789250669,
|
| 537 |
+
"eval_sickr_spearman": 0.782127648820403,
|
| 538 |
+
"eval_stsb_spearman": 0.8536325090297309,
|
| 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": 0.8181362028628546,
|
| 550 |
+
"eval_sickr_spearman": 0.7824101677590619,
|
| 551 |
+
"eval_stsb_spearman": 0.8538622379666473,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.52,
|
| 556 |
+
"eval_avg_sts": 0.8182071435777255,
|
| 557 |
+
"eval_sickr_spearman": 0.7826502752351511,
|
| 558 |
+
"eval_stsb_spearman": 0.8537640119202999,
|
| 559 |
+
"step": 8125
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.53,
|
| 563 |
+
"eval_avg_sts": 0.8175148093264073,
|
| 564 |
+
"eval_sickr_spearman": 0.7809989179366073,
|
| 565 |
+
"eval_stsb_spearman": 0.8540307007162073,
|
| 566 |
+
"step": 8250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.54,
|
| 570 |
+
"eval_avg_sts": 0.817271425771201,
|
| 571 |
+
"eval_sickr_spearman": 0.7809910408359715,
|
| 572 |
+
"eval_stsb_spearman": 0.8535518107064306,
|
| 573 |
+
"step": 8375
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.54,
|
| 577 |
+
"learning_rate": 5.096121848201715e-06,
|
| 578 |
+
"loss": 0.0,
|
| 579 |
+
"step": 8500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.54,
|
| 583 |
+
"eval_avg_sts": 0.8169878861543607,
|
| 584 |
+
"eval_sickr_spearman": 0.7807656308769224,
|
| 585 |
+
"eval_stsb_spearman": 0.8532101414317989,
|
| 586 |
+
"step": 8500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.55,
|
| 590 |
+
"eval_avg_sts": 0.8163714998445242,
|
| 591 |
+
"eval_sickr_spearman": 0.7799410809585343,
|
| 592 |
+
"eval_stsb_spearman": 0.852801918730514,
|
| 593 |
+
"step": 8625
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.56,
|
| 597 |
+
"eval_avg_sts": 0.814914066335918,
|
| 598 |
+
"eval_sickr_spearman": 0.7796482833641676,
|
| 599 |
+
"eval_stsb_spearman": 0.8501798493076684,
|
| 600 |
+
"step": 8750
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.57,
|
| 604 |
+
"eval_avg_sts": 0.8150768291940962,
|
| 605 |
+
"eval_sickr_spearman": 0.7799102930225125,
|
| 606 |
+
"eval_stsb_spearman": 0.8502433653656799,
|
| 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": 0.8157444131185677,
|
| 618 |
+
"eval_sickr_spearman": 0.7805133715321694,
|
| 619 |
+
"eval_stsb_spearman": 0.850975454704966,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.58,
|
| 624 |
+
"eval_avg_sts": 0.8194025294491036,
|
| 625 |
+
"eval_sickr_spearman": 0.7869190393754633,
|
| 626 |
+
"eval_stsb_spearman": 0.851886019522744,
|
| 627 |
+
"step": 9125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.59,
|
| 631 |
+
"eval_avg_sts": 0.6858142517829269,
|
| 632 |
+
"eval_sickr_spearman": 0.6164898018315937,
|
| 633 |
+
"eval_stsb_spearman": 0.7551387017342599,
|
| 634 |
+
"step": 9250
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6,
|
| 638 |
+
"eval_avg_sts": 0.8177747035338222,
|
| 639 |
+
"eval_sickr_spearman": 0.783078280380066,
|
| 640 |
+
"eval_stsb_spearman": 0.8524711266875784,
|
| 641 |
+
"step": 9375
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.61,
|
| 645 |
+
"learning_rate": 4.872136183284269e-06,
|
| 646 |
+
"loss": 0.0015,
|
| 647 |
+
"step": 9500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.61,
|
| 651 |
+
"eval_avg_sts": 0.819985242900733,
|
| 652 |
+
"eval_sickr_spearman": 0.7850574019148235,
|
| 653 |
+
"eval_stsb_spearman": 0.8549130838866427,
|
| 654 |
+
"step": 9500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.62,
|
| 658 |
+
"eval_avg_sts": 0.820612467391125,
|
| 659 |
+
"eval_sickr_spearman": 0.7860280624437863,
|
| 660 |
+
"eval_stsb_spearman": 0.8551968723384636,
|
| 661 |
+
"step": 9625
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.62,
|
| 665 |
+
"eval_avg_sts": 0.8210179120381628,
|
| 666 |
+
"eval_sickr_spearman": 0.7866489124609753,
|
| 667 |
+
"eval_stsb_spearman": 0.8553869116153502,
|
| 668 |
+
"step": 9750
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.63,
|
| 672 |
+
"eval_avg_sts": 0.821463549997331,
|
| 673 |
+
"eval_sickr_spearman": 0.787914243797261,
|
| 674 |
+
"eval_stsb_spearman": 0.8550128561974009,
|
| 675 |
+
"step": 9875
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.64,
|
| 679 |
+
"learning_rate": 4.760143350825547e-06,
|
| 680 |
+
"loss": 0.0002,
|
| 681 |
+
"step": 10000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.64,
|
| 685 |
+
"eval_avg_sts": 0.8220538798411258,
|
| 686 |
+
"eval_sickr_spearman": 0.7882646787133534,
|
| 687 |
+
"eval_stsb_spearman": 0.8558430809688982,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.65,
|
| 692 |
+
"eval_avg_sts": 0.8227053843456922,
|
| 693 |
+
"eval_sickr_spearman": 0.7892594508552383,
|
| 694 |
+
"eval_stsb_spearman": 0.856151317836146,
|
| 695 |
+
"step": 10125
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.66,
|
| 699 |
+
"eval_avg_sts": 0.8211210354889169,
|
| 700 |
+
"eval_sickr_spearman": 0.7858874273787755,
|
| 701 |
+
"eval_stsb_spearman": 0.8563546435990582,
|
| 702 |
+
"step": 10250
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.66,
|
| 706 |
+
"eval_avg_sts": 0.8217109523377687,
|
| 707 |
+
"eval_sickr_spearman": 0.7865405062650296,
|
| 708 |
+
"eval_stsb_spearman": 0.8568813984105078,
|
| 709 |
+
"step": 10375
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.67,
|
| 713 |
+
"learning_rate": 4.648150518366825e-06,
|
| 714 |
+
"loss": 0.0002,
|
| 715 |
+
"step": 10500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.67,
|
| 719 |
+
"eval_avg_sts": 0.8231847712907092,
|
| 720 |
+
"eval_sickr_spearman": 0.7883226042216879,
|
| 721 |
+
"eval_stsb_spearman": 0.8580469383597307,
|
| 722 |
+
"step": 10500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.68,
|
| 726 |
+
"eval_avg_sts": 0.8231833094531285,
|
| 727 |
+
"eval_sickr_spearman": 0.7886680439032306,
|
| 728 |
+
"eval_stsb_spearman": 0.8576985750030263,
|
| 729 |
+
"step": 10625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.69,
|
| 733 |
+
"eval_avg_sts": 0.8235797750151058,
|
| 734 |
+
"eval_sickr_spearman": 0.7894692507063199,
|
| 735 |
+
"eval_stsb_spearman": 0.8576902993238917,
|
| 736 |
+
"step": 10750
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7,
|
| 740 |
+
"eval_avg_sts": 0.8239802387430818,
|
| 741 |
+
"eval_sickr_spearman": 0.7900059982648908,
|
| 742 |
+
"eval_stsb_spearman": 0.8579544792212728,
|
| 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": 0.8228846723006884,
|
| 754 |
+
"eval_sickr_spearman": 0.7878013707088813,
|
| 755 |
+
"eval_stsb_spearman": 0.8579679738924955,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.71,
|
| 760 |
+
"eval_avg_sts": 0.8233402178257747,
|
| 761 |
+
"eval_sickr_spearman": 0.788485765873273,
|
| 762 |
+
"eval_stsb_spearman": 0.8581946697782764,
|
| 763 |
+
"step": 11125
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.72,
|
| 767 |
+
"eval_avg_sts": 0.8233165033728497,
|
| 768 |
+
"eval_sickr_spearman": 0.788493306756199,
|
| 769 |
+
"eval_stsb_spearman": 0.8581396999895003,
|
| 770 |
+
"step": 11250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.73,
|
| 774 |
+
"eval_avg_sts": 0.8211286933035429,
|
| 775 |
+
"eval_sickr_spearman": 0.787368274267214,
|
| 776 |
+
"eval_stsb_spearman": 0.8548891123398719,
|
| 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": 0.8222354006770852,
|
| 788 |
+
"eval_sickr_spearman": 0.7882437371531265,
|
| 789 |
+
"eval_stsb_spearman": 0.856227064201044,
|
| 790 |
+
"step": 11500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.74,
|
| 794 |
+
"eval_avg_sts": 0.823058736106017,
|
| 795 |
+
"eval_sickr_spearman": 0.7882230837795081,
|
| 796 |
+
"eval_stsb_spearman": 0.8578943884325259,
|
| 797 |
+
"step": 11625
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.75,
|
| 801 |
+
"eval_avg_sts": 0.8240623262398707,
|
| 802 |
+
"eval_sickr_spearman": 0.7903270861780045,
|
| 803 |
+
"eval_stsb_spearman": 0.8577975663017371,
|
| 804 |
+
"step": 11750
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.76,
|
| 808 |
+
"eval_avg_sts": 0.8193741224170432,
|
| 809 |
+
"eval_sickr_spearman": 0.7834559008995725,
|
| 810 |
+
"eval_stsb_spearman": 0.8552923439345139,
|
| 811 |
+
"step": 11875
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.77,
|
| 815 |
+
"learning_rate": 4.312172020990656e-06,
|
| 816 |
+
"loss": 0.0004,
|
| 817 |
+
"step": 12000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.77,
|
| 821 |
+
"eval_avg_sts": 0.8219118427006455,
|
| 822 |
+
"eval_sickr_spearman": 0.785794199010884,
|
| 823 |
+
"eval_stsb_spearman": 0.8580294863904071,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.78,
|
| 828 |
+
"eval_avg_sts": 0.823098023008008,
|
| 829 |
+
"eval_sickr_spearman": 0.7879260114171134,
|
| 830 |
+
"eval_stsb_spearman": 0.8582700345989028,
|
| 831 |
+
"step": 12125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.78,
|
| 835 |
+
"eval_avg_sts": 0.8227772117211238,
|
| 836 |
+
"eval_sickr_spearman": 0.7878058376013152,
|
| 837 |
+
"eval_stsb_spearman": 0.8577485858409325,
|
| 838 |
+
"step": 12250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.79,
|
| 842 |
+
"eval_avg_sts": 0.8244800942376741,
|
| 843 |
+
"eval_sickr_spearman": 0.7899311658088503,
|
| 844 |
+
"eval_stsb_spearman": 0.8590290226664979,
|
| 845 |
+
"step": 12375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8,
|
| 849 |
+
"learning_rate": 4.2001791885319345e-06,
|
| 850 |
+
"loss": 0.0003,
|
| 851 |
+
"step": 12500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8,
|
| 855 |
+
"eval_avg_sts": 0.8252546537289246,
|
| 856 |
+
"eval_sickr_spearman": 0.7905314585146238,
|
| 857 |
+
"eval_stsb_spearman": 0.8599778489432254,
|
| 858 |
+
"step": 12500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.81,
|
| 862 |
+
"eval_avg_sts": 0.8242515246774704,
|
| 863 |
+
"eval_sickr_spearman": 0.7934860436884877,
|
| 864 |
+
"eval_stsb_spearman": 0.855017005666453,
|
| 865 |
+
"step": 12625
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.82,
|
| 869 |
+
"eval_avg_sts": 0.8251886392831695,
|
| 870 |
+
"eval_sickr_spearman": 0.7935808570827266,
|
| 871 |
+
"eval_stsb_spearman": 0.8567964214836123,
|
| 872 |
+
"step": 12750
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.82,
|
| 876 |
+
"eval_avg_sts": 0.8255732979417849,
|
| 877 |
+
"eval_sickr_spearman": 0.7939037701776952,
|
| 878 |
+
"eval_stsb_spearman": 0.8572428257058746,
|
| 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": 0.8272525514506217,
|
| 890 |
+
"eval_sickr_spearman": 0.7954193915835747,
|
| 891 |
+
"eval_stsb_spearman": 0.8590857113176686,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.84,
|
| 896 |
+
"eval_avg_sts": 0.8276110249953785,
|
| 897 |
+
"eval_sickr_spearman": 0.7955957617880555,
|
| 898 |
+
"eval_stsb_spearman": 0.8596262882027015,
|
| 899 |
+
"step": 13125
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.85,
|
| 903 |
+
"eval_avg_sts": 0.8262806808137206,
|
| 904 |
+
"eval_sickr_spearman": 0.792061729406442,
|
| 905 |
+
"eval_stsb_spearman": 0.8604996322209992,
|
| 906 |
+
"step": 13250
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.86,
|
| 910 |
+
"eval_avg_sts": 0.8270413161061019,
|
| 911 |
+
"eval_sickr_spearman": 0.7918599027181991,
|
| 912 |
+
"eval_stsb_spearman": 0.8622227294940048,
|
| 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": 0.8277173388272963,
|
| 924 |
+
"eval_sickr_spearman": 0.7929541472711621,
|
| 925 |
+
"eval_stsb_spearman": 0.8624805303834304,
|
| 926 |
+
"step": 13500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.87,
|
| 930 |
+
"eval_avg_sts": 0.8280371802211439,
|
| 931 |
+
"eval_sickr_spearman": 0.7936189937772684,
|
| 932 |
+
"eval_stsb_spearman": 0.8624553666650194,
|
| 933 |
+
"step": 13625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.88,
|
| 937 |
+
"eval_avg_sts": 0.8280087430461096,
|
| 938 |
+
"eval_sickr_spearman": 0.7934894538966899,
|
| 939 |
+
"eval_stsb_spearman": 0.8625280321955292,
|
| 940 |
+
"step": 13750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.89,
|
| 944 |
+
"eval_avg_sts": 0.8279846750031183,
|
| 945 |
+
"eval_sickr_spearman": 0.7941465193643633,
|
| 946 |
+
"eval_stsb_spearman": 0.8618228306418733,
|
| 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": 0.8281003824811937,
|
| 958 |
+
"eval_sickr_spearman": 0.7943439752223754,
|
| 959 |
+
"eval_stsb_spearman": 0.8618567897400118,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9,
|
| 964 |
+
"eval_avg_sts": 0.8280440185035953,
|
| 965 |
+
"eval_sickr_spearman": 0.792904915392188,
|
| 966 |
+
"eval_stsb_spearman": 0.8631831216150027,
|
| 967 |
+
"step": 14125
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.91,
|
| 971 |
+
"eval_avg_sts": 0.8279193239585301,
|
| 972 |
+
"eval_sickr_spearman": 0.7931221120328913,
|
| 973 |
+
"eval_stsb_spearman": 0.8627165358841689,
|
| 974 |
+
"step": 14250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.92,
|
| 978 |
+
"eval_avg_sts": 0.8275099017452278,
|
| 979 |
+
"eval_sickr_spearman": 0.793065195177687,
|
| 980 |
+
"eval_stsb_spearman": 0.8619546083127685,
|
| 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": 0.8275982959975564,
|
| 992 |
+
"eval_sickr_spearman": 0.7935053521912658,
|
| 993 |
+
"eval_stsb_spearman": 0.861691239803847,
|
| 994 |
+
"step": 14500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.94,
|
| 998 |
+
"eval_avg_sts": 0.8276150816017793,
|
| 999 |
+
"eval_sickr_spearman": 0.7940267778284781,
|
| 1000 |
+
"eval_stsb_spearman": 0.8612033853750805,
|
| 1001 |
+
"step": 14625
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.94,
|
| 1005 |
+
"eval_avg_sts": 0.8277678050001869,
|
| 1006 |
+
"eval_sickr_spearman": 0.7940122244047422,
|
| 1007 |
+
"eval_stsb_spearman": 0.8615233855956315,
|
| 1008 |
+
"step": 14750
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.95,
|
| 1012 |
+
"eval_avg_sts": 0.827775044421294,
|
| 1013 |
+
"eval_sickr_spearman": 0.79435247672733,
|
| 1014 |
+
"eval_stsb_spearman": 0.861197612115258,
|
| 1015 |
+
"step": 14875
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.96,
|
| 1019 |
+
"learning_rate": 3.6402150262383203e-06,
|
| 1020 |
+
"loss": 0.0002,
|
| 1021 |
+
"step": 15000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.96,
|
| 1025 |
+
"eval_avg_sts": 0.8265288786526938,
|
| 1026 |
+
"eval_sickr_spearman": 0.7941830230014563,
|
| 1027 |
+
"eval_stsb_spearman": 0.8588747343039312,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.97,
|
| 1032 |
+
"eval_avg_sts": 0.826595528411173,
|
| 1033 |
+
"eval_sickr_spearman": 0.7947538726420482,
|
| 1034 |
+
"eval_stsb_spearman": 0.8584371841802979,
|
| 1035 |
+
"step": 15125
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.98,
|
| 1039 |
+
"eval_avg_sts": 0.8271259707838263,
|
| 1040 |
+
"eval_sickr_spearman": 0.7952840399397222,
|
| 1041 |
+
"eval_stsb_spearman": 0.8589679016279306,
|
| 1042 |
+
"step": 15250
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.98,
|
| 1046 |
+
"eval_avg_sts": 0.8269049666463504,
|
| 1047 |
+
"eval_sickr_spearman": 0.7927316191781993,
|
| 1048 |
+
"eval_stsb_spearman": 0.8610783141145013,
|
| 1049 |
+
"step": 15375
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.99,
|
| 1053 |
+
"learning_rate": 3.5282221937795976e-06,
|
| 1054 |
+
"loss": 0.0003,
|
| 1055 |
+
"step": 15500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.99,
|
| 1059 |
+
"eval_avg_sts": 0.82737580758211,
|
| 1060 |
+
"eval_sickr_spearman": 0.7935406550508229,
|
| 1061 |
+
"eval_stsb_spearman": 0.8612109601133972,
|
| 1062 |
+
"step": 15500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.0,
|
| 1066 |
+
"eval_avg_sts": 0.8264028870845463,
|
| 1067 |
+
"eval_sickr_spearman": 0.7940738673657366,
|
| 1068 |
+
"eval_stsb_spearman": 0.8587319068033561,
|
| 1069 |
+
"step": 15625
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.01,
|
| 1073 |
+
"eval_avg_sts": 0.8268441102829658,
|
| 1074 |
+
"eval_sickr_spearman": 0.7937048253555384,
|
| 1075 |
+
"eval_stsb_spearman": 0.8599833952103932,
|
| 1076 |
+
"step": 15750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.02,
|
| 1080 |
+
"eval_avg_sts": 0.8275739286019619,
|
| 1081 |
+
"eval_sickr_spearman": 0.7947639591733503,
|
| 1082 |
+
"eval_stsb_spearman": 0.8603838980305735,
|
| 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": 0.8277768410299685,
|
| 1094 |
+
"eval_sickr_spearman": 0.7952131460339995,
|
| 1095 |
+
"eval_stsb_spearman": 0.8603405360259375,
|
| 1096 |
+
"step": 16000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.03,
|
| 1100 |
+
"eval_avg_sts": 0.8282682698041279,
|
| 1101 |
+
"eval_sickr_spearman": 0.7963400997670419,
|
| 1102 |
+
"eval_stsb_spearman": 0.860196439841214,
|
| 1103 |
+
"step": 16125
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.04,
|
| 1107 |
+
"eval_avg_sts": 0.8264618348746703,
|
| 1108 |
+
"eval_sickr_spearman": 0.7934643816617393,
|
| 1109 |
+
"eval_stsb_spearman": 0.8594592880876013,
|
| 1110 |
+
"step": 16250
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.05,
|
| 1114 |
+
"eval_avg_sts": 0.8264717428559492,
|
| 1115 |
+
"eval_sickr_spearman": 0.7932766280862176,
|
| 1116 |
+
"eval_stsb_spearman": 0.8596668576256806,
|
| 1117 |
+
"step": 16375
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.06,
|
| 1121 |
+
"learning_rate": 3.304236528862153e-06,
|
| 1122 |
+
"loss": 0.0002,
|
| 1123 |
+
"step": 16500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.06,
|
| 1127 |
+
"eval_avg_sts": 0.8274883631622513,
|
| 1128 |
+
"eval_sickr_spearman": 0.7946689056236043,
|
| 1129 |
+
"eval_stsb_spearman": 0.8603078207008983,
|
| 1130 |
+
"step": 16500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.06,
|
| 1134 |
+
"eval_avg_sts": 0.8285054599151072,
|
| 1135 |
+
"eval_sickr_spearman": 0.7953375465867241,
|
| 1136 |
+
"eval_stsb_spearman": 0.8616733732434904,
|
| 1137 |
+
"step": 16625
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.07,
|
| 1141 |
+
"eval_avg_sts": 0.8267040342845151,
|
| 1142 |
+
"eval_sickr_spearman": 0.7930167317963359,
|
| 1143 |
+
"eval_stsb_spearman": 0.8603913367726943,
|
| 1144 |
+
"step": 16750
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.08,
|
| 1148 |
+
"eval_avg_sts": 0.8254063226482575,
|
| 1149 |
+
"eval_sickr_spearman": 0.7925604363326739,
|
| 1150 |
+
"eval_stsb_spearman": 0.8582522089638411,
|
| 1151 |
+
"step": 16875
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.09,
|
| 1155 |
+
"learning_rate": 3.19224369640343e-06,
|
| 1156 |
+
"loss": 0.0003,
|
| 1157 |
+
"step": 17000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.09,
|
| 1161 |
+
"eval_avg_sts": 0.8263459648804743,
|
| 1162 |
+
"eval_sickr_spearman": 0.7938006474029073,
|
| 1163 |
+
"eval_stsb_spearman": 0.8588912823580412,
|
| 1164 |
+
"step": 17000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.1,
|
| 1168 |
+
"eval_avg_sts": 0.8265585284525776,
|
| 1169 |
+
"eval_sickr_spearman": 0.7938499273129829,
|
| 1170 |
+
"eval_stsb_spearman": 0.8592671295921722,
|
| 1171 |
+
"step": 17125
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.1,
|
| 1175 |
+
"eval_avg_sts": 0.8275713806370856,
|
| 1176 |
+
"eval_sickr_spearman": 0.795413819975808,
|
| 1177 |
+
"eval_stsb_spearman": 0.8597289412983632,
|
| 1178 |
+
"step": 17250
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.11,
|
| 1182 |
+
"eval_avg_sts": 0.8278030720022054,
|
| 1183 |
+
"eval_sickr_spearman": 0.7957596439061624,
|
| 1184 |
+
"eval_stsb_spearman": 0.8598465000982485,
|
| 1185 |
+
"step": 17375
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.12,
|
| 1189 |
+
"learning_rate": 3.0802508639447074e-06,
|
| 1190 |
+
"loss": 0.0003,
|
| 1191 |
+
"step": 17500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.12,
|
| 1195 |
+
"eval_avg_sts": 0.828665230451958,
|
| 1196 |
+
"eval_sickr_spearman": 0.7959547942713053,
|
| 1197 |
+
"eval_stsb_spearman": 0.8613756666326104,
|
| 1198 |
+
"step": 17500
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.13,
|
| 1202 |
+
"eval_avg_sts": 0.8288773890103436,
|
| 1203 |
+
"eval_sickr_spearman": 0.7964317911396872,
|
| 1204 |
+
"eval_stsb_spearman": 0.861322986881,
|
| 1205 |
+
"step": 17625
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.14,
|
| 1209 |
+
"eval_avg_sts": 0.8287921576974288,
|
| 1210 |
+
"eval_sickr_spearman": 0.7965225699214054,
|
| 1211 |
+
"eval_stsb_spearman": 0.8610617454734522,
|
| 1212 |
+
"step": 17750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 1.14,
|
| 1216 |
+
"eval_avg_sts": 0.8287755856452497,
|
| 1217 |
+
"eval_sickr_spearman": 0.7967101794036225,
|
| 1218 |
+
"eval_stsb_spearman": 0.8608409918868768,
|
| 1219 |
+
"step": 17875
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.15,
|
| 1223 |
+
"learning_rate": 2.9682580314859847e-06,
|
| 1224 |
+
"loss": 0.0001,
|
| 1225 |
+
"step": 18000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.15,
|
| 1229 |
+
"eval_avg_sts": 0.8292774010789281,
|
| 1230 |
+
"eval_sickr_spearman": 0.7969440428365246,
|
| 1231 |
+
"eval_stsb_spearman": 0.8616107593213317,
|
| 1232 |
+
"step": 18000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.16,
|
| 1236 |
+
"eval_avg_sts": 0.8293137062967321,
|
| 1237 |
+
"eval_sickr_spearman": 0.7971494238262741,
|
| 1238 |
+
"eval_stsb_spearman": 0.8614779887671901,
|
| 1239 |
+
"step": 18125
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.17,
|
| 1243 |
+
"eval_avg_sts": 0.8293003591512393,
|
| 1244 |
+
"eval_sickr_spearman": 0.7972976478053122,
|
| 1245 |
+
"eval_stsb_spearman": 0.8613030704971664,
|
| 1246 |
+
"step": 18250
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.18,
|
| 1250 |
+
"eval_avg_sts": 0.8269276043107123,
|
| 1251 |
+
"eval_sickr_spearman": 0.7936150552269506,
|
| 1252 |
+
"eval_stsb_spearman": 0.8602401533944739,
|
| 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": 0.8271598852494388,
|
| 1264 |
+
"eval_sickr_spearman": 0.7938677468516165,
|
| 1265 |
+
"eval_stsb_spearman": 0.8604520236472611,
|
| 1266 |
+
"step": 18500
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.19,
|
| 1270 |
+
"eval_avg_sts": 0.8273011691673453,
|
| 1271 |
+
"eval_sickr_spearman": 0.7941100157272702,
|
| 1272 |
+
"eval_stsb_spearman": 0.8604923226074204,
|
| 1273 |
+
"step": 18625
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.2,
|
| 1277 |
+
"eval_avg_sts": 0.8274659412451935,
|
| 1278 |
+
"eval_sickr_spearman": 0.7943473373994759,
|
| 1279 |
+
"eval_stsb_spearman": 0.860584545090911,
|
| 1280 |
+
"step": 18750
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.21,
|
| 1284 |
+
"eval_avg_sts": 0.8273871753451842,
|
| 1285 |
+
"eval_sickr_spearman": 0.7941770191137765,
|
| 1286 |
+
"eval_stsb_spearman": 0.8605973315765919,
|
| 1287 |
+
"step": 18875
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.22,
|
| 1291 |
+
"learning_rate": 2.7442723665685396e-06,
|
| 1292 |
+
"loss": 0.0002,
|
| 1293 |
+
"step": 19000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.22,
|
| 1297 |
+
"eval_avg_sts": 0.8268924907436139,
|
| 1298 |
+
"eval_sickr_spearman": 0.7941484406084208,
|
| 1299 |
+
"eval_stsb_spearman": 0.859636540878807,
|
| 1300 |
+
"step": 19000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.22,
|
| 1304 |
+
"eval_avg_sts": 0.8258034139625235,
|
| 1305 |
+
"eval_sickr_spearman": 0.7932116900370734,
|
| 1306 |
+
"eval_stsb_spearman": 0.8583951378879737,
|
| 1307 |
+
"step": 19125
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.23,
|
| 1311 |
+
"eval_avg_sts": 0.8252544789859086,
|
| 1312 |
+
"eval_sickr_spearman": 0.7925500616147634,
|
| 1313 |
+
"eval_stsb_spearman": 0.857958896357054,
|
| 1314 |
+
"step": 19250
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.24,
|
| 1318 |
+
"eval_avg_sts": 0.8253536873185088,
|
| 1319 |
+
"eval_sickr_spearman": 0.7926197067118486,
|
| 1320 |
+
"eval_stsb_spearman": 0.858087667925169,
|
| 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": 0.8259692031147807,
|
| 1332 |
+
"eval_sickr_spearman": 0.7942922457261266,
|
| 1333 |
+
"eval_stsb_spearman": 0.8576461605034348,
|
| 1334 |
+
"step": 19500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.26,
|
| 1338 |
+
"eval_avg_sts": 0.8262977896726795,
|
| 1339 |
+
"eval_sickr_spearman": 0.7945857637870148,
|
| 1340 |
+
"eval_stsb_spearman": 0.8580098155583442,
|
| 1341 |
+
"step": 19625
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 1.26,
|
| 1345 |
+
"eval_avg_sts": 0.8265435124446001,
|
| 1346 |
+
"eval_sickr_spearman": 0.7949808676274447,
|
| 1347 |
+
"eval_stsb_spearman": 0.8581061572617555,
|
| 1348 |
+
"step": 19750
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 1.27,
|
| 1352 |
+
"eval_avg_sts": 0.82660901551375,
|
| 1353 |
+
"eval_sickr_spearman": 0.795241820601558,
|
| 1354 |
+
"eval_stsb_spearman": 0.8579762104259421,
|
| 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": 0.8249759667991925,
|
| 1366 |
+
"eval_sickr_spearman": 0.7929103429066506,
|
| 1367 |
+
"eval_stsb_spearman": 0.8570415906917342,
|
| 1368 |
+
"step": 20000
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.29,
|
| 1372 |
+
"eval_avg_sts": 0.8252695158247048,
|
| 1373 |
+
"eval_sickr_spearman": 0.7941818702550217,
|
| 1374 |
+
"eval_stsb_spearman": 0.8563571613943879,
|
| 1375 |
+
"step": 20125
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.3,
|
| 1379 |
+
"eval_avg_sts": 0.8254168575586551,
|
| 1380 |
+
"eval_sickr_spearman": 0.794336146152841,
|
| 1381 |
+
"eval_stsb_spearman": 0.8564975689644694,
|
| 1382 |
+
"step": 20250
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3,
|
| 1386 |
+
"eval_avg_sts": 0.8259865535716795,
|
| 1387 |
+
"eval_sickr_spearman": 0.7950048831781639,
|
| 1388 |
+
"eval_stsb_spearman": 0.8569682239651952,
|
| 1389 |
+
"step": 20375
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.31,
|
| 1393 |
+
"learning_rate": 2.4082938691923718e-06,
|
| 1394 |
+
"loss": 0.0001,
|
| 1395 |
+
"step": 20500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.31,
|
| 1399 |
+
"eval_avg_sts": 0.826209318888689,
|
| 1400 |
+
"eval_sickr_spearman": 0.7952033957204077,
|
| 1401 |
+
"eval_stsb_spearman": 0.8572152420569702,
|
| 1402 |
+
"step": 20500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.32,
|
| 1406 |
+
"eval_avg_sts": 0.8259891403986184,
|
| 1407 |
+
"eval_sickr_spearman": 0.7948762078574111,
|
| 1408 |
+
"eval_stsb_spearman": 0.8571020729398255,
|
| 1409 |
+
"step": 20625
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.33,
|
| 1413 |
+
"eval_avg_sts": 0.8259890083537097,
|
| 1414 |
+
"eval_sickr_spearman": 0.7947911447767642,
|
| 1415 |
+
"eval_stsb_spearman": 0.8571868719306552,
|
| 1416 |
+
"step": 20750
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.34,
|
| 1420 |
+
"eval_avg_sts": 0.8261152907691348,
|
| 1421 |
+
"eval_sickr_spearman": 0.7949135280232285,
|
| 1422 |
+
"eval_stsb_spearman": 0.8573170535150412,
|
| 1423 |
+
"step": 20875
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.34,
|
| 1427 |
+
"learning_rate": 2.296301036733649e-06,
|
| 1428 |
+
"loss": 0.0001,
|
| 1429 |
+
"step": 21000
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.34,
|
| 1433 |
+
"eval_avg_sts": 0.826274962054796,
|
| 1434 |
+
"eval_sickr_spearman": 0.7950501284757184,
|
| 1435 |
+
"eval_stsb_spearman": 0.8574997956338737,
|
| 1436 |
+
"step": 21000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.35,
|
| 1440 |
+
"eval_avg_sts": 0.8260486313726075,
|
| 1441 |
+
"eval_sickr_spearman": 0.794899647034913,
|
| 1442 |
+
"eval_stsb_spearman": 0.8571976157103021,
|
| 1443 |
+
"step": 21125
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.36,
|
| 1447 |
+
"eval_avg_sts": 0.825587114078729,
|
| 1448 |
+
"eval_sickr_spearman": 0.7946725559873136,
|
| 1449 |
+
"eval_stsb_spearman": 0.8565016721701444,
|
| 1450 |
+
"step": 21250
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.37,
|
| 1454 |
+
"eval_avg_sts": 0.8256303672089018,
|
| 1455 |
+
"eval_sickr_spearman": 0.7944853787850091,
|
| 1456 |
+
"eval_stsb_spearman": 0.8567753556327944,
|
| 1457 |
+
"step": 21375
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.38,
|
| 1461 |
+
"learning_rate": 2.1843082042749267e-06,
|
| 1462 |
+
"loss": 0.0002,
|
| 1463 |
+
"step": 21500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.38,
|
| 1467 |
+
"eval_avg_sts": 0.8254654257169443,
|
| 1468 |
+
"eval_sickr_spearman": 0.7936856129149631,
|
| 1469 |
+
"eval_stsb_spearman": 0.8572452385189255,
|
| 1470 |
+
"step": 21500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.38,
|
| 1474 |
+
"eval_avg_sts": 0.8257646791990041,
|
| 1475 |
+
"eval_sickr_spearman": 0.7941317738162218,
|
| 1476 |
+
"eval_stsb_spearman": 0.8573975845817864,
|
| 1477 |
+
"step": 21625
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.39,
|
| 1481 |
+
"eval_avg_sts": 0.8263390736725806,
|
| 1482 |
+
"eval_sickr_spearman": 0.7947459955414125,
|
| 1483 |
+
"eval_stsb_spearman": 0.8579321518037489,
|
| 1484 |
+
"step": 21750
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.4,
|
| 1488 |
+
"eval_avg_sts": 0.825957826826842,
|
| 1489 |
+
"eval_sickr_spearman": 0.7945194808670303,
|
| 1490 |
+
"eval_stsb_spearman": 0.8573961727866538,
|
| 1491 |
+
"step": 21875
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.41,
|
| 1495 |
+
"learning_rate": 2.072315371816204e-06,
|
| 1496 |
+
"loss": 0.0001,
|
| 1497 |
+
"step": 22000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.41,
|
| 1501 |
+
"eval_avg_sts": 0.8257198535359889,
|
| 1502 |
+
"eval_sickr_spearman": 0.7936219236744562,
|
| 1503 |
+
"eval_stsb_spearman": 0.8578177833975217,
|
| 1504 |
+
"step": 22000
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.42,
|
| 1508 |
+
"eval_avg_sts": 0.8270054813778303,
|
| 1509 |
+
"eval_sickr_spearman": 0.7958380306637094,
|
| 1510 |
+
"eval_stsb_spearman": 0.858172932091951,
|
| 1511 |
+
"step": 22125
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.42,
|
| 1515 |
+
"eval_avg_sts": 0.8270091578481822,
|
| 1516 |
+
"eval_sickr_spearman": 0.7962583028012928,
|
| 1517 |
+
"eval_stsb_spearman": 0.8577600128950715,
|
| 1518 |
+
"step": 22250
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.43,
|
| 1522 |
+
"eval_avg_sts": 0.8259725703398417,
|
| 1523 |
+
"eval_sickr_spearman": 0.7959245346773993,
|
| 1524 |
+
"eval_stsb_spearman": 0.8560206060022842,
|
| 1525 |
+
"step": 22375
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 1.44,
|
| 1529 |
+
"learning_rate": 1.9603225393574807e-06,
|
| 1530 |
+
"loss": 0.0002,
|
| 1531 |
+
"step": 22500
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 1.44,
|
| 1535 |
+
"eval_avg_sts": 0.8254714237214871,
|
| 1536 |
+
"eval_sickr_spearman": 0.7955676635937141,
|
| 1537 |
+
"eval_stsb_spearman": 0.8553751838492601,
|
| 1538 |
+
"step": 22500
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.45,
|
| 1542 |
+
"eval_avg_sts": 0.8243312613565763,
|
| 1543 |
+
"eval_sickr_spearman": 0.7926490056837258,
|
| 1544 |
+
"eval_stsb_spearman": 0.8560135170294269,
|
| 1545 |
+
"step": 22625
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 1.46,
|
| 1549 |
+
"eval_avg_sts": 0.8244931271533935,
|
| 1550 |
+
"eval_sickr_spearman": 0.7931114971594734,
|
| 1551 |
+
"eval_stsb_spearman": 0.8558747571473136,
|
| 1552 |
+
"step": 22750
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 1.46,
|
| 1556 |
+
"eval_avg_sts": 0.8245178381258861,
|
| 1557 |
+
"eval_sickr_spearman": 0.7931850518122927,
|
| 1558 |
+
"eval_stsb_spearman": 0.8558506244394795,
|
| 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": 0.8250123369922542,
|
| 1570 |
+
"eval_sickr_spearman": 0.7931228324994128,
|
| 1571 |
+
"eval_stsb_spearman": 0.8569018414850956,
|
| 1572 |
+
"step": 23000
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.48,
|
| 1576 |
+
"eval_avg_sts": 0.8254867372327745,
|
| 1577 |
+
"eval_sickr_spearman": 0.7938168819151935,
|
| 1578 |
+
"eval_stsb_spearman": 0.8571565925503556,
|
| 1579 |
+
"step": 23125
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.49,
|
| 1583 |
+
"eval_avg_sts": 0.8256499116596692,
|
| 1584 |
+
"eval_sickr_spearman": 0.7939716381240272,
|
| 1585 |
+
"eval_stsb_spearman": 0.8573281851953113,
|
| 1586 |
+
"step": 23250
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.5,
|
| 1590 |
+
"eval_avg_sts": 0.8258346679802114,
|
| 1591 |
+
"eval_sickr_spearman": 0.7940527146232547,
|
| 1592 |
+
"eval_stsb_spearman": 0.8576166213371682,
|
| 1593 |
+
"step": 23375
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.5,
|
| 1597 |
+
"learning_rate": 1.7363368744400357e-06,
|
| 1598 |
+
"loss": 0.0001,
|
| 1599 |
+
"step": 23500
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.5,
|
| 1603 |
+
"eval_avg_sts": 0.825945269207895,
|
| 1604 |
+
"eval_sickr_spearman": 0.7943781253354978,
|
| 1605 |
+
"eval_stsb_spearman": 0.8575124130802922,
|
| 1606 |
+
"step": 23500
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.51,
|
| 1610 |
+
"eval_avg_sts": 0.8258713568091718,
|
| 1611 |
+
"eval_sickr_spearman": 0.794315540810324,
|
| 1612 |
+
"eval_stsb_spearman": 0.8574271728080196,
|
| 1613 |
+
"step": 23625
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.52,
|
| 1617 |
+
"eval_avg_sts": 0.8258355435328646,
|
| 1618 |
+
"eval_sickr_spearman": 0.7940151062708286,
|
| 1619 |
+
"eval_stsb_spearman": 0.8576559807949005,
|
| 1620 |
+
"step": 23750
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.53,
|
| 1624 |
+
"eval_avg_sts": 0.8257865803230886,
|
| 1625 |
+
"eval_sickr_spearman": 0.7940416194388225,
|
| 1626 |
+
"eval_stsb_spearman": 0.8575315412073548,
|
| 1627 |
+
"step": 23875
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.54,
|
| 1631 |
+
"learning_rate": 1.6243440419813131e-06,
|
| 1632 |
+
"loss": 0.0002,
|
| 1633 |
+
"step": 24000
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.54,
|
| 1637 |
+
"eval_avg_sts": 0.8258057571249391,
|
| 1638 |
+
"eval_sickr_spearman": 0.7941539161539849,
|
| 1639 |
+
"eval_stsb_spearman": 0.8574575980958933,
|
| 1640 |
+
"step": 24000
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.54,
|
| 1644 |
+
"eval_avg_sts": 0.8258599414659757,
|
| 1645 |
+
"eval_sickr_spearman": 0.7942335517201692,
|
| 1646 |
+
"eval_stsb_spearman": 0.8574863312117823,
|
| 1647 |
+
"step": 24125
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.55,
|
| 1651 |
+
"eval_avg_sts": 0.8259837419138151,
|
| 1652 |
+
"eval_sickr_spearman": 0.7943245706573944,
|
| 1653 |
+
"eval_stsb_spearman": 0.8576429131702358,
|
| 1654 |
+
"step": 24250
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.56,
|
| 1658 |
+
"eval_avg_sts": 0.8273046944370666,
|
| 1659 |
+
"eval_sickr_spearman": 0.7953777005875265,
|
| 1660 |
+
"eval_stsb_spearman": 0.8592316882866066,
|
| 1661 |
+
"step": 24375
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.57,
|
| 1665 |
+
"learning_rate": 1.5123512095225906e-06,
|
| 1666 |
+
"loss": 0.0001,
|
| 1667 |
+
"step": 24500
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.57,
|
| 1671 |
+
"eval_avg_sts": 0.8270336322444836,
|
| 1672 |
+
"eval_sickr_spearman": 0.7948833644915253,
|
| 1673 |
+
"eval_stsb_spearman": 0.8591838999974419,
|
| 1674 |
+
"step": 24500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.58,
|
| 1678 |
+
"eval_avg_sts": 0.8268251999183458,
|
| 1679 |
+
"eval_sickr_spearman": 0.7944777418398805,
|
| 1680 |
+
"eval_stsb_spearman": 0.8591726579968111,
|
| 1681 |
+
"step": 24625
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.58,
|
| 1685 |
+
"eval_avg_sts": 0.8267020534374147,
|
| 1686 |
+
"eval_sickr_spearman": 0.7943936393812624,
|
| 1687 |
+
"eval_stsb_spearman": 0.8590104674935669,
|
| 1688 |
+
"step": 24750
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 1.59,
|
| 1692 |
+
"eval_avg_sts": 0.825917107993902,
|
| 1693 |
+
"eval_sickr_spearman": 0.7938579965380246,
|
| 1694 |
+
"eval_stsb_spearman": 0.8579762194497796,
|
| 1695 |
+
"step": 24875
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.6,
|
| 1699 |
+
"learning_rate": 1.4003583770638678e-06,
|
| 1700 |
+
"loss": 0.0002,
|
| 1701 |
+
"step": 25000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.6,
|
| 1705 |
+
"eval_avg_sts": 0.8263527703022291,
|
| 1706 |
+
"eval_sickr_spearman": 0.7941290360434399,
|
| 1707 |
+
"eval_stsb_spearman": 0.8585765045610182,
|
| 1708 |
+
"step": 25000
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.61,
|
| 1712 |
+
"eval_avg_sts": 0.8269584920385149,
|
| 1713 |
+
"eval_sickr_spearman": 0.7941601601971716,
|
| 1714 |
+
"eval_stsb_spearman": 0.8597568238798581,
|
| 1715 |
+
"step": 25125
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.62,
|
| 1719 |
+
"eval_avg_sts": 0.8264998215853827,
|
| 1720 |
+
"eval_sickr_spearman": 0.7927663936956405,
|
| 1721 |
+
"eval_stsb_spearman": 0.8602332494751249,
|
| 1722 |
+
"step": 25250
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.62,
|
| 1726 |
+
"eval_avg_sts": 0.825942745088348,
|
| 1727 |
+
"eval_sickr_spearman": 0.7922521246925426,
|
| 1728 |
+
"eval_stsb_spearman": 0.8596333654841534,
|
| 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": 0.8259010696773026,
|
| 1740 |
+
"eval_sickr_spearman": 0.7922646127789166,
|
| 1741 |
+
"eval_stsb_spearman": 0.8595375265756887,
|
| 1742 |
+
"step": 25500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 1.64,
|
| 1746 |
+
"eval_avg_sts": 0.8259285307896478,
|
| 1747 |
+
"eval_sickr_spearman": 0.7926812825838921,
|
| 1748 |
+
"eval_stsb_spearman": 0.8591757789954035,
|
| 1749 |
+
"step": 25625
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.65,
|
| 1753 |
+
"eval_avg_sts": 0.8258391793675839,
|
| 1754 |
+
"eval_sickr_spearman": 0.7926954517588166,
|
| 1755 |
+
"eval_stsb_spearman": 0.858982906976351,
|
| 1756 |
+
"step": 25750
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 1.66,
|
| 1760 |
+
"eval_avg_sts": 0.8258409312899861,
|
| 1761 |
+
"eval_sickr_spearman": 0.7928338293620596,
|
| 1762 |
+
"eval_stsb_spearman": 0.8588480332179126,
|
| 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": 0.8251984305884675,
|
| 1774 |
+
"eval_sickr_spearman": 0.7933060231202977,
|
| 1775 |
+
"eval_stsb_spearman": 0.8570908380566373,
|
| 1776 |
+
"step": 26000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.67,
|
| 1780 |
+
"eval_avg_sts": 0.8253196217152283,
|
| 1781 |
+
"eval_sickr_spearman": 0.7932125065657978,
|
| 1782 |
+
"eval_stsb_spearman": 0.8574267368646588,
|
| 1783 |
+
"step": 26125
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 1.68,
|
| 1787 |
+
"eval_avg_sts": 0.8253745698430313,
|
| 1788 |
+
"eval_sickr_spearman": 0.7933913263564519,
|
| 1789 |
+
"eval_stsb_spearman": 0.8573578133296105,
|
| 1790 |
+
"step": 26250
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.69,
|
| 1794 |
+
"eval_avg_sts": 0.825411316540875,
|
| 1795 |
+
"eval_sickr_spearman": 0.7934114513879544,
|
| 1796 |
+
"eval_stsb_spearman": 0.8574111816937955,
|
| 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": 0.8249370852399975,
|
| 1808 |
+
"eval_sickr_spearman": 0.7937128945805799,
|
| 1809 |
+
"eval_stsb_spearman": 0.8561612758994152,
|
| 1810 |
+
"step": 26500
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.7,
|
| 1814 |
+
"eval_avg_sts": 0.825459765367129,
|
| 1815 |
+
"eval_sickr_spearman": 0.7933420944774778,
|
| 1816 |
+
"eval_stsb_spearman": 0.8575774362567802,
|
| 1817 |
+
"step": 26625
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.71,
|
| 1821 |
+
"eval_avg_sts": 0.826427995376563,
|
| 1822 |
+
"eval_sickr_spearman": 0.7947685701590883,
|
| 1823 |
+
"eval_stsb_spearman": 0.8580874205940376,
|
| 1824 |
+
"step": 26750
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.72,
|
| 1828 |
+
"eval_avg_sts": 0.8258856380174763,
|
| 1829 |
+
"eval_sickr_spearman": 0.7942930142237495,
|
| 1830 |
+
"eval_stsb_spearman": 0.857478261811203,
|
| 1831 |
+
"step": 26875
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.73,
|
| 1835 |
+
"learning_rate": 9.523870472289774e-07,
|
| 1836 |
+
"loss": 0.0002,
|
| 1837 |
+
"step": 27000
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.73,
|
| 1841 |
+
"eval_avg_sts": 0.8258593024414255,
|
| 1842 |
+
"eval_sickr_spearman": 0.7941693821686479,
|
| 1843 |
+
"eval_stsb_spearman": 0.8575492227142031,
|
| 1844 |
+
"step": 27000
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.74,
|
| 1848 |
+
"eval_avg_sts": 0.8258720619743833,
|
| 1849 |
+
"eval_sickr_spearman": 0.7941788923267327,
|
| 1850 |
+
"eval_stsb_spearman": 0.857565231622034,
|
| 1851 |
+
"step": 27125
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.74,
|
| 1855 |
+
"eval_avg_sts": 0.8259531389747516,
|
| 1856 |
+
"eval_sickr_spearman": 0.7941532917496662,
|
| 1857 |
+
"eval_stsb_spearman": 0.8577529861998372,
|
| 1858 |
+
"step": 27250
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.75,
|
| 1862 |
+
"eval_avg_sts": 0.825969657799255,
|
| 1863 |
+
"eval_sickr_spearman": 0.7942109771024933,
|
| 1864 |
+
"eval_stsb_spearman": 0.8577283384960166,
|
| 1865 |
+
"step": 27375
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.76,
|
| 1869 |
+
"learning_rate": 8.403942147702547e-07,
|
| 1870 |
+
"loss": 0.0002,
|
| 1871 |
+
"step": 27500
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.76,
|
| 1875 |
+
"eval_avg_sts": 0.8259987251545413,
|
| 1876 |
+
"eval_sickr_spearman": 0.7943161171835413,
|
| 1877 |
+
"eval_stsb_spearman": 0.8576813331255413,
|
| 1878 |
+
"step": 27500
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.77,
|
| 1882 |
+
"eval_avg_sts": 0.8252131722274082,
|
| 1883 |
+
"eval_sickr_spearman": 0.793231382788663,
|
| 1884 |
+
"eval_stsb_spearman": 0.8571949616661534,
|
| 1885 |
+
"step": 27625
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.78,
|
| 1889 |
+
"eval_avg_sts": 0.8252604604270115,
|
| 1890 |
+
"eval_sickr_spearman": 0.7933024207876899,
|
| 1891 |
+
"eval_stsb_spearman": 0.857218500066333,
|
| 1892 |
+
"step": 27750
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.78,
|
| 1896 |
+
"eval_avg_sts": 0.8251969961170478,
|
| 1897 |
+
"eval_sickr_spearman": 0.793198385421975,
|
| 1898 |
+
"eval_stsb_spearman": 0.8571956068121205,
|
| 1899 |
+
"step": 27875
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.79,
|
| 1903 |
+
"learning_rate": 7.284013823115321e-07,
|
| 1904 |
+
"loss": 0.0002,
|
| 1905 |
+
"step": 28000
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.79,
|
| 1909 |
+
"eval_avg_sts": 0.825311717070901,
|
| 1910 |
+
"eval_sickr_spearman": 0.7931744179023573,
|
| 1911 |
+
"eval_stsb_spearman": 0.8574490162394447,
|
| 1912 |
+
"step": 28000
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 1.8,
|
| 1916 |
+
"eval_avg_sts": 0.8256482381761492,
|
| 1917 |
+
"eval_sickr_spearman": 0.7934648139416521,
|
| 1918 |
+
"eval_stsb_spearman": 0.8578316624106462,
|
| 1919 |
+
"step": 28125
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.81,
|
| 1923 |
+
"eval_avg_sts": 0.8261129479959839,
|
| 1924 |
+
"eval_sickr_spearman": 0.7939418588411357,
|
| 1925 |
+
"eval_stsb_spearman": 0.858284037150832,
|
| 1926 |
+
"step": 28250
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.82,
|
| 1930 |
+
"eval_avg_sts": 0.8262712326490254,
|
| 1931 |
+
"eval_sickr_spearman": 0.7933230261302068,
|
| 1932 |
+
"eval_stsb_spearman": 0.8592194391678438,
|
| 1933 |
+
"step": 28375
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.82,
|
| 1937 |
+
"learning_rate": 6.164085498528094e-07,
|
| 1938 |
+
"loss": 0.0002,
|
| 1939 |
+
"step": 28500
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.82,
|
| 1943 |
+
"eval_avg_sts": 0.8262943695062834,
|
| 1944 |
+
"eval_sickr_spearman": 0.7934199048618075,
|
| 1945 |
+
"eval_stsb_spearman": 0.8591688341507593,
|
| 1946 |
+
"step": 28500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.83,
|
| 1950 |
+
"eval_avg_sts": 0.8260598340905722,
|
| 1951 |
+
"eval_sickr_spearman": 0.7933951208134654,
|
| 1952 |
+
"eval_stsb_spearman": 0.8587245473676789,
|
| 1953 |
+
"step": 28625
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.84,
|
| 1957 |
+
"eval_avg_sts": 0.8259360112469695,
|
| 1958 |
+
"eval_sickr_spearman": 0.7933420944774778,
|
| 1959 |
+
"eval_stsb_spearman": 0.8585299280164611,
|
| 1960 |
+
"step": 28750
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.85,
|
| 1964 |
+
"eval_avg_sts": 0.8258330858999741,
|
| 1965 |
+
"eval_sickr_spearman": 0.7933054467470805,
|
| 1966 |
+
"eval_stsb_spearman": 0.8583607250528676,
|
| 1967 |
+
"step": 28875
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.86,
|
| 1971 |
+
"learning_rate": 5.044157173940868e-07,
|
| 1972 |
+
"loss": 0.0001,
|
| 1973 |
+
"step": 29000
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 1.86,
|
| 1977 |
+
"eval_avg_sts": 0.8258376969438936,
|
| 1978 |
+
"eval_sickr_spearman": 0.7933141884075422,
|
| 1979 |
+
"eval_stsb_spearman": 0.8583612054802452,
|
| 1980 |
+
"step": 29000
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 1.86,
|
| 1984 |
+
"eval_avg_sts": 0.8259136180644091,
|
| 1985 |
+
"eval_sickr_spearman": 0.7933194718287004,
|
| 1986 |
+
"eval_stsb_spearman": 0.8585077643001178,
|
| 1987 |
+
"step": 29125
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 1.87,
|
| 1991 |
+
"eval_avg_sts": 0.825910175107258,
|
| 1992 |
+
"eval_sickr_spearman": 0.7933039097518345,
|
| 1993 |
+
"eval_stsb_spearman": 0.8585164404626813,
|
| 1994 |
+
"step": 29250
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.88,
|
| 1998 |
+
"eval_avg_sts": 0.8258308833879402,
|
| 1999 |
+
"eval_sickr_spearman": 0.7933173584602371,
|
| 2000 |
+
"eval_stsb_spearman": 0.8583444083156432,
|
| 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": 0.8257221328599513,
|
| 2012 |
+
"eval_sickr_spearman": 0.7931374819853514,
|
| 2013 |
+
"eval_stsb_spearman": 0.8583067837345514,
|
| 2014 |
+
"step": 29500
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 1.9,
|
| 2018 |
+
"eval_avg_sts": 0.825786763719202,
|
| 2019 |
+
"eval_sickr_spearman": 0.7932694234210019,
|
| 2020 |
+
"eval_stsb_spearman": 0.858304104017402,
|
| 2021 |
+
"step": 29625
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 1.9,
|
| 2025 |
+
"eval_avg_sts": 0.8257681951340192,
|
| 2026 |
+
"eval_sickr_spearman": 0.7932804705743327,
|
| 2027 |
+
"eval_stsb_spearman": 0.8582559196937056,
|
| 2028 |
+
"step": 29750
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 1.91,
|
| 2032 |
+
"eval_avg_sts": 0.8258082608558808,
|
| 2033 |
+
"eval_sickr_spearman": 0.7933519408532725,
|
| 2034 |
+
"eval_stsb_spearman": 0.8582645808584891,
|
| 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": 0.8258262861889483,
|
| 2046 |
+
"eval_sickr_spearman": 0.7933999719547107,
|
| 2047 |
+
"eval_stsb_spearman": 0.8582526004231857,
|
| 2048 |
+
"step": 30000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.93,
|
| 2052 |
+
"eval_avg_sts": 0.8256086631585,
|
| 2053 |
+
"eval_sickr_spearman": 0.7930556369885008,
|
| 2054 |
+
"eval_stsb_spearman": 0.8581616893284993,
|
| 2055 |
+
"step": 30125
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 1.94,
|
| 2059 |
+
"eval_avg_sts": 0.8256480515518101,
|
| 2060 |
+
"eval_sickr_spearman": 0.7931325828130048,
|
| 2061 |
+
"eval_stsb_spearman": 0.8581635202906153,
|
| 2062 |
+
"step": 30250
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 1.94,
|
| 2066 |
+
"eval_avg_sts": 0.8258219208455879,
|
| 2067 |
+
"eval_sickr_spearman": 0.7934267252782117,
|
| 2068 |
+
"eval_stsb_spearman": 0.8582171164129642,
|
| 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": 0.8258322719939588,
|
| 2080 |
+
"eval_sickr_spearman": 0.7934731233222009,
|
| 2081 |
+
"eval_stsb_spearman": 0.8581914206657169,
|
| 2082 |
+
"step": 30500
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.96,
|
| 2086 |
+
"eval_avg_sts": 0.8258242424865203,
|
| 2087 |
+
"eval_sickr_spearman": 0.7934302315486167,
|
| 2088 |
+
"eval_stsb_spearman": 0.858218253424424,
|
| 2089 |
+
"step": 30625
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.97,
|
| 2093 |
+
"eval_avg_sts": 0.8258248316168127,
|
| 2094 |
+
"eval_sickr_spearman": 0.7934435841948165,
|
| 2095 |
+
"eval_stsb_spearman": 0.858206079038809,
|
| 2096 |
+
"step": 30750
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.98,
|
| 2100 |
+
"eval_avg_sts": 0.8257922895919085,
|
| 2101 |
+
"eval_sickr_spearman": 0.7933790303944838,
|
| 2102 |
+
"eval_stsb_spearman": 0.8582055487893332,
|
| 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": 0.8257897415072173,
|
| 2114 |
+
"eval_sickr_spearman": 0.7933720178536738,
|
| 2115 |
+
"eval_stsb_spearman": 0.8582074651607609,
|
| 2116 |
+
"step": 31000
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.99,
|
| 2120 |
+
"eval_avg_sts": 0.8257977713308224,
|
| 2121 |
+
"eval_sickr_spearman": 0.7933829209137002,
|
| 2122 |
+
"eval_stsb_spearman": 0.8582126217479447,
|
| 2123 |
+
"step": 31125
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 2.0,
|
| 2127 |
+
"eval_avg_sts": 0.8258126560134551,
|
| 2128 |
+
"eval_sickr_spearman": 0.7934017010743625,
|
| 2129 |
+
"eval_stsb_spearman": 0.8582236109525477,
|
| 2130 |
+
"step": 31250
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 2.0,
|
| 2134 |
+
"step": 31252,
|
| 2135 |
+
"train_runtime": 21163.9877,
|
| 2136 |
+
"train_samples_per_second": 1.477
|
| 2137 |
+
}
|
| 2138 |
+
],
|
| 2139 |
+
"max_steps": 31252,
|
| 2140 |
+
"num_train_epochs": 2,
|
| 2141 |
+
"total_flos": 776159526314354880,
|
| 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:b62de19596bba1fff78bcccbfa92f5b6bbfcea66eef5978916f4d4365d460033
|
| 3 |
+
size 2095
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|