Upload 9 files
Browse files- config.json +24 -0
- eval_results.txt +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +1426 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/longgen-soft_sort-multicse-bert-large-uncased-lr:3e-6-es:25-dw:0.5",
|
| 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 = 0.3
|
| 2 |
+
eval_CR = 90.42
|
| 3 |
+
eval_MPQA = 89.54
|
| 4 |
+
eval_MR = 84.37
|
| 5 |
+
eval_MRPC = 75.86
|
| 6 |
+
eval_SST2 = 89.22
|
| 7 |
+
eval_SUBJ = 95.08
|
| 8 |
+
eval_TREC = 80.47
|
| 9 |
+
eval_avg_sts = 0.8620181447373103
|
| 10 |
+
eval_avg_transfer = 86.42285714285715
|
| 11 |
+
eval_sickr_spearman = 0.8451327343184558
|
| 12 |
+
eval_stsb_spearman = 0.8789035551561649
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d89003c22e89245aedc77b2d41c0308ce91216872b43ae8f12a16bd9c70115b0
|
| 3 |
+
size 1340732138
|
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, "special_tokens_map_file": null, "name_or_path": "/data/lyhe/SentenceGen/RankCSE-master/checkpoints/multicse-bert-large-uncased", "do_basic_tokenize": true, "never_split": null}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 0.3
|
| 2 |
+
train_runtime = 2847.5807
|
| 3 |
+
train_samples_per_second = 1.692
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1426 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8620181447373103,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/longgen-soft_sort-multicse-bert-large-uncased-lr:3e-6-es:25-dw:0.5",
|
| 4 |
+
"epoch": 0.3000062254871444,
|
| 5 |
+
"global_step": 4819,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"eval_avg_sts": 0.7624996022459282,
|
| 13 |
+
"eval_sickr_spearman": 0.7306625637849724,
|
| 14 |
+
"eval_stsb_spearman": 0.7943366407068839,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"eval_avg_sts": 0.8071313365516628,
|
| 20 |
+
"eval_sickr_spearman": 0.7781768986027124,
|
| 21 |
+
"eval_stsb_spearman": 0.8360857745006132,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.08,
|
| 26 |
+
"eval_avg_sts": 0.8149248188031465,
|
| 27 |
+
"eval_sickr_spearman": 0.7874237501893749,
|
| 28 |
+
"eval_stsb_spearman": 0.842425887416918,
|
| 29 |
+
"step": 75
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.11,
|
| 33 |
+
"eval_avg_sts": 0.8218597211542165,
|
| 34 |
+
"eval_sickr_spearman": 0.7970756000233636,
|
| 35 |
+
"eval_stsb_spearman": 0.8466438422850692,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.14,
|
| 40 |
+
"eval_avg_sts": 0.8222996516785348,
|
| 41 |
+
"eval_sickr_spearman": 0.7976810320569911,
|
| 42 |
+
"eval_stsb_spearman": 0.8469182713000784,
|
| 43 |
+
"step": 125
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.17,
|
| 47 |
+
"eval_avg_sts": 0.8296571369885761,
|
| 48 |
+
"eval_sickr_spearman": 0.806694500521766,
|
| 49 |
+
"eval_stsb_spearman": 0.8526197734553864,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"eval_avg_sts": 0.8336126250309825,
|
| 55 |
+
"eval_sickr_spearman": 0.8114649014854978,
|
| 56 |
+
"eval_stsb_spearman": 0.8557603485764674,
|
| 57 |
+
"step": 175
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.22,
|
| 61 |
+
"eval_avg_sts": 0.8353162227426572,
|
| 62 |
+
"eval_sickr_spearman": 0.8118504471367415,
|
| 63 |
+
"eval_stsb_spearman": 0.8587819983485729,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.25,
|
| 68 |
+
"eval_avg_sts": 0.8300942602644428,
|
| 69 |
+
"eval_sickr_spearman": 0.8061713937960034,
|
| 70 |
+
"eval_stsb_spearman": 0.8540171267328822,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.28,
|
| 75 |
+
"eval_avg_sts": 0.8347835912873767,
|
| 76 |
+
"eval_sickr_spearman": 0.8143648272659254,
|
| 77 |
+
"eval_stsb_spearman": 0.855202355308828,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.3,
|
| 82 |
+
"eval_avg_sts": 0.8319994856438386,
|
| 83 |
+
"eval_sickr_spearman": 0.8115708100641689,
|
| 84 |
+
"eval_stsb_spearman": 0.8524281612235085,
|
| 85 |
+
"step": 275
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.33,
|
| 89 |
+
"eval_avg_sts": 0.8368355138029437,
|
| 90 |
+
"eval_sickr_spearman": 0.8189529021685982,
|
| 91 |
+
"eval_stsb_spearman": 0.8547181254372894,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"eval_avg_sts": 0.8374901642309274,
|
| 97 |
+
"eval_sickr_spearman": 0.8199181832142,
|
| 98 |
+
"eval_stsb_spearman": 0.8550621452476548,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.39,
|
| 103 |
+
"eval_avg_sts": 0.835477792488754,
|
| 104 |
+
"eval_sickr_spearman": 0.814654118589887,
|
| 105 |
+
"eval_stsb_spearman": 0.8563014663876211,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.42,
|
| 110 |
+
"eval_avg_sts": 0.839369517546883,
|
| 111 |
+
"eval_sickr_spearman": 0.8205669393013246,
|
| 112 |
+
"eval_stsb_spearman": 0.8581720957924415,
|
| 113 |
+
"step": 375
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.44,
|
| 117 |
+
"eval_avg_sts": 0.8380452297674821,
|
| 118 |
+
"eval_sickr_spearman": 0.8173899220967006,
|
| 119 |
+
"eval_stsb_spearman": 0.8587005374382635,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.47,
|
| 124 |
+
"eval_avg_sts": 0.8416927413750428,
|
| 125 |
+
"eval_sickr_spearman": 0.8239470800339302,
|
| 126 |
+
"eval_stsb_spearman": 0.8594384027161553,
|
| 127 |
+
"step": 425
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.5,
|
| 131 |
+
"eval_avg_sts": 0.8319043646289148,
|
| 132 |
+
"eval_sickr_spearman": 0.8098517769436988,
|
| 133 |
+
"eval_stsb_spearman": 0.8539569523141309,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.53,
|
| 138 |
+
"eval_avg_sts": 0.8327259954986015,
|
| 139 |
+
"eval_sickr_spearman": 0.8118681706131722,
|
| 140 |
+
"eval_stsb_spearman": 0.8535838203840307,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.55,
|
| 145 |
+
"learning_rate": 8.152254249815226e-06,
|
| 146 |
+
"loss": 0.4849,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.55,
|
| 151 |
+
"eval_avg_sts": 0.8398049341434459,
|
| 152 |
+
"eval_sickr_spearman": 0.8219116180171858,
|
| 153 |
+
"eval_stsb_spearman": 0.857698250269706,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.58,
|
| 158 |
+
"eval_avg_sts": 0.8399287988815654,
|
| 159 |
+
"eval_sickr_spearman": 0.8219933669518336,
|
| 160 |
+
"eval_stsb_spearman": 0.8578642308112973,
|
| 161 |
+
"step": 525
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.61,
|
| 165 |
+
"eval_avg_sts": 0.8372186514713016,
|
| 166 |
+
"eval_sickr_spearman": 0.8191553052300584,
|
| 167 |
+
"eval_stsb_spearman": 0.8552819977125447,
|
| 168 |
+
"step": 550
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.64,
|
| 172 |
+
"eval_avg_sts": 0.8397984072854183,
|
| 173 |
+
"eval_sickr_spearman": 0.8222581624140619,
|
| 174 |
+
"eval_stsb_spearman": 0.8573386521567748,
|
| 175 |
+
"step": 575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.67,
|
| 179 |
+
"eval_avg_sts": 0.8424072290367514,
|
| 180 |
+
"eval_sickr_spearman": 0.8249417080825108,
|
| 181 |
+
"eval_stsb_spearman": 0.859872749990992,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.69,
|
| 186 |
+
"eval_avg_sts": 0.8389197343591988,
|
| 187 |
+
"eval_sickr_spearman": 0.8207355284673723,
|
| 188 |
+
"eval_stsb_spearman": 0.8571039402510253,
|
| 189 |
+
"step": 625
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.72,
|
| 193 |
+
"eval_avg_sts": 0.8418254593701419,
|
| 194 |
+
"eval_sickr_spearman": 0.8221261729473099,
|
| 195 |
+
"eval_stsb_spearman": 0.8615247457929738,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.75,
|
| 200 |
+
"eval_avg_sts": 0.844244457574689,
|
| 201 |
+
"eval_sickr_spearman": 0.824336131955579,
|
| 202 |
+
"eval_stsb_spearman": 0.8641527831937991,
|
| 203 |
+
"step": 675
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.78,
|
| 207 |
+
"eval_avg_sts": 0.8422699522786281,
|
| 208 |
+
"eval_sickr_spearman": 0.8214674744221877,
|
| 209 |
+
"eval_stsb_spearman": 0.8630724301350685,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8,
|
| 214 |
+
"eval_avg_sts": 0.8437980698256882,
|
| 215 |
+
"eval_sickr_spearman": 0.824677537024601,
|
| 216 |
+
"eval_stsb_spearman": 0.8629186026267753,
|
| 217 |
+
"step": 725
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.83,
|
| 221 |
+
"eval_avg_sts": 0.8439136197370887,
|
| 222 |
+
"eval_sickr_spearman": 0.8249638984513751,
|
| 223 |
+
"eval_stsb_spearman": 0.8628633410228024,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.86,
|
| 228 |
+
"eval_avg_sts": 0.8426886128766484,
|
| 229 |
+
"eval_sickr_spearman": 0.8233757020512226,
|
| 230 |
+
"eval_stsb_spearman": 0.8620015237020744,
|
| 231 |
+
"step": 775
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.89,
|
| 235 |
+
"eval_avg_sts": 0.841929144469251,
|
| 236 |
+
"eval_sickr_spearman": 0.8214800585707644,
|
| 237 |
+
"eval_stsb_spearman": 0.8623782303677376,
|
| 238 |
+
"step": 800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.91,
|
| 242 |
+
"eval_avg_sts": 0.8463814591231265,
|
| 243 |
+
"eval_sickr_spearman": 0.827185240830685,
|
| 244 |
+
"eval_stsb_spearman": 0.8655776774155678,
|
| 245 |
+
"step": 825
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.94,
|
| 249 |
+
"eval_avg_sts": 0.8382240140191579,
|
| 250 |
+
"eval_sickr_spearman": 0.8145595933822568,
|
| 251 |
+
"eval_stsb_spearman": 0.8618884346560589,
|
| 252 |
+
"step": 850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.97,
|
| 256 |
+
"eval_avg_sts": 0.8402986385705378,
|
| 257 |
+
"eval_sickr_spearman": 0.818052799327648,
|
| 258 |
+
"eval_stsb_spearman": 0.8625444778134276,
|
| 259 |
+
"step": 875
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.0,
|
| 263 |
+
"eval_avg_sts": 0.8417166888579826,
|
| 264 |
+
"eval_sickr_spearman": 0.8214943238078914,
|
| 265 |
+
"eval_stsb_spearman": 0.8619390539080737,
|
| 266 |
+
"step": 900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.03,
|
| 270 |
+
"eval_avg_sts": 0.840021113372968,
|
| 271 |
+
"eval_sickr_spearman": 0.8206462386497989,
|
| 272 |
+
"eval_stsb_spearman": 0.8593959880961373,
|
| 273 |
+
"step": 925
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.05,
|
| 277 |
+
"eval_avg_sts": 0.8407725046557779,
|
| 278 |
+
"eval_sickr_spearman": 0.8213717484370214,
|
| 279 |
+
"eval_stsb_spearman": 0.8601732608745344,
|
| 280 |
+
"step": 950
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.08,
|
| 284 |
+
"eval_avg_sts": 0.8431906318067501,
|
| 285 |
+
"eval_sickr_spearman": 0.8246691796129508,
|
| 286 |
+
"eval_stsb_spearman": 0.8617120840005495,
|
| 287 |
+
"step": 975
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.11,
|
| 291 |
+
"learning_rate": 6.304508499630452e-06,
|
| 292 |
+
"loss": 0.3038,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.11,
|
| 297 |
+
"eval_avg_sts": 0.8416510189604846,
|
| 298 |
+
"eval_sickr_spearman": 0.822419114634981,
|
| 299 |
+
"eval_stsb_spearman": 0.8608829232859881,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.14,
|
| 304 |
+
"eval_avg_sts": 0.8447615088290126,
|
| 305 |
+
"eval_sickr_spearman": 0.8269052195093008,
|
| 306 |
+
"eval_stsb_spearman": 0.8626177981487243,
|
| 307 |
+
"step": 1025
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.16,
|
| 311 |
+
"eval_avg_sts": 0.8424856124518805,
|
| 312 |
+
"eval_sickr_spearman": 0.8238848317264664,
|
| 313 |
+
"eval_stsb_spearman": 0.8610863931772945,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.19,
|
| 318 |
+
"eval_avg_sts": 0.8424277323953787,
|
| 319 |
+
"eval_sickr_spearman": 0.8237316125128787,
|
| 320 |
+
"eval_stsb_spearman": 0.8611238522778787,
|
| 321 |
+
"step": 1075
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.22,
|
| 325 |
+
"eval_avg_sts": 0.8442776434640062,
|
| 326 |
+
"eval_sickr_spearman": 0.8274288545771791,
|
| 327 |
+
"eval_stsb_spearman": 0.8611264323508335,
|
| 328 |
+
"step": 1100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.25,
|
| 332 |
+
"eval_avg_sts": 0.8442605597470911,
|
| 333 |
+
"eval_sickr_spearman": 0.8269961423843231,
|
| 334 |
+
"eval_stsb_spearman": 0.8615249771098593,
|
| 335 |
+
"step": 1125
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.27,
|
| 339 |
+
"eval_avg_sts": 0.8460938684955821,
|
| 340 |
+
"eval_sickr_spearman": 0.8296871328734947,
|
| 341 |
+
"eval_stsb_spearman": 0.8625006041176696,
|
| 342 |
+
"step": 1150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.3,
|
| 346 |
+
"eval_avg_sts": 0.8452328292042266,
|
| 347 |
+
"eval_sickr_spearman": 0.8290738237392314,
|
| 348 |
+
"eval_stsb_spearman": 0.8613918346692219,
|
| 349 |
+
"step": 1175
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.33,
|
| 353 |
+
"eval_avg_sts": 0.8443542857305267,
|
| 354 |
+
"eval_sickr_spearman": 0.8283039812453815,
|
| 355 |
+
"eval_stsb_spearman": 0.860404590215672,
|
| 356 |
+
"step": 1200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.36,
|
| 360 |
+
"eval_avg_sts": 0.8455779584769261,
|
| 361 |
+
"eval_sickr_spearman": 0.8298153759143346,
|
| 362 |
+
"eval_stsb_spearman": 0.8613405410395174,
|
| 363 |
+
"step": 1225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.39,
|
| 367 |
+
"eval_avg_sts": 0.8465431787883896,
|
| 368 |
+
"eval_sickr_spearman": 0.8306829136685097,
|
| 369 |
+
"eval_stsb_spearman": 0.8624034439082695,
|
| 370 |
+
"step": 1250
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.41,
|
| 374 |
+
"eval_avg_sts": 0.8452222856659524,
|
| 375 |
+
"eval_sickr_spearman": 0.8282286684783264,
|
| 376 |
+
"eval_stsb_spearman": 0.8622159028535784,
|
| 377 |
+
"step": 1275
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.44,
|
| 381 |
+
"eval_avg_sts": 0.8460353103962084,
|
| 382 |
+
"eval_sickr_spearman": 0.8289619112728808,
|
| 383 |
+
"eval_stsb_spearman": 0.8631087095195359,
|
| 384 |
+
"step": 1300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.47,
|
| 388 |
+
"eval_avg_sts": 0.8428046052986686,
|
| 389 |
+
"eval_sickr_spearman": 0.8233728201851361,
|
| 390 |
+
"eval_stsb_spearman": 0.862236390412201,
|
| 391 |
+
"step": 1325
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.5,
|
| 395 |
+
"eval_avg_sts": 0.8439709964632203,
|
| 396 |
+
"eval_sickr_spearman": 0.8263711616924103,
|
| 397 |
+
"eval_stsb_spearman": 0.8615708312340303,
|
| 398 |
+
"step": 1350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.52,
|
| 402 |
+
"eval_avg_sts": 0.8464117078835496,
|
| 403 |
+
"eval_sickr_spearman": 0.8287957716930062,
|
| 404 |
+
"eval_stsb_spearman": 0.8640276440740928,
|
| 405 |
+
"step": 1375
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.55,
|
| 409 |
+
"eval_avg_sts": 0.8426142536649475,
|
| 410 |
+
"eval_sickr_spearman": 0.8228226239181626,
|
| 411 |
+
"eval_stsb_spearman": 0.8624058834117323,
|
| 412 |
+
"step": 1400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.58,
|
| 416 |
+
"eval_avg_sts": 0.84970489436635,
|
| 417 |
+
"eval_sickr_spearman": 0.8333206856972879,
|
| 418 |
+
"eval_stsb_spearman": 0.8660891030354121,
|
| 419 |
+
"step": 1425
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.61,
|
| 423 |
+
"eval_avg_sts": 0.8459628076570953,
|
| 424 |
+
"eval_sickr_spearman": 0.8295129240685788,
|
| 425 |
+
"eval_stsb_spearman": 0.8624126912456118,
|
| 426 |
+
"step": 1450
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.64,
|
| 430 |
+
"eval_avg_sts": 0.8464511583090627,
|
| 431 |
+
"eval_sickr_spearman": 0.8300802674387656,
|
| 432 |
+
"eval_stsb_spearman": 0.8628220491793598,
|
| 433 |
+
"step": 1475
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.66,
|
| 437 |
+
"learning_rate": 4.456762749445676e-06,
|
| 438 |
+
"loss": 0.2711,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.66,
|
| 443 |
+
"eval_avg_sts": 0.8432266307908444,
|
| 444 |
+
"eval_sickr_spearman": 0.8264625168473455,
|
| 445 |
+
"eval_stsb_spearman": 0.8599907447343432,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.69,
|
| 450 |
+
"eval_avg_sts": 0.8444286205972751,
|
| 451 |
+
"eval_sickr_spearman": 0.8294252673084542,
|
| 452 |
+
"eval_stsb_spearman": 0.859431973886096,
|
| 453 |
+
"step": 1525
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.72,
|
| 457 |
+
"eval_avg_sts": 0.8448525205916575,
|
| 458 |
+
"eval_sickr_spearman": 0.8308334911715182,
|
| 459 |
+
"eval_stsb_spearman": 0.8588715500117969,
|
| 460 |
+
"step": 1550
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.75,
|
| 464 |
+
"eval_avg_sts": 0.8411986614799187,
|
| 465 |
+
"eval_sickr_spearman": 0.8257495912086997,
|
| 466 |
+
"eval_stsb_spearman": 0.8566477317511376,
|
| 467 |
+
"step": 1575
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.77,
|
| 471 |
+
"eval_avg_sts": 0.8429029812617075,
|
| 472 |
+
"eval_sickr_spearman": 0.8264979157691056,
|
| 473 |
+
"eval_stsb_spearman": 0.8593080467543093,
|
| 474 |
+
"step": 1600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8,
|
| 478 |
+
"eval_avg_sts": 0.844172778094097,
|
| 479 |
+
"eval_sickr_spearman": 0.8278518644875444,
|
| 480 |
+
"eval_stsb_spearman": 0.8604936917006495,
|
| 481 |
+
"step": 1625
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.83,
|
| 485 |
+
"eval_avg_sts": 0.8440312504721765,
|
| 486 |
+
"eval_sickr_spearman": 0.828057053352888,
|
| 487 |
+
"eval_stsb_spearman": 0.8600054475914649,
|
| 488 |
+
"step": 1650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.86,
|
| 492 |
+
"eval_avg_sts": 0.8466716345393903,
|
| 493 |
+
"eval_sickr_spearman": 0.8323783154870722,
|
| 494 |
+
"eval_stsb_spearman": 0.8609649535917084,
|
| 495 |
+
"step": 1675
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.88,
|
| 499 |
+
"eval_avg_sts": 0.8470752337564638,
|
| 500 |
+
"eval_sickr_spearman": 0.8329202984356999,
|
| 501 |
+
"eval_stsb_spearman": 0.8612301690772276,
|
| 502 |
+
"step": 1700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.91,
|
| 506 |
+
"eval_avg_sts": 0.8491146738016275,
|
| 507 |
+
"eval_sickr_spearman": 0.8357918378351774,
|
| 508 |
+
"eval_stsb_spearman": 0.8624375097680775,
|
| 509 |
+
"step": 1725
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.94,
|
| 513 |
+
"eval_avg_sts": 0.8490639696081586,
|
| 514 |
+
"eval_sickr_spearman": 0.8353252637158076,
|
| 515 |
+
"eval_stsb_spearman": 0.8628026755005095,
|
| 516 |
+
"step": 1750
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.97,
|
| 520 |
+
"eval_avg_sts": 0.8490725041726443,
|
| 521 |
+
"eval_sickr_spearman": 0.8349738681776864,
|
| 522 |
+
"eval_stsb_spearman": 0.8631711401676022,
|
| 523 |
+
"step": 1775
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.0,
|
| 527 |
+
"eval_avg_sts": 0.849465151594995,
|
| 528 |
+
"eval_sickr_spearman": 0.8350664241101576,
|
| 529 |
+
"eval_stsb_spearman": 0.8638638790798324,
|
| 530 |
+
"step": 1800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.02,
|
| 534 |
+
"eval_avg_sts": 0.8486443980616268,
|
| 535 |
+
"eval_sickr_spearman": 0.8342315955360619,
|
| 536 |
+
"eval_stsb_spearman": 0.8630572005871918,
|
| 537 |
+
"step": 1825
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.05,
|
| 541 |
+
"eval_avg_sts": 0.8476111291438189,
|
| 542 |
+
"eval_sickr_spearman": 0.8335225604166323,
|
| 543 |
+
"eval_stsb_spearman": 0.8616996978710053,
|
| 544 |
+
"step": 1850
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.08,
|
| 548 |
+
"eval_avg_sts": 0.8474970961473779,
|
| 549 |
+
"eval_sickr_spearman": 0.8330892238194576,
|
| 550 |
+
"eval_stsb_spearman": 0.8619049684752982,
|
| 551 |
+
"step": 1875
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.11,
|
| 555 |
+
"eval_avg_sts": 0.8477943008360005,
|
| 556 |
+
"eval_sickr_spearman": 0.8332226061881515,
|
| 557 |
+
"eval_stsb_spearman": 0.8623659954838494,
|
| 558 |
+
"step": 1900
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.13,
|
| 562 |
+
"eval_avg_sts": 0.8464807160435242,
|
| 563 |
+
"eval_sickr_spearman": 0.8316015565146151,
|
| 564 |
+
"eval_stsb_spearman": 0.8613598755724333,
|
| 565 |
+
"step": 1925
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.16,
|
| 569 |
+
"eval_avg_sts": 0.8462238944734057,
|
| 570 |
+
"eval_sickr_spearman": 0.831052512994076,
|
| 571 |
+
"eval_stsb_spearman": 0.8613952759527355,
|
| 572 |
+
"step": 1950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.19,
|
| 576 |
+
"eval_avg_sts": 0.8464057290981915,
|
| 577 |
+
"eval_sickr_spearman": 0.8310086125673615,
|
| 578 |
+
"eval_stsb_spearman": 0.8618028456290214,
|
| 579 |
+
"step": 1975
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.22,
|
| 583 |
+
"learning_rate": 2.609016999260902e-06,
|
| 584 |
+
"loss": 0.258,
|
| 585 |
+
"step": 2000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.22,
|
| 589 |
+
"eval_avg_sts": 0.8468793796616104,
|
| 590 |
+
"eval_sickr_spearman": 0.8316847944134073,
|
| 591 |
+
"eval_stsb_spearman": 0.8620739649098136,
|
| 592 |
+
"step": 2000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.25,
|
| 596 |
+
"eval_avg_sts": 0.8473069362456496,
|
| 597 |
+
"eval_sickr_spearman": 0.8321533858390374,
|
| 598 |
+
"eval_stsb_spearman": 0.8624604866522616,
|
| 599 |
+
"step": 2025
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.27,
|
| 603 |
+
"eval_avg_sts": 0.8458607867715203,
|
| 604 |
+
"eval_sickr_spearman": 0.8302502975378566,
|
| 605 |
+
"eval_stsb_spearman": 0.861471276005184,
|
| 606 |
+
"step": 2050
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.3,
|
| 610 |
+
"eval_avg_sts": 0.8465971265934726,
|
| 611 |
+
"eval_sickr_spearman": 0.8308937702038229,
|
| 612 |
+
"eval_stsb_spearman": 0.8623004829831225,
|
| 613 |
+
"step": 2075
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.33,
|
| 617 |
+
"eval_avg_sts": 0.8476369809742725,
|
| 618 |
+
"eval_sickr_spearman": 0.8326747154140468,
|
| 619 |
+
"eval_stsb_spearman": 0.8625992465344982,
|
| 620 |
+
"step": 2100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.36,
|
| 624 |
+
"eval_avg_sts": 0.8487784986875214,
|
| 625 |
+
"eval_sickr_spearman": 0.833981881839685,
|
| 626 |
+
"eval_stsb_spearman": 0.8635751155353578,
|
| 627 |
+
"step": 2125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.38,
|
| 631 |
+
"eval_avg_sts": 0.8482552739490947,
|
| 632 |
+
"eval_sickr_spearman": 0.8330946513339202,
|
| 633 |
+
"eval_stsb_spearman": 0.8634158965642693,
|
| 634 |
+
"step": 2150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.41,
|
| 638 |
+
"eval_avg_sts": 0.8459693374985795,
|
| 639 |
+
"eval_sickr_spearman": 0.8297586992146375,
|
| 640 |
+
"eval_stsb_spearman": 0.8621799757825214,
|
| 641 |
+
"step": 2175
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.44,
|
| 645 |
+
"eval_avg_sts": 0.8476635726729035,
|
| 646 |
+
"eval_sickr_spearman": 0.8323805729488398,
|
| 647 |
+
"eval_stsb_spearman": 0.8629465723969671,
|
| 648 |
+
"step": 2200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.47,
|
| 652 |
+
"eval_avg_sts": 0.8479733460637723,
|
| 653 |
+
"eval_sickr_spearman": 0.8331660735817588,
|
| 654 |
+
"eval_stsb_spearman": 0.8627806185457858,
|
| 655 |
+
"step": 2225
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.49,
|
| 659 |
+
"eval_avg_sts": 0.8473017297750429,
|
| 660 |
+
"eval_sickr_spearman": 0.8320290333174142,
|
| 661 |
+
"eval_stsb_spearman": 0.8625744262326718,
|
| 662 |
+
"step": 2250
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.52,
|
| 666 |
+
"eval_avg_sts": 0.8479177356313778,
|
| 667 |
+
"eval_sickr_spearman": 0.8327113151133426,
|
| 668 |
+
"eval_stsb_spearman": 0.863124156149413,
|
| 669 |
+
"step": 2275
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.55,
|
| 673 |
+
"eval_avg_sts": 0.8475060767928835,
|
| 674 |
+
"eval_sickr_spearman": 0.8321914264713766,
|
| 675 |
+
"eval_stsb_spearman": 0.8628207271143905,
|
| 676 |
+
"step": 2300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.58,
|
| 680 |
+
"eval_avg_sts": 0.8471482251359982,
|
| 681 |
+
"eval_sickr_spearman": 0.831474706375717,
|
| 682 |
+
"eval_stsb_spearman": 0.8628217438962794,
|
| 683 |
+
"step": 2325
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.61,
|
| 687 |
+
"eval_avg_sts": 0.8471555097744191,
|
| 688 |
+
"eval_sickr_spearman": 0.8313104880399002,
|
| 689 |
+
"eval_stsb_spearman": 0.8630005315089381,
|
| 690 |
+
"step": 2350
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.63,
|
| 694 |
+
"eval_avg_sts": 0.8463330579657068,
|
| 695 |
+
"eval_sickr_spearman": 0.8301000562525582,
|
| 696 |
+
"eval_stsb_spearman": 0.8625660596788554,
|
| 697 |
+
"step": 2375
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.66,
|
| 701 |
+
"eval_avg_sts": 0.8462206147101088,
|
| 702 |
+
"eval_sickr_spearman": 0.8299467890078692,
|
| 703 |
+
"eval_stsb_spearman": 0.8624944404123482,
|
| 704 |
+
"step": 2400
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.69,
|
| 708 |
+
"eval_avg_sts": 0.8466291774217871,
|
| 709 |
+
"eval_sickr_spearman": 0.8307020300468819,
|
| 710 |
+
"eval_stsb_spearman": 0.8625563247966924,
|
| 711 |
+
"step": 2425
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.72,
|
| 715 |
+
"eval_avg_sts": 0.846255947089394,
|
| 716 |
+
"eval_sickr_spearman": 0.8300505801238202,
|
| 717 |
+
"eval_stsb_spearman": 0.8624613140549677,
|
| 718 |
+
"step": 2450
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.74,
|
| 722 |
+
"eval_avg_sts": 0.84652808904023,
|
| 723 |
+
"eval_sickr_spearman": 0.830373449281944,
|
| 724 |
+
"eval_stsb_spearman": 0.8626827287985159,
|
| 725 |
+
"step": 2475
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.77,
|
| 729 |
+
"learning_rate": 7.612712490761272e-07,
|
| 730 |
+
"loss": 0.2459,
|
| 731 |
+
"step": 2500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.77,
|
| 735 |
+
"eval_avg_sts": 0.8462118162645162,
|
| 736 |
+
"eval_sickr_spearman": 0.830052889710946,
|
| 737 |
+
"eval_stsb_spearman": 0.8623707428180863,
|
| 738 |
+
"step": 2500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.8,
|
| 742 |
+
"eval_avg_sts": 0.8459259791683191,
|
| 743 |
+
"eval_sickr_spearman": 0.8294702724505018,
|
| 744 |
+
"eval_stsb_spearman": 0.8623816858861365,
|
| 745 |
+
"step": 2525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.83,
|
| 749 |
+
"eval_avg_sts": 0.8464449438786035,
|
| 750 |
+
"eval_sickr_spearman": 0.8304476093025643,
|
| 751 |
+
"eval_stsb_spearman": 0.8624422784546426,
|
| 752 |
+
"step": 2550
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.85,
|
| 756 |
+
"eval_avg_sts": 0.84648379412736,
|
| 757 |
+
"eval_sickr_spearman": 0.8305015962605808,
|
| 758 |
+
"eval_stsb_spearman": 0.8624659919941392,
|
| 759 |
+
"step": 2575
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.88,
|
| 763 |
+
"eval_avg_sts": 0.8465871172906757,
|
| 764 |
+
"eval_sickr_spearman": 0.8306914151734642,
|
| 765 |
+
"eval_stsb_spearman": 0.8624828194078872,
|
| 766 |
+
"step": 2600
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.91,
|
| 770 |
+
"eval_avg_sts": 0.8464858615057194,
|
| 771 |
+
"eval_sickr_spearman": 0.8305917026068788,
|
| 772 |
+
"eval_stsb_spearman": 0.8623800204045601,
|
| 773 |
+
"step": 2625
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.94,
|
| 777 |
+
"eval_avg_sts": 0.8466908586012467,
|
| 778 |
+
"eval_sickr_spearman": 0.8309179778789479,
|
| 779 |
+
"eval_stsb_spearman": 0.8624637393235455,
|
| 780 |
+
"step": 2650
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.97,
|
| 784 |
+
"eval_avg_sts": 0.8467372932579469,
|
| 785 |
+
"eval_sickr_spearman": 0.830980274217513,
|
| 786 |
+
"eval_stsb_spearman": 0.8624943122983809,
|
| 787 |
+
"step": 2675
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.99,
|
| 791 |
+
"eval_avg_sts": 0.8467338856246951,
|
| 792 |
+
"eval_sickr_spearman": 0.8309889198157718,
|
| 793 |
+
"eval_stsb_spearman": 0.8624788514336185,
|
| 794 |
+
"step": 2700
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.0,
|
| 798 |
+
"step": 2706,
|
| 799 |
+
"train_runtime": 7555.7932,
|
| 800 |
+
"train_samples_per_second": 0.358
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.17,
|
| 804 |
+
"eval_avg_sts": 0.8577875482283541,
|
| 805 |
+
"eval_sickr_spearman": 0.8398533958038857,
|
| 806 |
+
"eval_stsb_spearman": 0.8757217006528226,
|
| 807 |
+
"step": 2725
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.17,
|
| 811 |
+
"eval_avg_sts": 0.8614007268101659,
|
| 812 |
+
"eval_sickr_spearman": 0.8446720199934614,
|
| 813 |
+
"eval_stsb_spearman": 0.8781294336268703,
|
| 814 |
+
"step": 2750
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.17,
|
| 818 |
+
"eval_avg_sts": 0.8620181447373103,
|
| 819 |
+
"eval_sickr_spearman": 0.8451327343184558,
|
| 820 |
+
"eval_stsb_spearman": 0.8789035551561649,
|
| 821 |
+
"step": 2775
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.17,
|
| 825 |
+
"eval_avg_sts": 0.8617610624844292,
|
| 826 |
+
"eval_sickr_spearman": 0.8442458880615025,
|
| 827 |
+
"eval_stsb_spearman": 0.8792762369073559,
|
| 828 |
+
"step": 2800
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.18,
|
| 832 |
+
"eval_avg_sts": 0.8613249897224624,
|
| 833 |
+
"eval_sickr_spearman": 0.8435179286881065,
|
| 834 |
+
"eval_stsb_spearman": 0.8791320507568182,
|
| 835 |
+
"step": 2825
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.18,
|
| 839 |
+
"eval_avg_sts": 0.8609754605525997,
|
| 840 |
+
"eval_sickr_spearman": 0.8432573119317033,
|
| 841 |
+
"eval_stsb_spearman": 0.878693609173496,
|
| 842 |
+
"step": 2850
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.18,
|
| 846 |
+
"eval_avg_sts": 0.8602516222063733,
|
| 847 |
+
"eval_sickr_spearman": 0.8428514491245513,
|
| 848 |
+
"eval_stsb_spearman": 0.8776517952881953,
|
| 849 |
+
"step": 2875
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.18,
|
| 853 |
+
"eval_avg_sts": 0.8575511355067605,
|
| 854 |
+
"eval_sickr_spearman": 0.8403360603422372,
|
| 855 |
+
"eval_stsb_spearman": 0.8747662106712839,
|
| 856 |
+
"step": 2900
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.18,
|
| 860 |
+
"eval_avg_sts": 0.8575893271102367,
|
| 861 |
+
"eval_sickr_spearman": 0.8404061377192356,
|
| 862 |
+
"eval_stsb_spearman": 0.8747725165012379,
|
| 863 |
+
"step": 2925
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.18,
|
| 867 |
+
"eval_avg_sts": 0.8581586254016319,
|
| 868 |
+
"eval_sickr_spearman": 0.8397912915897261,
|
| 869 |
+
"eval_stsb_spearman": 0.8765259592135377,
|
| 870 |
+
"step": 2950
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.19,
|
| 874 |
+
"eval_avg_sts": 0.8600663448850088,
|
| 875 |
+
"eval_sickr_spearman": 0.8398630980863762,
|
| 876 |
+
"eval_stsb_spearman": 0.8802695916836415,
|
| 877 |
+
"step": 2975
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.19,
|
| 881 |
+
"learning_rate": 2.816974476032372e-06,
|
| 882 |
+
"loss": 5.8677,
|
| 883 |
+
"step": 3000
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.19,
|
| 887 |
+
"eval_avg_sts": 0.8602041511172854,
|
| 888 |
+
"eval_sickr_spearman": 0.8391646298092632,
|
| 889 |
+
"eval_stsb_spearman": 0.8812436724253077,
|
| 890 |
+
"step": 3000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.19,
|
| 894 |
+
"eval_avg_sts": 0.85878989353369,
|
| 895 |
+
"eval_sickr_spearman": 0.837757606723735,
|
| 896 |
+
"eval_stsb_spearman": 0.8798221803436449,
|
| 897 |
+
"step": 3025
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.19,
|
| 901 |
+
"eval_avg_sts": 0.8582917269578925,
|
| 902 |
+
"eval_sickr_spearman": 0.8370325772475268,
|
| 903 |
+
"eval_stsb_spearman": 0.879550876668258,
|
| 904 |
+
"step": 3050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.19,
|
| 908 |
+
"eval_avg_sts": 0.8577173493362535,
|
| 909 |
+
"eval_sickr_spearman": 0.8355930371063252,
|
| 910 |
+
"eval_stsb_spearman": 0.879841661566182,
|
| 911 |
+
"step": 3075
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.19,
|
| 915 |
+
"eval_avg_sts": 0.8561189552564514,
|
| 916 |
+
"eval_sickr_spearman": 0.8356565342224264,
|
| 917 |
+
"eval_stsb_spearman": 0.8765813762904766,
|
| 918 |
+
"step": 3100
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.19,
|
| 922 |
+
"eval_avg_sts": 0.8538777535259878,
|
| 923 |
+
"eval_sickr_spearman": 0.8346490778858695,
|
| 924 |
+
"eval_stsb_spearman": 0.8731064291661061,
|
| 925 |
+
"step": 3125
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.2,
|
| 929 |
+
"eval_avg_sts": 0.8535538681053674,
|
| 930 |
+
"eval_sickr_spearman": 0.8336998912431418,
|
| 931 |
+
"eval_stsb_spearman": 0.8734078449675928,
|
| 932 |
+
"step": 3150
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.2,
|
| 936 |
+
"eval_avg_sts": 0.8527968335877911,
|
| 937 |
+
"eval_sickr_spearman": 0.8316596261162539,
|
| 938 |
+
"eval_stsb_spearman": 0.8739340410593283,
|
| 939 |
+
"step": 3175
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.2,
|
| 943 |
+
"eval_avg_sts": 0.8520648016386033,
|
| 944 |
+
"eval_sickr_spearman": 0.8301450133635043,
|
| 945 |
+
"eval_stsb_spearman": 0.8739845899137023,
|
| 946 |
+
"step": 3200
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.2,
|
| 950 |
+
"eval_avg_sts": 0.8519624267121835,
|
| 951 |
+
"eval_sickr_spearman": 0.8296039910369053,
|
| 952 |
+
"eval_stsb_spearman": 0.8743208623874617,
|
| 953 |
+
"step": 3225
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.2,
|
| 957 |
+
"eval_avg_sts": 0.8519439873790962,
|
| 958 |
+
"eval_sickr_spearman": 0.8297755581312424,
|
| 959 |
+
"eval_stsb_spearman": 0.87411241662695,
|
| 960 |
+
"step": 3250
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.2,
|
| 964 |
+
"eval_avg_sts": 0.852192918854755,
|
| 965 |
+
"eval_sickr_spearman": 0.830445495934101,
|
| 966 |
+
"eval_stsb_spearman": 0.8739403417754091,
|
| 967 |
+
"step": 3275
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.21,
|
| 971 |
+
"eval_avg_sts": 0.8512981097165223,
|
| 972 |
+
"eval_sickr_spearman": 0.8296350191284344,
|
| 973 |
+
"eval_stsb_spearman": 0.8729612003046102,
|
| 974 |
+
"step": 3300
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.21,
|
| 978 |
+
"eval_avg_sts": 0.8510227438917293,
|
| 979 |
+
"eval_sickr_spearman": 0.8306557280650958,
|
| 980 |
+
"eval_stsb_spearman": 0.8713897597183629,
|
| 981 |
+
"step": 3325
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.21,
|
| 985 |
+
"eval_avg_sts": 0.8507748469467518,
|
| 986 |
+
"eval_sickr_spearman": 0.8290585498489742,
|
| 987 |
+
"eval_stsb_spearman": 0.8724911440445293,
|
| 988 |
+
"step": 3350
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.21,
|
| 992 |
+
"eval_avg_sts": 0.8513637656369242,
|
| 993 |
+
"eval_sickr_spearman": 0.829042747616601,
|
| 994 |
+
"eval_stsb_spearman": 0.8736847836572473,
|
| 995 |
+
"step": 3375
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.21,
|
| 999 |
+
"eval_avg_sts": 0.8488924187422411,
|
| 1000 |
+
"eval_sickr_spearman": 0.8285427918817317,
|
| 1001 |
+
"eval_stsb_spearman": 0.8692420456027505,
|
| 1002 |
+
"step": 3400
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.21,
|
| 1006 |
+
"eval_avg_sts": 0.8488562209336381,
|
| 1007 |
+
"eval_sickr_spearman": 0.8280534510202803,
|
| 1008 |
+
"eval_stsb_spearman": 0.869658990846996,
|
| 1009 |
+
"step": 3425
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.21,
|
| 1013 |
+
"eval_avg_sts": 0.8486084528155196,
|
| 1014 |
+
"eval_sickr_spearman": 0.8274891816405853,
|
| 1015 |
+
"eval_stsb_spearman": 0.8697277239904537,
|
| 1016 |
+
"step": 3450
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.22,
|
| 1020 |
+
"eval_avg_sts": 0.8501553683216607,
|
| 1021 |
+
"eval_sickr_spearman": 0.8278544581670221,
|
| 1022 |
+
"eval_stsb_spearman": 0.8724562784762994,
|
| 1023 |
+
"step": 3475
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.22,
|
| 1027 |
+
"learning_rate": 2.5057065781282424e-06,
|
| 1028 |
+
"loss": 57.1716,
|
| 1029 |
+
"step": 3500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.22,
|
| 1033 |
+
"eval_avg_sts": 0.8502042596106525,
|
| 1034 |
+
"eval_sickr_spearman": 0.8269706378694595,
|
| 1035 |
+
"eval_stsb_spearman": 0.8734378813518455,
|
| 1036 |
+
"step": 3500
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.22,
|
| 1040 |
+
"eval_avg_sts": 0.8505942522111252,
|
| 1041 |
+
"eval_sickr_spearman": 0.8264316808802225,
|
| 1042 |
+
"eval_stsb_spearman": 0.874756823542028,
|
| 1043 |
+
"step": 3525
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.22,
|
| 1047 |
+
"eval_avg_sts": 0.8494469451730362,
|
| 1048 |
+
"eval_sickr_spearman": 0.826196156187557,
|
| 1049 |
+
"eval_stsb_spearman": 0.8726977341585155,
|
| 1050 |
+
"step": 3550
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.22,
|
| 1054 |
+
"eval_avg_sts": 0.8486996901831254,
|
| 1055 |
+
"eval_sickr_spearman": 0.824325613144364,
|
| 1056 |
+
"eval_stsb_spearman": 0.8730737672218867,
|
| 1057 |
+
"step": 3575
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.22,
|
| 1061 |
+
"eval_avg_sts": 0.8483785331915861,
|
| 1062 |
+
"eval_sickr_spearman": 0.8239273392512392,
|
| 1063 |
+
"eval_stsb_spearman": 0.872829727131933,
|
| 1064 |
+
"step": 3600
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.23,
|
| 1068 |
+
"eval_avg_sts": 0.8491078657617939,
|
| 1069 |
+
"eval_sickr_spearman": 0.8249937257653681,
|
| 1070 |
+
"eval_stsb_spearman": 0.8732220057582195,
|
| 1071 |
+
"step": 3625
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.23,
|
| 1075 |
+
"eval_avg_sts": 0.8479980515825691,
|
| 1076 |
+
"eval_sickr_spearman": 0.8254658234614033,
|
| 1077 |
+
"eval_stsb_spearman": 0.8705302797037351,
|
| 1078 |
+
"step": 3650
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.23,
|
| 1082 |
+
"eval_avg_sts": 0.8464531979748835,
|
| 1083 |
+
"eval_sickr_spearman": 0.8248943494164926,
|
| 1084 |
+
"eval_stsb_spearman": 0.8680120465332744,
|
| 1085 |
+
"step": 3675
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.23,
|
| 1089 |
+
"eval_avg_sts": 0.8463198965448482,
|
| 1090 |
+
"eval_sickr_spearman": 0.8244845480590227,
|
| 1091 |
+
"eval_stsb_spearman": 0.8681552450306737,
|
| 1092 |
+
"step": 3700
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.23,
|
| 1096 |
+
"eval_avg_sts": 0.8450313625573547,
|
| 1097 |
+
"eval_sickr_spearman": 0.823135114264119,
|
| 1098 |
+
"eval_stsb_spearman": 0.8669276108505903,
|
| 1099 |
+
"step": 3725
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.23,
|
| 1103 |
+
"eval_avg_sts": 0.8451338275602696,
|
| 1104 |
+
"eval_sickr_spearman": 0.8231491873768403,
|
| 1105 |
+
"eval_stsb_spearman": 0.8671184677436989,
|
| 1106 |
+
"step": 3750
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.24,
|
| 1110 |
+
"eval_avg_sts": 0.844512175562927,
|
| 1111 |
+
"eval_sickr_spearman": 0.8225128713449883,
|
| 1112 |
+
"eval_stsb_spearman": 0.8665114797808657,
|
| 1113 |
+
"step": 3775
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.24,
|
| 1117 |
+
"eval_avg_sts": 0.8452690889433365,
|
| 1118 |
+
"eval_sickr_spearman": 0.8219510995825681,
|
| 1119 |
+
"eval_stsb_spearman": 0.8685870783041049,
|
| 1120 |
+
"step": 3800
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.24,
|
| 1124 |
+
"eval_avg_sts": 0.8438205733477075,
|
| 1125 |
+
"eval_sickr_spearman": 0.8199196241472431,
|
| 1126 |
+
"eval_stsb_spearman": 0.867721522548172,
|
| 1127 |
+
"step": 3825
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.24,
|
| 1131 |
+
"eval_avg_sts": 0.8434603141476464,
|
| 1132 |
+
"eval_sickr_spearman": 0.8195560287093566,
|
| 1133 |
+
"eval_stsb_spearman": 0.8673645995859364,
|
| 1134 |
+
"step": 3850
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.24,
|
| 1138 |
+
"eval_avg_sts": 0.8438898362881964,
|
| 1139 |
+
"eval_sickr_spearman": 0.8195005527871955,
|
| 1140 |
+
"eval_stsb_spearman": 0.8682791197891973,
|
| 1141 |
+
"step": 3875
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.24,
|
| 1145 |
+
"eval_avg_sts": 0.8432592745140008,
|
| 1146 |
+
"eval_sickr_spearman": 0.8180013580180077,
|
| 1147 |
+
"eval_stsb_spearman": 0.8685171910099939,
|
| 1148 |
+
"step": 3900
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.24,
|
| 1152 |
+
"eval_avg_sts": 0.843917389147516,
|
| 1153 |
+
"eval_sickr_spearman": 0.8182050098881054,
|
| 1154 |
+
"eval_stsb_spearman": 0.8696297684069265,
|
| 1155 |
+
"step": 3925
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.25,
|
| 1159 |
+
"eval_avg_sts": 0.8440255001788017,
|
| 1160 |
+
"eval_sickr_spearman": 0.818556453457328,
|
| 1161 |
+
"eval_stsb_spearman": 0.8694945469002756,
|
| 1162 |
+
"step": 3950
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.25,
|
| 1166 |
+
"eval_avg_sts": 0.8435903956718499,
|
| 1167 |
+
"eval_sickr_spearman": 0.8173234950834116,
|
| 1168 |
+
"eval_stsb_spearman": 0.8698572962602882,
|
| 1169 |
+
"step": 3975
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.25,
|
| 1173 |
+
"learning_rate": 2.194438680224113e-06,
|
| 1174 |
+
"loss": 56.7286,
|
| 1175 |
+
"step": 4000
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.25,
|
| 1179 |
+
"eval_avg_sts": 0.8434390553176612,
|
| 1180 |
+
"eval_sickr_spearman": 0.8170182574337724,
|
| 1181 |
+
"eval_stsb_spearman": 0.86985985320155,
|
| 1182 |
+
"step": 4000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.25,
|
| 1186 |
+
"eval_avg_sts": 0.8409497580451699,
|
| 1187 |
+
"eval_sickr_spearman": 0.8163146978599068,
|
| 1188 |
+
"eval_stsb_spearman": 0.8655848182304331,
|
| 1189 |
+
"step": 4025
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.25,
|
| 1193 |
+
"eval_avg_sts": 0.8399932811511823,
|
| 1194 |
+
"eval_sickr_spearman": 0.8158981721482357,
|
| 1195 |
+
"eval_stsb_spearman": 0.8640883901541291,
|
| 1196 |
+
"step": 4050
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.25,
|
| 1200 |
+
"eval_avg_sts": 0.8394128025706773,
|
| 1201 |
+
"eval_sickr_spearman": 0.8138923933521801,
|
| 1202 |
+
"eval_stsb_spearman": 0.8649332117891744,
|
| 1203 |
+
"step": 4075
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.26,
|
| 1207 |
+
"eval_avg_sts": 0.8387116441153566,
|
| 1208 |
+
"eval_sickr_spearman": 0.8135261081726131,
|
| 1209 |
+
"eval_stsb_spearman": 0.8638971800581,
|
| 1210 |
+
"step": 4100
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.26,
|
| 1214 |
+
"eval_avg_sts": 0.839193944307536,
|
| 1215 |
+
"eval_sickr_spearman": 0.813573034558718,
|
| 1216 |
+
"eval_stsb_spearman": 0.8648148540563542,
|
| 1217 |
+
"step": 4125
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.26,
|
| 1221 |
+
"eval_avg_sts": 0.8394751113727135,
|
| 1222 |
+
"eval_sickr_spearman": 0.8138994058929901,
|
| 1223 |
+
"eval_stsb_spearman": 0.8650508168524367,
|
| 1224 |
+
"step": 4150
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.26,
|
| 1228 |
+
"eval_avg_sts": 0.8398711630512481,
|
| 1229 |
+
"eval_sickr_spearman": 0.8156752598064614,
|
| 1230 |
+
"eval_stsb_spearman": 0.8640670662960348,
|
| 1231 |
+
"step": 4175
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.26,
|
| 1235 |
+
"eval_avg_sts": 0.8412707356018712,
|
| 1236 |
+
"eval_sickr_spearman": 0.8173963582642932,
|
| 1237 |
+
"eval_stsb_spearman": 0.865145112939449,
|
| 1238 |
+
"step": 4200
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.26,
|
| 1242 |
+
"eval_avg_sts": 0.8405537325709878,
|
| 1243 |
+
"eval_sickr_spearman": 0.817264560921947,
|
| 1244 |
+
"eval_stsb_spearman": 0.8638429042200285,
|
| 1245 |
+
"step": 4225
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.26,
|
| 1249 |
+
"eval_avg_sts": 0.8374471729711384,
|
| 1250 |
+
"eval_sickr_spearman": 0.8147968670233612,
|
| 1251 |
+
"eval_stsb_spearman": 0.8600974789189154,
|
| 1252 |
+
"step": 4250
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.27,
|
| 1256 |
+
"eval_avg_sts": 0.8370952269843919,
|
| 1257 |
+
"eval_sickr_spearman": 0.8145577682004022,
|
| 1258 |
+
"eval_stsb_spearman": 0.8596326857683816,
|
| 1259 |
+
"step": 4275
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.27,
|
| 1263 |
+
"eval_avg_sts": 0.8364730414781547,
|
| 1264 |
+
"eval_sickr_spearman": 0.8138203467000228,
|
| 1265 |
+
"eval_stsb_spearman": 0.8591257362562865,
|
| 1266 |
+
"step": 4300
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.27,
|
| 1270 |
+
"eval_avg_sts": 0.8371611215708128,
|
| 1271 |
+
"eval_sickr_spearman": 0.8138282718317601,
|
| 1272 |
+
"eval_stsb_spearman": 0.8604939713098656,
|
| 1273 |
+
"step": 4325
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.27,
|
| 1277 |
+
"eval_avg_sts": 0.8377565812312395,
|
| 1278 |
+
"eval_sickr_spearman": 0.8139810587654348,
|
| 1279 |
+
"eval_stsb_spearman": 0.8615321036970441,
|
| 1280 |
+
"step": 4350
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.27,
|
| 1284 |
+
"eval_avg_sts": 0.8378457135383265,
|
| 1285 |
+
"eval_sickr_spearman": 0.8139322591663736,
|
| 1286 |
+
"eval_stsb_spearman": 0.8617591679102794,
|
| 1287 |
+
"step": 4375
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.27,
|
| 1291 |
+
"eval_avg_sts": 0.838291484526801,
|
| 1292 |
+
"eval_sickr_spearman": 0.8139556503127741,
|
| 1293 |
+
"eval_stsb_spearman": 0.862627318740828,
|
| 1294 |
+
"step": 4400
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.28,
|
| 1298 |
+
"eval_avg_sts": 0.8385300749312086,
|
| 1299 |
+
"eval_sickr_spearman": 0.8140668423126032,
|
| 1300 |
+
"eval_stsb_spearman": 0.8629933075498138,
|
| 1301 |
+
"step": 4425
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.28,
|
| 1305 |
+
"eval_avg_sts": 0.837914731278594,
|
| 1306 |
+
"eval_sickr_spearman": 0.8139509432648331,
|
| 1307 |
+
"eval_stsb_spearman": 0.8618785192923547,
|
| 1308 |
+
"step": 4450
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.28,
|
| 1312 |
+
"eval_avg_sts": 0.8368392760965009,
|
| 1313 |
+
"eval_sickr_spearman": 0.8131855676634169,
|
| 1314 |
+
"eval_stsb_spearman": 0.8604929845295848,
|
| 1315 |
+
"step": 4475
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.28,
|
| 1319 |
+
"learning_rate": 1.8831707823199833e-06,
|
| 1320 |
+
"loss": 56.6263,
|
| 1321 |
+
"step": 4500
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.28,
|
| 1325 |
+
"eval_avg_sts": 0.8360835846949243,
|
| 1326 |
+
"eval_sickr_spearman": 0.8114090413145253,
|
| 1327 |
+
"eval_stsb_spearman": 0.8607581280753233,
|
| 1328 |
+
"step": 4500
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.28,
|
| 1332 |
+
"eval_avg_sts": 0.8341844414445859,
|
| 1333 |
+
"eval_sickr_spearman": 0.809870653166564,
|
| 1334 |
+
"eval_stsb_spearman": 0.8584982297226078,
|
| 1335 |
+
"step": 4525
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.28,
|
| 1339 |
+
"eval_avg_sts": 0.8320697380456459,
|
| 1340 |
+
"eval_sickr_spearman": 0.8087751117738622,
|
| 1341 |
+
"eval_stsb_spearman": 0.8553643643174295,
|
| 1342 |
+
"step": 4550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.28,
|
| 1346 |
+
"eval_avg_sts": 0.8310886285462743,
|
| 1347 |
+
"eval_sickr_spearman": 0.8082496995552306,
|
| 1348 |
+
"eval_stsb_spearman": 0.853927557537318,
|
| 1349 |
+
"step": 4575
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.29,
|
| 1353 |
+
"eval_avg_sts": 0.831059210698874,
|
| 1354 |
+
"eval_sickr_spearman": 0.8070865784028052,
|
| 1355 |
+
"eval_stsb_spearman": 0.8550318429949428,
|
| 1356 |
+
"step": 4600
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.29,
|
| 1360 |
+
"eval_avg_sts": 0.8302341263420077,
|
| 1361 |
+
"eval_sickr_spearman": 0.8068780273603611,
|
| 1362 |
+
"eval_stsb_spearman": 0.8535902253236541,
|
| 1363 |
+
"step": 4625
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.29,
|
| 1367 |
+
"eval_avg_sts": 0.8310209630719942,
|
| 1368 |
+
"eval_sickr_spearman": 0.8079218872879155,
|
| 1369 |
+
"eval_stsb_spearman": 0.854120038856073,
|
| 1370 |
+
"step": 4650
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.29,
|
| 1374 |
+
"eval_avg_sts": 0.8313364309267233,
|
| 1375 |
+
"eval_sickr_spearman": 0.807848063485005,
|
| 1376 |
+
"eval_stsb_spearman": 0.8548247983684415,
|
| 1377 |
+
"step": 4675
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.29,
|
| 1381 |
+
"eval_avg_sts": 0.8305659237753693,
|
| 1382 |
+
"eval_sickr_spearman": 0.8070360496840924,
|
| 1383 |
+
"eval_stsb_spearman": 0.8540957978666464,
|
| 1384 |
+
"step": 4700
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.29,
|
| 1388 |
+
"eval_avg_sts": 0.8293415322462968,
|
| 1389 |
+
"eval_sickr_spearman": 0.8057621688117507,
|
| 1390 |
+
"eval_stsb_spearman": 0.852920895680843,
|
| 1391 |
+
"step": 4725
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.3,
|
| 1395 |
+
"eval_avg_sts": 0.8291694033467524,
|
| 1396 |
+
"eval_sickr_spearman": 0.8053930978283003,
|
| 1397 |
+
"eval_stsb_spearman": 0.8529457088652045,
|
| 1398 |
+
"step": 4750
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.3,
|
| 1402 |
+
"eval_avg_sts": 0.827560000812239,
|
| 1403 |
+
"eval_sickr_spearman": 0.8046968389818533,
|
| 1404 |
+
"eval_stsb_spearman": 0.8504231626426249,
|
| 1405 |
+
"step": 4775
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.3,
|
| 1409 |
+
"eval_avg_sts": 0.8260965190722769,
|
| 1410 |
+
"eval_sickr_spearman": 0.8038504829434123,
|
| 1411 |
+
"eval_stsb_spearman": 0.8483425552011413,
|
| 1412 |
+
"step": 4800
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.3,
|
| 1416 |
+
"step": 4819,
|
| 1417 |
+
"train_runtime": 2847.5807,
|
| 1418 |
+
"train_samples_per_second": 1.692
|
| 1419 |
+
}
|
| 1420 |
+
],
|
| 1421 |
+
"max_steps": 4819,
|
| 1422 |
+
"num_train_epochs": 1,
|
| 1423 |
+
"total_flos": 297324574620496128,
|
| 1424 |
+
"trial_name": null,
|
| 1425 |
+
"trial_params": null
|
| 1426 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85776082aa4e971d3722508d61330fcdcf616888660c02c8b0ea0daf0d2ced8a
|
| 3 |
+
size 2744
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|