root
commited on
Commit
·
7cb776a
1
Parent(s):
93e41fc
init
Browse files- config.json +26 -0
- eval_results.txt +12 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +1083 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "result/esimcse-roberta-large-0.15-bpe-0.28-128-bs64",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.15,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.15,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"transformers_version": "4.2.1",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 50265
|
| 26 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 1.0
|
| 2 |
+
eval_CR = 88.35
|
| 3 |
+
eval_MPQA = 87.01
|
| 4 |
+
eval_MR = 81.98
|
| 5 |
+
eval_MRPC = 76.82
|
| 6 |
+
eval_SST2 = 86.12
|
| 7 |
+
eval_SUBJ = 93.42
|
| 8 |
+
eval_TREC = 79.44
|
| 9 |
+
eval_avg_sts = 0.8028596486819746
|
| 10 |
+
eval_avg_transfer = 84.73428571428569
|
| 11 |
+
eval_sickr_spearman = 0.7524543705696469
|
| 12 |
+
eval_stsb_spearman = 0.8532649267943023
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92305968933c39b7e7d2f35f6aec76dee8856410015a3cd7873addd96000579a
|
| 3 |
+
size 2843124845
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f0e898f4b03033687f3332ca6b9a51714f694a1ed87d169f9f64e430666d4b
|
| 3 |
+
size 2847428625
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:961c7e56f5d2f7626145d42afd038fe4f5f21bb86b87d87d234371557977c0e8
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "roberta-large"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 1.0
|
| 2 |
+
train_runtime = 11057.6017
|
| 3 |
+
train_samples_per_second = 1.413
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8532649267943023,
|
| 3 |
+
"best_model_checkpoint": "result/esimcse-roberta-large-0.15-bpe-0.28-128-bs64",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 15626,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"eval_avg_sts": 0.7558217259678449,
|
| 13 |
+
"eval_sickr_spearman": 0.7201285747419712,
|
| 14 |
+
"eval_stsb_spearman": 0.7915148771937186,
|
| 15 |
+
"step": 125
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"eval_avg_sts": 0.7742364775992936,
|
| 20 |
+
"eval_sickr_spearman": 0.7452505218826546,
|
| 21 |
+
"eval_stsb_spearman": 0.8032224333159326,
|
| 22 |
+
"step": 250
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.02,
|
| 26 |
+
"eval_avg_sts": 0.7750260297296185,
|
| 27 |
+
"eval_sickr_spearman": 0.7433483942035024,
|
| 28 |
+
"eval_stsb_spearman": 0.8067036652557346,
|
| 29 |
+
"step": 375
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 9.680020478689364e-06,
|
| 34 |
+
"loss": 0.3135,
|
| 35 |
+
"step": 500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.03,
|
| 39 |
+
"eval_avg_sts": 0.7818566453500417,
|
| 40 |
+
"eval_sickr_spearman": 0.7477289446624279,
|
| 41 |
+
"eval_stsb_spearman": 0.8159843460376556,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.04,
|
| 46 |
+
"eval_avg_sts": 0.7811770146364453,
|
| 47 |
+
"eval_sickr_spearman": 0.7481865670513635,
|
| 48 |
+
"eval_stsb_spearman": 0.814167462221527,
|
| 49 |
+
"step": 625
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.05,
|
| 53 |
+
"eval_avg_sts": 0.7770666807380804,
|
| 54 |
+
"eval_sickr_spearman": 0.7352241255196514,
|
| 55 |
+
"eval_stsb_spearman": 0.8189092359565092,
|
| 56 |
+
"step": 750
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_avg_sts": 0.7764823954854172,
|
| 61 |
+
"eval_sickr_spearman": 0.7331835722061546,
|
| 62 |
+
"eval_stsb_spearman": 0.8197812187646797,
|
| 63 |
+
"step": 875
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 9.36004095737873e-06,
|
| 68 |
+
"loss": 0.0031,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"eval_avg_sts": 0.7839001001478747,
|
| 74 |
+
"eval_sickr_spearman": 0.7432803341327646,
|
| 75 |
+
"eval_stsb_spearman": 0.8245198661629847,
|
| 76 |
+
"step": 1000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_avg_sts": 0.7943887972940393,
|
| 81 |
+
"eval_sickr_spearman": 0.7568865845481532,
|
| 82 |
+
"eval_stsb_spearman": 0.8318910100399254,
|
| 83 |
+
"step": 1125
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_avg_sts": 0.7936405273161878,
|
| 88 |
+
"eval_sickr_spearman": 0.7561879241466344,
|
| 89 |
+
"eval_stsb_spearman": 0.8310931304857413,
|
| 90 |
+
"step": 1250
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.09,
|
| 94 |
+
"eval_avg_sts": 0.7943520912745958,
|
| 95 |
+
"eval_sickr_spearman": 0.7518201139033611,
|
| 96 |
+
"eval_stsb_spearman": 0.8368840686458305,
|
| 97 |
+
"step": 1375
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.1,
|
| 101 |
+
"learning_rate": 9.040061436068092e-06,
|
| 102 |
+
"loss": 0.0015,
|
| 103 |
+
"step": 1500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.1,
|
| 107 |
+
"eval_avg_sts": 0.7887681712959922,
|
| 108 |
+
"eval_sickr_spearman": 0.7468924650853165,
|
| 109 |
+
"eval_stsb_spearman": 0.8306438775066679,
|
| 110 |
+
"step": 1500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1,
|
| 114 |
+
"eval_avg_sts": 0.7897590452490246,
|
| 115 |
+
"eval_sickr_spearman": 0.7516917807721141,
|
| 116 |
+
"eval_stsb_spearman": 0.8278263097259353,
|
| 117 |
+
"step": 1625
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_avg_sts": 0.7905759145553224,
|
| 122 |
+
"eval_sickr_spearman": 0.7542222513202796,
|
| 123 |
+
"eval_stsb_spearman": 0.8269295777903652,
|
| 124 |
+
"step": 1750
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.12,
|
| 128 |
+
"eval_avg_sts": 0.7904633436602717,
|
| 129 |
+
"eval_sickr_spearman": 0.7515385135274251,
|
| 130 |
+
"eval_stsb_spearman": 0.8293881737931184,
|
| 131 |
+
"step": 1875
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.13,
|
| 135 |
+
"learning_rate": 8.720081914757458e-06,
|
| 136 |
+
"loss": 0.0014,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.13,
|
| 141 |
+
"eval_avg_sts": 0.802801711004685,
|
| 142 |
+
"eval_sickr_spearman": 0.7642203093334342,
|
| 143 |
+
"eval_stsb_spearman": 0.8413831126759359,
|
| 144 |
+
"step": 2000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"eval_avg_sts": 0.8055867687511298,
|
| 149 |
+
"eval_sickr_spearman": 0.7670204745161748,
|
| 150 |
+
"eval_stsb_spearman": 0.8441530629860846,
|
| 151 |
+
"step": 2125
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.14,
|
| 155 |
+
"eval_avg_sts": 0.7998281543125508,
|
| 156 |
+
"eval_sickr_spearman": 0.7605069768501523,
|
| 157 |
+
"eval_stsb_spearman": 0.8391493317749493,
|
| 158 |
+
"step": 2250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"eval_avg_sts": 0.793160108534175,
|
| 163 |
+
"eval_sickr_spearman": 0.7518937995847628,
|
| 164 |
+
"eval_stsb_spearman": 0.8344264174835871,
|
| 165 |
+
"step": 2375
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 8.400102393446819e-06,
|
| 170 |
+
"loss": 0.001,
|
| 171 |
+
"step": 2500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"eval_avg_sts": 0.7992184752929077,
|
| 176 |
+
"eval_sickr_spearman": 0.7565757272596456,
|
| 177 |
+
"eval_stsb_spearman": 0.8418612233261697,
|
| 178 |
+
"step": 2500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17,
|
| 182 |
+
"eval_avg_sts": 0.7927251468672808,
|
| 183 |
+
"eval_sickr_spearman": 0.7446415355475207,
|
| 184 |
+
"eval_stsb_spearman": 0.8408087581870409,
|
| 185 |
+
"step": 2625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.18,
|
| 189 |
+
"eval_avg_sts": 0.8028596486819746,
|
| 190 |
+
"eval_sickr_spearman": 0.7524543705696469,
|
| 191 |
+
"eval_stsb_spearman": 0.8532649267943023,
|
| 192 |
+
"step": 2750
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.18,
|
| 196 |
+
"eval_avg_sts": 0.7893919999211613,
|
| 197 |
+
"eval_sickr_spearman": 0.7413113471604106,
|
| 198 |
+
"eval_stsb_spearman": 0.837472652681912,
|
| 199 |
+
"step": 2875
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.19,
|
| 203 |
+
"learning_rate": 8.080122872136184e-06,
|
| 204 |
+
"loss": 0.001,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"eval_avg_sts": 0.7934231636232565,
|
| 210 |
+
"eval_sickr_spearman": 0.7474009703562418,
|
| 211 |
+
"eval_stsb_spearman": 0.8394453568902713,
|
| 212 |
+
"step": 3000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2,
|
| 216 |
+
"eval_avg_sts": 0.7940617961811679,
|
| 217 |
+
"eval_sickr_spearman": 0.7509521018099672,
|
| 218 |
+
"eval_stsb_spearman": 0.8371714905523686,
|
| 219 |
+
"step": 3125
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"eval_avg_sts": 0.7937132166778321,
|
| 224 |
+
"eval_sickr_spearman": 0.7539420378744897,
|
| 225 |
+
"eval_stsb_spearman": 0.8334843954811746,
|
| 226 |
+
"step": 3250
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22,
|
| 230 |
+
"eval_avg_sts": 0.7923308718046048,
|
| 231 |
+
"eval_sickr_spearman": 0.7480851733962276,
|
| 232 |
+
"eval_stsb_spearman": 0.836576570212982,
|
| 233 |
+
"step": 3375
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 7.760143350825547e-06,
|
| 238 |
+
"loss": 0.0009,
|
| 239 |
+
"step": 3500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_avg_sts": 0.791635348297863,
|
| 244 |
+
"eval_sickr_spearman": 0.748936284513711,
|
| 245 |
+
"eval_stsb_spearman": 0.834334412082015,
|
| 246 |
+
"step": 3500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.23,
|
| 250 |
+
"eval_avg_sts": 0.7912451615688103,
|
| 251 |
+
"eval_sickr_spearman": 0.7463851304741407,
|
| 252 |
+
"eval_stsb_spearman": 0.83610519266348,
|
| 253 |
+
"step": 3625
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.24,
|
| 257 |
+
"eval_avg_sts": 0.7903505118672073,
|
| 258 |
+
"eval_sickr_spearman": 0.7453605611360493,
|
| 259 |
+
"eval_stsb_spearman": 0.8353404625983653,
|
| 260 |
+
"step": 3750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"eval_avg_sts": 0.7877047830672446,
|
| 265 |
+
"eval_sickr_spearman": 0.747770473619605,
|
| 266 |
+
"eval_stsb_spearman": 0.8276390925148842,
|
| 267 |
+
"step": 3875
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 7.440163829514912e-06,
|
| 272 |
+
"loss": 0.001,
|
| 273 |
+
"step": 4000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_avg_sts": 0.787528888012516,
|
| 278 |
+
"eval_sickr_spearman": 0.7437081951843754,
|
| 279 |
+
"eval_stsb_spearman": 0.8313495808406565,
|
| 280 |
+
"step": 4000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.26,
|
| 284 |
+
"eval_avg_sts": 0.7906651938867704,
|
| 285 |
+
"eval_sickr_spearman": 0.7461365516108834,
|
| 286 |
+
"eval_stsb_spearman": 0.8351938361626572,
|
| 287 |
+
"step": 4125
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.27,
|
| 291 |
+
"eval_avg_sts": 0.7920362260308209,
|
| 292 |
+
"eval_sickr_spearman": 0.7466354986926226,
|
| 293 |
+
"eval_stsb_spearman": 0.8374369533690192,
|
| 294 |
+
"step": 4250
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.28,
|
| 298 |
+
"eval_avg_sts": 0.7911902163460698,
|
| 299 |
+
"eval_sickr_spearman": 0.7485247540365892,
|
| 300 |
+
"eval_stsb_spearman": 0.8338556786555504,
|
| 301 |
+
"step": 4375
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.29,
|
| 305 |
+
"learning_rate": 7.120184308204276e-06,
|
| 306 |
+
"loss": 0.0009,
|
| 307 |
+
"step": 4500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.29,
|
| 311 |
+
"eval_avg_sts": 0.7911417580464639,
|
| 312 |
+
"eval_sickr_spearman": 0.7545039537302142,
|
| 313 |
+
"eval_stsb_spearman": 0.8277795623627137,
|
| 314 |
+
"step": 4500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3,
|
| 318 |
+
"eval_avg_sts": 0.7895925041055443,
|
| 319 |
+
"eval_sickr_spearman": 0.750248782391609,
|
| 320 |
+
"eval_stsb_spearman": 0.8289362258194797,
|
| 321 |
+
"step": 4625
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"eval_avg_sts": 0.7821260859065025,
|
| 326 |
+
"eval_sickr_spearman": 0.7355510732271406,
|
| 327 |
+
"eval_stsb_spearman": 0.8287010985858643,
|
| 328 |
+
"step": 4750
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"eval_avg_sts": 0.7922597968364788,
|
| 333 |
+
"eval_sickr_spearman": 0.7458612853685416,
|
| 334 |
+
"eval_stsb_spearman": 0.838658308304416,
|
| 335 |
+
"step": 4875
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.32,
|
| 339 |
+
"learning_rate": 6.800204786893639e-06,
|
| 340 |
+
"loss": 0.0006,
|
| 341 |
+
"step": 5000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.32,
|
| 345 |
+
"eval_avg_sts": 0.7854669556183871,
|
| 346 |
+
"eval_sickr_spearman": 0.7395174335527985,
|
| 347 |
+
"eval_stsb_spearman": 0.8314164776839756,
|
| 348 |
+
"step": 5000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.33,
|
| 352 |
+
"eval_avg_sts": 0.7826092624953684,
|
| 353 |
+
"eval_sickr_spearman": 0.7410220078053474,
|
| 354 |
+
"eval_stsb_spearman": 0.8241965171853896,
|
| 355 |
+
"step": 5125
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.34,
|
| 359 |
+
"eval_avg_sts": 0.7927314656873996,
|
| 360 |
+
"eval_sickr_spearman": 0.7533276720559947,
|
| 361 |
+
"eval_stsb_spearman": 0.8321352593188046,
|
| 362 |
+
"step": 5250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.34,
|
| 366 |
+
"eval_avg_sts": 0.7895263185412165,
|
| 367 |
+
"eval_sickr_spearman": 0.7509032541798045,
|
| 368 |
+
"eval_stsb_spearman": 0.8281493829026283,
|
| 369 |
+
"step": 5375
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.35,
|
| 373 |
+
"learning_rate": 6.480225265583003e-06,
|
| 374 |
+
"loss": 0.0008,
|
| 375 |
+
"step": 5500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.35,
|
| 379 |
+
"eval_avg_sts": 0.7935029645348786,
|
| 380 |
+
"eval_sickr_spearman": 0.7503155936537093,
|
| 381 |
+
"eval_stsb_spearman": 0.8366903354160478,
|
| 382 |
+
"step": 5500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36,
|
| 386 |
+
"eval_avg_sts": 0.793606484311646,
|
| 387 |
+
"eval_sickr_spearman": 0.7550370989561772,
|
| 388 |
+
"eval_stsb_spearman": 0.8321758696671149,
|
| 389 |
+
"step": 5625
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.37,
|
| 393 |
+
"eval_avg_sts": 0.7888706031258408,
|
| 394 |
+
"eval_sickr_spearman": 0.7515478015672222,
|
| 395 |
+
"eval_stsb_spearman": 0.8261934046844593,
|
| 396 |
+
"step": 5750
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38,
|
| 400 |
+
"eval_avg_sts": 0.7897914038552645,
|
| 401 |
+
"eval_sickr_spearman": 0.7541371882396327,
|
| 402 |
+
"eval_stsb_spearman": 0.8254456194708961,
|
| 403 |
+
"step": 5875
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.38,
|
| 407 |
+
"learning_rate": 6.1602457442723675e-06,
|
| 408 |
+
"loss": 0.0007,
|
| 409 |
+
"step": 6000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.38,
|
| 413 |
+
"eval_avg_sts": 0.7837650110744263,
|
| 414 |
+
"eval_sickr_spearman": 0.7490165925153156,
|
| 415 |
+
"eval_stsb_spearman": 0.818513429633537,
|
| 416 |
+
"step": 6000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.39,
|
| 420 |
+
"eval_avg_sts": 0.7830368725221115,
|
| 421 |
+
"eval_sickr_spearman": 0.752153984061253,
|
| 422 |
+
"eval_stsb_spearman": 0.81391976098297,
|
| 423 |
+
"step": 6125
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4,
|
| 427 |
+
"eval_avg_sts": 0.7928730911226451,
|
| 428 |
+
"eval_sickr_spearman": 0.7560166932700075,
|
| 429 |
+
"eval_stsb_spearman": 0.8297294889752829,
|
| 430 |
+
"step": 6250
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.41,
|
| 434 |
+
"eval_avg_sts": 0.7946611044937584,
|
| 435 |
+
"eval_sickr_spearman": 0.7549690388854393,
|
| 436 |
+
"eval_stsb_spearman": 0.8343531701020775,
|
| 437 |
+
"step": 6375
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.42,
|
| 441 |
+
"learning_rate": 5.840266222961732e-06,
|
| 442 |
+
"loss": 0.0009,
|
| 443 |
+
"step": 6500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.42,
|
| 447 |
+
"eval_avg_sts": 0.7918018347204214,
|
| 448 |
+
"eval_sickr_spearman": 0.7562617479495448,
|
| 449 |
+
"eval_stsb_spearman": 0.827341921491298,
|
| 450 |
+
"step": 6500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.42,
|
| 454 |
+
"eval_avg_sts": 0.7942526450763034,
|
| 455 |
+
"eval_sickr_spearman": 0.7569746255570893,
|
| 456 |
+
"eval_stsb_spearman": 0.8315306645955175,
|
| 457 |
+
"step": 6625
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.43,
|
| 461 |
+
"eval_avg_sts": 0.7940324422099587,
|
| 462 |
+
"eval_sickr_spearman": 0.757333417884832,
|
| 463 |
+
"eval_stsb_spearman": 0.8307314665350856,
|
| 464 |
+
"step": 6750
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.44,
|
| 468 |
+
"eval_avg_sts": 0.7955177075824724,
|
| 469 |
+
"eval_sickr_spearman": 0.7577290980984791,
|
| 470 |
+
"eval_stsb_spearman": 0.8333063170664659,
|
| 471 |
+
"step": 6875
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.45,
|
| 475 |
+
"learning_rate": 5.520286701651095e-06,
|
| 476 |
+
"loss": 0.0006,
|
| 477 |
+
"step": 7000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.45,
|
| 481 |
+
"eval_avg_sts": 0.7955995637779287,
|
| 482 |
+
"eval_sickr_spearman": 0.7530336736840921,
|
| 483 |
+
"eval_stsb_spearman": 0.8381654538717653,
|
| 484 |
+
"step": 7000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.46,
|
| 488 |
+
"eval_avg_sts": 0.7955238196018252,
|
| 489 |
+
"eval_sickr_spearman": 0.7530732993427786,
|
| 490 |
+
"eval_stsb_spearman": 0.8379743398608718,
|
| 491 |
+
"step": 7125
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"eval_avg_sts": 0.7921706195432732,
|
| 496 |
+
"eval_sickr_spearman": 0.7532472199610859,
|
| 497 |
+
"eval_stsb_spearman": 0.8310940191254605,
|
| 498 |
+
"step": 7250
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"eval_avg_sts": 0.7929086096204032,
|
| 503 |
+
"eval_sickr_spearman": 0.7574800088064211,
|
| 504 |
+
"eval_stsb_spearman": 0.8283372104343854,
|
| 505 |
+
"step": 7375
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.48,
|
| 509 |
+
"learning_rate": 5.200307180340458e-06,
|
| 510 |
+
"loss": 0.0008,
|
| 511 |
+
"step": 7500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.48,
|
| 515 |
+
"eval_avg_sts": 0.785403249216813,
|
| 516 |
+
"eval_sickr_spearman": 0.7543678816198399,
|
| 517 |
+
"eval_stsb_spearman": 0.8164386168137862,
|
| 518 |
+
"step": 7500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.49,
|
| 522 |
+
"eval_avg_sts": 0.7880462597418649,
|
| 523 |
+
"eval_sickr_spearman": 0.7476711933329325,
|
| 524 |
+
"eval_stsb_spearman": 0.8284213261507974,
|
| 525 |
+
"step": 7625
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.5,
|
| 529 |
+
"eval_avg_sts": 0.7942161541157922,
|
| 530 |
+
"eval_sickr_spearman": 0.754079454855704,
|
| 531 |
+
"eval_stsb_spearman": 0.8343528533758804,
|
| 532 |
+
"step": 7750
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.5,
|
| 536 |
+
"eval_avg_sts": 0.7968011299207969,
|
| 537 |
+
"eval_sickr_spearman": 0.7561006996664228,
|
| 538 |
+
"eval_stsb_spearman": 0.837501560175171,
|
| 539 |
+
"step": 7875
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.51,
|
| 543 |
+
"learning_rate": 4.8803276590298225e-06,
|
| 544 |
+
"loss": 0.0005,
|
| 545 |
+
"step": 8000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.51,
|
| 549 |
+
"eval_avg_sts": 0.7962915878196872,
|
| 550 |
+
"eval_sickr_spearman": 0.7541978995518505,
|
| 551 |
+
"eval_stsb_spearman": 0.838385276087524,
|
| 552 |
+
"step": 8000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.52,
|
| 556 |
+
"eval_avg_sts": 0.7903274885336161,
|
| 557 |
+
"eval_sickr_spearman": 0.7504886497121908,
|
| 558 |
+
"eval_stsb_spearman": 0.8301663273550415,
|
| 559 |
+
"step": 8125
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.53,
|
| 563 |
+
"eval_avg_sts": 0.7900160038644817,
|
| 564 |
+
"eval_sickr_spearman": 0.7502795222965293,
|
| 565 |
+
"eval_stsb_spearman": 0.829752485432434,
|
| 566 |
+
"step": 8250
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.54,
|
| 570 |
+
"eval_avg_sts": 0.7954484420566725,
|
| 571 |
+
"eval_sickr_spearman": 0.7508721300260727,
|
| 572 |
+
"eval_stsb_spearman": 0.8400247540872725,
|
| 573 |
+
"step": 8375
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.54,
|
| 577 |
+
"learning_rate": 4.560348137719187e-06,
|
| 578 |
+
"loss": 0.0005,
|
| 579 |
+
"step": 8500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.54,
|
| 583 |
+
"eval_avg_sts": 0.7934980610345465,
|
| 584 |
+
"eval_sickr_spearman": 0.7509290949123782,
|
| 585 |
+
"eval_stsb_spearman": 0.8360670271567147,
|
| 586 |
+
"step": 8500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.55,
|
| 590 |
+
"eval_avg_sts": 0.7886755296146708,
|
| 591 |
+
"eval_sickr_spearman": 0.747253658968131,
|
| 592 |
+
"eval_stsb_spearman": 0.8300974002612107,
|
| 593 |
+
"step": 8625
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.56,
|
| 597 |
+
"eval_avg_sts": 0.7889761398352569,
|
| 598 |
+
"eval_sickr_spearman": 0.7419386813762938,
|
| 599 |
+
"eval_stsb_spearman": 0.8360135982942201,
|
| 600 |
+
"step": 8750
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.57,
|
| 604 |
+
"eval_avg_sts": 0.7898054394244394,
|
| 605 |
+
"eval_sickr_spearman": 0.7431272109813798,
|
| 606 |
+
"eval_stsb_spearman": 0.836483667867499,
|
| 607 |
+
"step": 8875
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.58,
|
| 611 |
+
"learning_rate": 4.24036861640855e-06,
|
| 612 |
+
"loss": 0.0005,
|
| 613 |
+
"step": 9000
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.58,
|
| 617 |
+
"eval_avg_sts": 0.7904517544876187,
|
| 618 |
+
"eval_sickr_spearman": 0.7436593475542127,
|
| 619 |
+
"eval_stsb_spearman": 0.8372441614210248,
|
| 620 |
+
"step": 9000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.58,
|
| 624 |
+
"eval_avg_sts": 0.7851659097948578,
|
| 625 |
+
"eval_sickr_spearman": 0.7379476810955982,
|
| 626 |
+
"eval_stsb_spearman": 0.8323841384941174,
|
| 627 |
+
"step": 9125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.59,
|
| 631 |
+
"eval_avg_sts": 0.7848891215669203,
|
| 632 |
+
"eval_sickr_spearman": 0.7407074521220292,
|
| 633 |
+
"eval_stsb_spearman": 0.8290707910118115,
|
| 634 |
+
"step": 9250
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6,
|
| 638 |
+
"eval_avg_sts": 0.7871117814010626,
|
| 639 |
+
"eval_sickr_spearman": 0.752143561312241,
|
| 640 |
+
"eval_stsb_spearman": 0.8220800014898841,
|
| 641 |
+
"step": 9375
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.61,
|
| 645 |
+
"learning_rate": 3.920389095097914e-06,
|
| 646 |
+
"loss": 0.0008,
|
| 647 |
+
"step": 9500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.61,
|
| 651 |
+
"eval_avg_sts": 0.7930397869535002,
|
| 652 |
+
"eval_sickr_spearman": 0.7565603092760841,
|
| 653 |
+
"eval_stsb_spearman": 0.8295192646309164,
|
| 654 |
+
"step": 9500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.62,
|
| 658 |
+
"eval_avg_sts": 0.7979788678504024,
|
| 659 |
+
"eval_sickr_spearman": 0.7627290877270851,
|
| 660 |
+
"eval_stsb_spearman": 0.8332286479737196,
|
| 661 |
+
"step": 9625
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.62,
|
| 665 |
+
"eval_avg_sts": 0.7967114262262445,
|
| 666 |
+
"eval_sickr_spearman": 0.7644874102885316,
|
| 667 |
+
"eval_stsb_spearman": 0.8289354421639574,
|
| 668 |
+
"step": 9750
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.63,
|
| 672 |
+
"eval_avg_sts": 0.801864222640388,
|
| 673 |
+
"eval_sickr_spearman": 0.7659917924166748,
|
| 674 |
+
"eval_stsb_spearman": 0.8377366528641014,
|
| 675 |
+
"step": 9875
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.64,
|
| 679 |
+
"learning_rate": 3.600409573787278e-06,
|
| 680 |
+
"loss": 0.0005,
|
| 681 |
+
"step": 10000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.64,
|
| 685 |
+
"eval_avg_sts": 0.7984090692179152,
|
| 686 |
+
"eval_sickr_spearman": 0.7636251079244132,
|
| 687 |
+
"eval_stsb_spearman": 0.8331930305114172,
|
| 688 |
+
"step": 10000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.65,
|
| 692 |
+
"eval_avg_sts": 0.7950614235855115,
|
| 693 |
+
"eval_sickr_spearman": 0.761550308435591,
|
| 694 |
+
"eval_stsb_spearman": 0.8285725387354319,
|
| 695 |
+
"step": 10125
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.66,
|
| 699 |
+
"eval_avg_sts": 0.7995666707496905,
|
| 700 |
+
"eval_sickr_spearman": 0.7639466281174399,
|
| 701 |
+
"eval_stsb_spearman": 0.8351867133819411,
|
| 702 |
+
"step": 10250
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.66,
|
| 706 |
+
"eval_avg_sts": 0.794625632859824,
|
| 707 |
+
"eval_sickr_spearman": 0.761795891457244,
|
| 708 |
+
"eval_stsb_spearman": 0.8274553742624039,
|
| 709 |
+
"step": 10375
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.67,
|
| 713 |
+
"learning_rate": 3.280430052476642e-06,
|
| 714 |
+
"loss": 0.0005,
|
| 715 |
+
"step": 10500
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.67,
|
| 719 |
+
"eval_avg_sts": 0.7935143889832998,
|
| 720 |
+
"eval_sickr_spearman": 0.7613707384202849,
|
| 721 |
+
"eval_stsb_spearman": 0.8256580395463149,
|
| 722 |
+
"step": 10500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.68,
|
| 726 |
+
"eval_avg_sts": 0.7943479719067924,
|
| 727 |
+
"eval_sickr_spearman": 0.7625838416763363,
|
| 728 |
+
"eval_stsb_spearman": 0.8261121021372485,
|
| 729 |
+
"step": 10625
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.69,
|
| 733 |
+
"eval_avg_sts": 0.7887052397337098,
|
| 734 |
+
"eval_sickr_spearman": 0.7615231708632785,
|
| 735 |
+
"eval_stsb_spearman": 0.815887308604141,
|
| 736 |
+
"step": 10750
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.7,
|
| 740 |
+
"eval_avg_sts": 0.794244759928596,
|
| 741 |
+
"eval_sickr_spearman": 0.7613072230312128,
|
| 742 |
+
"eval_stsb_spearman": 0.8271822968259792,
|
| 743 |
+
"step": 10875
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.7,
|
| 747 |
+
"learning_rate": 2.960450531166006e-06,
|
| 748 |
+
"loss": 0.0006,
|
| 749 |
+
"step": 11000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.7,
|
| 753 |
+
"eval_avg_sts": 0.7874100790996466,
|
| 754 |
+
"eval_sickr_spearman": 0.7576639198938275,
|
| 755 |
+
"eval_stsb_spearman": 0.8171562383054657,
|
| 756 |
+
"step": 11000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.71,
|
| 760 |
+
"eval_avg_sts": 0.789179157033471,
|
| 761 |
+
"eval_sickr_spearman": 0.7584775187210878,
|
| 762 |
+
"eval_stsb_spearman": 0.819880795345854,
|
| 763 |
+
"step": 11125
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.72,
|
| 767 |
+
"eval_avg_sts": 0.7873417867649358,
|
| 768 |
+
"eval_sickr_spearman": 0.7538412686236725,
|
| 769 |
+
"eval_stsb_spearman": 0.8208423049061991,
|
| 770 |
+
"step": 11250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.73,
|
| 774 |
+
"eval_avg_sts": 0.7870785735870268,
|
| 775 |
+
"eval_sickr_spearman": 0.7543877664958354,
|
| 776 |
+
"eval_stsb_spearman": 0.8197693806782183,
|
| 777 |
+
"step": 11375
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.74,
|
| 781 |
+
"learning_rate": 2.640471009855369e-06,
|
| 782 |
+
"loss": 0.0006,
|
| 783 |
+
"step": 11500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.74,
|
| 787 |
+
"eval_avg_sts": 0.7886389449841755,
|
| 788 |
+
"eval_sickr_spearman": 0.7516758344464366,
|
| 789 |
+
"eval_stsb_spearman": 0.8256020555219146,
|
| 790 |
+
"step": 11500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.74,
|
| 794 |
+
"eval_avg_sts": 0.7816407061330272,
|
| 795 |
+
"eval_sickr_spearman": 0.7511766952402917,
|
| 796 |
+
"eval_stsb_spearman": 0.8121047170257626,
|
| 797 |
+
"step": 11625
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.75,
|
| 801 |
+
"eval_avg_sts": 0.7880937817548945,
|
| 802 |
+
"eval_sickr_spearman": 0.7527955835142635,
|
| 803 |
+
"eval_stsb_spearman": 0.8233919799955256,
|
| 804 |
+
"step": 11750
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.76,
|
| 808 |
+
"eval_avg_sts": 0.7923766055265167,
|
| 809 |
+
"eval_sickr_spearman": 0.7552486279269106,
|
| 810 |
+
"eval_stsb_spearman": 0.8295045831261226,
|
| 811 |
+
"step": 11875
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.77,
|
| 815 |
+
"learning_rate": 2.3204914885447333e-06,
|
| 816 |
+
"loss": 0.0006,
|
| 817 |
+
"step": 12000
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.77,
|
| 821 |
+
"eval_avg_sts": 0.7926331664582384,
|
| 822 |
+
"eval_sickr_spearman": 0.7545561155063759,
|
| 823 |
+
"eval_stsb_spearman": 0.8307102174101011,
|
| 824 |
+
"step": 12000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.78,
|
| 828 |
+
"eval_avg_sts": 0.7931451615056908,
|
| 829 |
+
"eval_sickr_spearman": 0.7558778833868514,
|
| 830 |
+
"eval_stsb_spearman": 0.8304124396245304,
|
| 831 |
+
"step": 12125
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.78,
|
| 835 |
+
"eval_avg_sts": 0.7883567651086225,
|
| 836 |
+
"eval_sickr_spearman": 0.7542461708087957,
|
| 837 |
+
"eval_stsb_spearman": 0.8224673594084494,
|
| 838 |
+
"step": 12250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.79,
|
| 842 |
+
"eval_avg_sts": 0.7862547538448916,
|
| 843 |
+
"eval_sickr_spearman": 0.7544667296265997,
|
| 844 |
+
"eval_stsb_spearman": 0.8180427780631837,
|
| 845 |
+
"step": 12375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.8,
|
| 849 |
+
"learning_rate": 2.000511967234097e-06,
|
| 850 |
+
"loss": 0.0008,
|
| 851 |
+
"step": 12500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8,
|
| 855 |
+
"eval_avg_sts": 0.7841379910987387,
|
| 856 |
+
"eval_sickr_spearman": 0.7531644143422066,
|
| 857 |
+
"eval_stsb_spearman": 0.815111567855271,
|
| 858 |
+
"step": 12500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.81,
|
| 862 |
+
"eval_avg_sts": 0.7835845835747262,
|
| 863 |
+
"eval_sickr_spearman": 0.7517147876697029,
|
| 864 |
+
"eval_stsb_spearman": 0.8154543794797493,
|
| 865 |
+
"step": 12625
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.82,
|
| 869 |
+
"eval_avg_sts": 0.785837092232381,
|
| 870 |
+
"eval_sickr_spearman": 0.7525228148891964,
|
| 871 |
+
"eval_stsb_spearman": 0.8191513695755656,
|
| 872 |
+
"step": 12750
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.82,
|
| 876 |
+
"eval_avg_sts": 0.7832659241868551,
|
| 877 |
+
"eval_sickr_spearman": 0.750127647953782,
|
| 878 |
+
"eval_stsb_spearman": 0.8164042004199282,
|
| 879 |
+
"step": 12875
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.83,
|
| 883 |
+
"learning_rate": 1.6805324459234608e-06,
|
| 884 |
+
"loss": 0.0006,
|
| 885 |
+
"step": 13000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.83,
|
| 889 |
+
"eval_avg_sts": 0.7814624983749696,
|
| 890 |
+
"eval_sickr_spearman": 0.7456563366587051,
|
| 891 |
+
"eval_stsb_spearman": 0.8172686600912342,
|
| 892 |
+
"step": 13000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.84,
|
| 896 |
+
"eval_avg_sts": 0.7813485495429527,
|
| 897 |
+
"eval_sickr_spearman": 0.7430078536943062,
|
| 898 |
+
"eval_stsb_spearman": 0.8196892453915993,
|
| 899 |
+
"step": 13125
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.85,
|
| 903 |
+
"eval_avg_sts": 0.7848142530915927,
|
| 904 |
+
"eval_sickr_spearman": 0.7457980764390489,
|
| 905 |
+
"eval_stsb_spearman": 0.8238304297441366,
|
| 906 |
+
"step": 13250
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.86,
|
| 910 |
+
"eval_avg_sts": 0.7872867184061136,
|
| 911 |
+
"eval_sickr_spearman": 0.7477951135746429,
|
| 912 |
+
"eval_stsb_spearman": 0.8267783232375843,
|
| 913 |
+
"step": 13375
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.86,
|
| 917 |
+
"learning_rate": 1.3605529246128248e-06,
|
| 918 |
+
"loss": 0.0008,
|
| 919 |
+
"step": 13500
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.86,
|
| 923 |
+
"eval_avg_sts": 0.7841077000969573,
|
| 924 |
+
"eval_sickr_spearman": 0.7476563997536896,
|
| 925 |
+
"eval_stsb_spearman": 0.820559000440225,
|
| 926 |
+
"step": 13500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.87,
|
| 930 |
+
"eval_avg_sts": 0.7858331122771427,
|
| 931 |
+
"eval_sickr_spearman": 0.7483037808982353,
|
| 932 |
+
"eval_stsb_spearman": 0.8233624436560499,
|
| 933 |
+
"step": 13625
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.88,
|
| 937 |
+
"eval_avg_sts": 0.7841019114435142,
|
| 938 |
+
"eval_sickr_spearman": 0.7481370469857809,
|
| 939 |
+
"eval_stsb_spearman": 0.8200667759012474,
|
| 940 |
+
"step": 13750
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.89,
|
| 944 |
+
"eval_avg_sts": 0.7799615698577176,
|
| 945 |
+
"eval_sickr_spearman": 0.745557104403134,
|
| 946 |
+
"eval_stsb_spearman": 0.8143660353123011,
|
| 947 |
+
"step": 13875
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9,
|
| 951 |
+
"learning_rate": 1.0405734033021888e-06,
|
| 952 |
+
"loss": 0.0006,
|
| 953 |
+
"step": 14000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.9,
|
| 957 |
+
"eval_avg_sts": 0.7825679820043924,
|
| 958 |
+
"eval_sickr_spearman": 0.7460993934448276,
|
| 959 |
+
"eval_stsb_spearman": 0.8190365705639572,
|
| 960 |
+
"step": 14000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.9,
|
| 964 |
+
"eval_avg_sts": 0.7831020374187931,
|
| 965 |
+
"eval_sickr_spearman": 0.7452405314135555,
|
| 966 |
+
"eval_stsb_spearman": 0.8209635434240309,
|
| 967 |
+
"step": 14125
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.91,
|
| 971 |
+
"eval_avg_sts": 0.7813864099961566,
|
| 972 |
+
"eval_sickr_spearman": 0.7446007571423997,
|
| 973 |
+
"eval_stsb_spearman": 0.8181720628499135,
|
| 974 |
+
"step": 14250
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.92,
|
| 978 |
+
"eval_avg_sts": 0.7834609263550933,
|
| 979 |
+
"eval_sickr_spearman": 0.7452780917348799,
|
| 980 |
+
"eval_stsb_spearman": 0.8216437609753068,
|
| 981 |
+
"step": 14375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.93,
|
| 985 |
+
"learning_rate": 7.205938819915525e-07,
|
| 986 |
+
"loss": 0.0004,
|
| 987 |
+
"step": 14500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.93,
|
| 991 |
+
"eval_avg_sts": 0.7842031580372257,
|
| 992 |
+
"eval_sickr_spearman": 0.7454702641717339,
|
| 993 |
+
"eval_stsb_spearman": 0.8229360519027176,
|
| 994 |
+
"step": 14500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.94,
|
| 998 |
+
"eval_avg_sts": 0.7831083936431449,
|
| 999 |
+
"eval_sickr_spearman": 0.744312234316061,
|
| 1000 |
+
"eval_stsb_spearman": 0.8219045529702287,
|
| 1001 |
+
"step": 14625
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.94,
|
| 1005 |
+
"eval_avg_sts": 0.7840839730054485,
|
| 1006 |
+
"eval_sickr_spearman": 0.7447129097642577,
|
| 1007 |
+
"eval_stsb_spearman": 0.8234550362466394,
|
| 1008 |
+
"step": 14750
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.95,
|
| 1012 |
+
"eval_avg_sts": 0.7836831213121471,
|
| 1013 |
+
"eval_sickr_spearman": 0.7446981642161162,
|
| 1014 |
+
"eval_stsb_spearman": 0.8226680784081779,
|
| 1015 |
+
"step": 14875
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.96,
|
| 1019 |
+
"learning_rate": 4.0061436068091647e-07,
|
| 1020 |
+
"loss": 0.0008,
|
| 1021 |
+
"step": 15000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.96,
|
| 1025 |
+
"eval_avg_sts": 0.7842518604266702,
|
| 1026 |
+
"eval_sickr_spearman": 0.7449969176670613,
|
| 1027 |
+
"eval_stsb_spearman": 0.823506803186279,
|
| 1028 |
+
"step": 15000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.97,
|
| 1032 |
+
"eval_avg_sts": 0.7840099446787474,
|
| 1033 |
+
"eval_sickr_spearman": 0.744850855087588,
|
| 1034 |
+
"eval_stsb_spearman": 0.823169034269907,
|
| 1035 |
+
"step": 15125
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.98,
|
| 1039 |
+
"eval_avg_sts": 0.7847295434857142,
|
| 1040 |
+
"eval_sickr_spearman": 0.745309888324032,
|
| 1041 |
+
"eval_stsb_spearman": 0.8241491986473966,
|
| 1042 |
+
"step": 15250
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.98,
|
| 1046 |
+
"eval_avg_sts": 0.7847406171241809,
|
| 1047 |
+
"eval_sickr_spearman": 0.7451867846110461,
|
| 1048 |
+
"eval_stsb_spearman": 0.8242944496373156,
|
| 1049 |
+
"step": 15375
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.99,
|
| 1053 |
+
"learning_rate": 8.06348393702803e-08,
|
| 1054 |
+
"loss": 0.0005,
|
| 1055 |
+
"step": 15500
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.99,
|
| 1059 |
+
"eval_avg_sts": 0.7846749915698714,
|
| 1060 |
+
"eval_sickr_spearman": 0.7452754500243008,
|
| 1061 |
+
"eval_stsb_spearman": 0.824074533115442,
|
| 1062 |
+
"step": 15500
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.0,
|
| 1066 |
+
"eval_avg_sts": 0.7844513467514725,
|
| 1067 |
+
"eval_sickr_spearman": 0.7450856249779936,
|
| 1068 |
+
"eval_stsb_spearman": 0.8238170685249515,
|
| 1069 |
+
"step": 15625
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.0,
|
| 1073 |
+
"step": 15626,
|
| 1074 |
+
"train_runtime": 11057.6017,
|
| 1075 |
+
"train_samples_per_second": 1.413
|
| 1076 |
+
}
|
| 1077 |
+
],
|
| 1078 |
+
"max_steps": 15626,
|
| 1079 |
+
"num_train_epochs": 1,
|
| 1080 |
+
"total_flos": 332584911022755840,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:231f592aa03f827b78510fdb3cdbe456071da539ed468e0104ec3880f3f8d38a
|
| 3 |
+
size 2095
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|