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 +919 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/bert-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 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 = 3.0
|
| 2 |
+
eval_CR = 90.51
|
| 3 |
+
eval_MPQA = 89.4
|
| 4 |
+
eval_MR = 83.79
|
| 5 |
+
eval_MRPC = 75.74
|
| 6 |
+
eval_SST2 = 89.11
|
| 7 |
+
eval_SUBJ = 94.58
|
| 8 |
+
eval_TREC = 77.48
|
| 9 |
+
eval_avg_sts = 0.8528364235468135
|
| 10 |
+
eval_avg_transfer = 85.80142857142857
|
| 11 |
+
eval_sickr_spearman = 0.8424179684340722
|
| 12 |
+
eval_stsb_spearman = 0.8632548786595547
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78710b3a7c80e4b953c58861611794e645bef5ceca2dcf40ad9a37e3c9626d71
|
| 3 |
+
size 1470047490
|
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/data/bert-large-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_runtime = 8699.7484
|
| 3 |
+
train_samples_per_second = 0.354
|
trainer_state.json
ADDED
|
@@ -0,0 +1,919 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8528364235468135,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/bert-large-uncased",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 3081,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"eval_avg_sts": 0.7741718103390286,
|
| 13 |
+
"eval_sickr_spearman": 0.745954513736433,
|
| 14 |
+
"eval_stsb_spearman": 0.8023891069416242,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"eval_avg_sts": 0.8081911987521978,
|
| 20 |
+
"eval_sickr_spearman": 0.779239730815335,
|
| 21 |
+
"eval_stsb_spearman": 0.8371426666890606,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.07,
|
| 26 |
+
"eval_avg_sts": 0.8136161115454807,
|
| 27 |
+
"eval_sickr_spearman": 0.7835086390489516,
|
| 28 |
+
"eval_stsb_spearman": 0.8437235840420098,
|
| 29 |
+
"step": 75
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1,
|
| 33 |
+
"eval_avg_sts": 0.8155047769520929,
|
| 34 |
+
"eval_sickr_spearman": 0.7852900645701897,
|
| 35 |
+
"eval_stsb_spearman": 0.845719489333996,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.12,
|
| 40 |
+
"eval_avg_sts": 0.8238067491381542,
|
| 41 |
+
"eval_sickr_spearman": 0.7985816632400571,
|
| 42 |
+
"eval_stsb_spearman": 0.8490318350362512,
|
| 43 |
+
"step": 125
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.15,
|
| 47 |
+
"eval_avg_sts": 0.8224993495563874,
|
| 48 |
+
"eval_sickr_spearman": 0.7982152819982874,
|
| 49 |
+
"eval_stsb_spearman": 0.8467834171144873,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.17,
|
| 54 |
+
"eval_avg_sts": 0.8263297389680633,
|
| 55 |
+
"eval_sickr_spearman": 0.8034025929225019,
|
| 56 |
+
"eval_stsb_spearman": 0.8492568850136247,
|
| 57 |
+
"step": 175
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.19,
|
| 61 |
+
"eval_avg_sts": 0.82711974150715,
|
| 62 |
+
"eval_sickr_spearman": 0.8028132513078563,
|
| 63 |
+
"eval_stsb_spearman": 0.8514262317064436,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.22,
|
| 68 |
+
"eval_avg_sts": 0.8285051091857007,
|
| 69 |
+
"eval_sickr_spearman": 0.8064033359848481,
|
| 70 |
+
"eval_stsb_spearman": 0.8506068823865535,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.24,
|
| 75 |
+
"eval_avg_sts": 0.8308924909456856,
|
| 76 |
+
"eval_sickr_spearman": 0.8108744071244177,
|
| 77 |
+
"eval_stsb_spearman": 0.8509105747669534,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.27,
|
| 82 |
+
"eval_avg_sts": 0.8292742145946509,
|
| 83 |
+
"eval_sickr_spearman": 0.8081889402119113,
|
| 84 |
+
"eval_stsb_spearman": 0.8503594889773904,
|
| 85 |
+
"step": 275
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.29,
|
| 89 |
+
"eval_avg_sts": 0.8302783515064169,
|
| 90 |
+
"eval_sickr_spearman": 0.8108542340618137,
|
| 91 |
+
"eval_stsb_spearman": 0.8497024689510201,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.32,
|
| 96 |
+
"eval_avg_sts": 0.8354548973044524,
|
| 97 |
+
"eval_sickr_spearman": 0.8162711816820041,
|
| 98 |
+
"eval_stsb_spearman": 0.8546386129269009,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.34,
|
| 103 |
+
"eval_avg_sts": 0.8376245074641093,
|
| 104 |
+
"eval_sickr_spearman": 0.820640234762119,
|
| 105 |
+
"eval_stsb_spearman": 0.8546087801660995,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.37,
|
| 110 |
+
"eval_avg_sts": 0.842346577377938,
|
| 111 |
+
"eval_sickr_spearman": 0.8251871470108594,
|
| 112 |
+
"eval_stsb_spearman": 0.8595060077450167,
|
| 113 |
+
"step": 375
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.39,
|
| 117 |
+
"eval_avg_sts": 0.8392487017993179,
|
| 118 |
+
"eval_sickr_spearman": 0.8222254052028811,
|
| 119 |
+
"eval_stsb_spearman": 0.8562719983957546,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.41,
|
| 124 |
+
"eval_avg_sts": 0.836585408133989,
|
| 125 |
+
"eval_sickr_spearman": 0.8178774858073988,
|
| 126 |
+
"eval_stsb_spearman": 0.855293330460579,
|
| 127 |
+
"step": 425
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.44,
|
| 131 |
+
"eval_avg_sts": 0.8377417996341128,
|
| 132 |
+
"eval_sickr_spearman": 0.8186622659737961,
|
| 133 |
+
"eval_stsb_spearman": 0.8568213332944294,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.46,
|
| 138 |
+
"eval_avg_sts": 0.8409718734645293,
|
| 139 |
+
"eval_sickr_spearman": 0.8244389665437579,
|
| 140 |
+
"eval_stsb_spearman": 0.8575047803853006,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.49,
|
| 145 |
+
"learning_rate": 8.377150275884453e-06,
|
| 146 |
+
"loss": 0.5144,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.49,
|
| 151 |
+
"eval_avg_sts": 0.8409672497360382,
|
| 152 |
+
"eval_sickr_spearman": 0.8242925677465746,
|
| 153 |
+
"eval_stsb_spearman": 0.8576419317255018,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.51,
|
| 158 |
+
"eval_avg_sts": 0.8413119218825833,
|
| 159 |
+
"eval_sickr_spearman": 0.8241660538253865,
|
| 160 |
+
"eval_stsb_spearman": 0.85845778993978,
|
| 161 |
+
"step": 525
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.54,
|
| 165 |
+
"eval_avg_sts": 0.8405090163812534,
|
| 166 |
+
"eval_sickr_spearman": 0.8231903980618742,
|
| 167 |
+
"eval_stsb_spearman": 0.8578276347006326,
|
| 168 |
+
"step": 550
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.56,
|
| 172 |
+
"eval_avg_sts": 0.8461025764167975,
|
| 173 |
+
"eval_sickr_spearman": 0.8310040496127249,
|
| 174 |
+
"eval_stsb_spearman": 0.8612011032208701,
|
| 175 |
+
"step": 575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.58,
|
| 179 |
+
"eval_avg_sts": 0.8447104900811846,
|
| 180 |
+
"eval_sickr_spearman": 0.8284478343941886,
|
| 181 |
+
"eval_stsb_spearman": 0.8609731457681805,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.61,
|
| 186 |
+
"eval_avg_sts": 0.8462395445603483,
|
| 187 |
+
"eval_sickr_spearman": 0.8308051047905681,
|
| 188 |
+
"eval_stsb_spearman": 0.8616739843301284,
|
| 189 |
+
"step": 625
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.63,
|
| 193 |
+
"eval_avg_sts": 0.8436677522914944,
|
| 194 |
+
"eval_sickr_spearman": 0.8276286639591616,
|
| 195 |
+
"eval_stsb_spearman": 0.8597068406238272,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.66,
|
| 200 |
+
"eval_avg_sts": 0.8447115186169327,
|
| 201 |
+
"eval_sickr_spearman": 0.8297105720509965,
|
| 202 |
+
"eval_stsb_spearman": 0.8597124651828688,
|
| 203 |
+
"step": 675
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.68,
|
| 207 |
+
"eval_avg_sts": 0.8434972279862564,
|
| 208 |
+
"eval_sickr_spearman": 0.8294735385653995,
|
| 209 |
+
"eval_stsb_spearman": 0.8575209174071132,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.71,
|
| 214 |
+
"eval_avg_sts": 0.8440935405127372,
|
| 215 |
+
"eval_sickr_spearman": 0.8307528469522036,
|
| 216 |
+
"eval_stsb_spearman": 0.8574342340732707,
|
| 217 |
+
"step": 725
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.73,
|
| 221 |
+
"eval_avg_sts": 0.8430030266304707,
|
| 222 |
+
"eval_sickr_spearman": 0.8273284695751733,
|
| 223 |
+
"eval_stsb_spearman": 0.858677583685768,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"eval_avg_sts": 0.8459169389588843,
|
| 229 |
+
"eval_sickr_spearman": 0.8317631811709543,
|
| 230 |
+
"eval_stsb_spearman": 0.8600706967468144,
|
| 231 |
+
"step": 775
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.78,
|
| 235 |
+
"eval_avg_sts": 0.8451542594549106,
|
| 236 |
+
"eval_sickr_spearman": 0.8302367527672511,
|
| 237 |
+
"eval_stsb_spearman": 0.8600717661425702,
|
| 238 |
+
"step": 800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.8,
|
| 242 |
+
"eval_avg_sts": 0.8441819324586433,
|
| 243 |
+
"eval_sickr_spearman": 0.8280832303031719,
|
| 244 |
+
"eval_stsb_spearman": 0.8602806346141146,
|
| 245 |
+
"step": 825
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.83,
|
| 249 |
+
"eval_avg_sts": 0.84041329364274,
|
| 250 |
+
"eval_sickr_spearman": 0.8234209671109596,
|
| 251 |
+
"eval_stsb_spearman": 0.8574056201745204,
|
| 252 |
+
"step": 850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.85,
|
| 256 |
+
"eval_avg_sts": 0.8463098863081795,
|
| 257 |
+
"eval_sickr_spearman": 0.8311718222500483,
|
| 258 |
+
"eval_stsb_spearman": 0.8614479503663108,
|
| 259 |
+
"step": 875
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.88,
|
| 263 |
+
"eval_avg_sts": 0.8489707536403015,
|
| 264 |
+
"eval_sickr_spearman": 0.8359545191757484,
|
| 265 |
+
"eval_stsb_spearman": 0.8619869881048546,
|
| 266 |
+
"step": 900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.9,
|
| 270 |
+
"eval_avg_sts": 0.8459381219997153,
|
| 271 |
+
"eval_sickr_spearman": 0.8324996900804063,
|
| 272 |
+
"eval_stsb_spearman": 0.8593765539190245,
|
| 273 |
+
"step": 925
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.93,
|
| 277 |
+
"eval_avg_sts": 0.8441563920982813,
|
| 278 |
+
"eval_sickr_spearman": 0.8308032796087136,
|
| 279 |
+
"eval_stsb_spearman": 0.8575095045878491,
|
| 280 |
+
"step": 950
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.95,
|
| 284 |
+
"eval_avg_sts": 0.8417274944195297,
|
| 285 |
+
"eval_sickr_spearman": 0.8286961551886236,
|
| 286 |
+
"eval_stsb_spearman": 0.8547588336504358,
|
| 287 |
+
"step": 975
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.97,
|
| 291 |
+
"learning_rate": 6.754300551768907e-06,
|
| 292 |
+
"loss": 0.338,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.97,
|
| 297 |
+
"eval_avg_sts": 0.8439797180911035,
|
| 298 |
+
"eval_sickr_spearman": 0.8322901784159331,
|
| 299 |
+
"eval_stsb_spearman": 0.8556692577662738,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.0,
|
| 304 |
+
"eval_avg_sts": 0.846580279698808,
|
| 305 |
+
"eval_sickr_spearman": 0.8351822751268263,
|
| 306 |
+
"eval_stsb_spearman": 0.8579782842707896,
|
| 307 |
+
"step": 1025
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.02,
|
| 311 |
+
"eval_avg_sts": 0.8444154454958996,
|
| 312 |
+
"eval_sickr_spearman": 0.8319871021658588,
|
| 313 |
+
"eval_stsb_spearman": 0.8568437888259406,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.05,
|
| 318 |
+
"eval_avg_sts": 0.8432409670453203,
|
| 319 |
+
"eval_sickr_spearman": 0.8314499703584763,
|
| 320 |
+
"eval_stsb_spearman": 0.8550319637321643,
|
| 321 |
+
"step": 1075
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.07,
|
| 325 |
+
"eval_avg_sts": 0.8446753892080279,
|
| 326 |
+
"eval_sickr_spearman": 0.8331656893329471,
|
| 327 |
+
"eval_stsb_spearman": 0.8561850890831085,
|
| 328 |
+
"step": 1100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.1,
|
| 332 |
+
"eval_avg_sts": 0.8474510190292008,
|
| 333 |
+
"eval_sickr_spearman": 0.8356278596548676,
|
| 334 |
+
"eval_stsb_spearman": 0.8592741784035342,
|
| 335 |
+
"step": 1125
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.12,
|
| 339 |
+
"eval_avg_sts": 0.8505734569059473,
|
| 340 |
+
"eval_sickr_spearman": 0.8389641479918606,
|
| 341 |
+
"eval_stsb_spearman": 0.862182765820034,
|
| 342 |
+
"step": 1150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.14,
|
| 346 |
+
"eval_avg_sts": 0.8521021908496921,
|
| 347 |
+
"eval_sickr_spearman": 0.8412426954129831,
|
| 348 |
+
"eval_stsb_spearman": 0.862961686286401,
|
| 349 |
+
"step": 1175
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.17,
|
| 353 |
+
"eval_avg_sts": 0.8514560490494238,
|
| 354 |
+
"eval_sickr_spearman": 0.840301718104709,
|
| 355 |
+
"eval_stsb_spearman": 0.8626103799941387,
|
| 356 |
+
"step": 1200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.19,
|
| 360 |
+
"eval_avg_sts": 0.8486972541916555,
|
| 361 |
+
"eval_sickr_spearman": 0.8367856973861348,
|
| 362 |
+
"eval_stsb_spearman": 0.8606088109971762,
|
| 363 |
+
"step": 1225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.22,
|
| 367 |
+
"eval_avg_sts": 0.848898608926278,
|
| 368 |
+
"eval_sickr_spearman": 0.8370826736863266,
|
| 369 |
+
"eval_stsb_spearman": 0.8607145441662293,
|
| 370 |
+
"step": 1250
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.24,
|
| 374 |
+
"eval_avg_sts": 0.8454701656945296,
|
| 375 |
+
"eval_sickr_spearman": 0.8321730305595257,
|
| 376 |
+
"eval_stsb_spearman": 0.8587673008295333,
|
| 377 |
+
"step": 1275
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.27,
|
| 381 |
+
"eval_avg_sts": 0.8452672490522616,
|
| 382 |
+
"eval_sickr_spearman": 0.833004064676608,
|
| 383 |
+
"eval_stsb_spearman": 0.8575304334279151,
|
| 384 |
+
"step": 1300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.29,
|
| 388 |
+
"eval_avg_sts": 0.8489039116599046,
|
| 389 |
+
"eval_sickr_spearman": 0.8371614927237867,
|
| 390 |
+
"eval_stsb_spearman": 0.8606463305960226,
|
| 391 |
+
"step": 1325
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.31,
|
| 395 |
+
"eval_avg_sts": 0.8467466937976185,
|
| 396 |
+
"eval_sickr_spearman": 0.8343573409596268,
|
| 397 |
+
"eval_stsb_spearman": 0.85913604663561,
|
| 398 |
+
"step": 1350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.34,
|
| 402 |
+
"eval_avg_sts": 0.8479786014484607,
|
| 403 |
+
"eval_sickr_spearman": 0.8356114810492773,
|
| 404 |
+
"eval_stsb_spearman": 0.8603457218476441,
|
| 405 |
+
"step": 1375
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.36,
|
| 409 |
+
"eval_avg_sts": 0.8481320629670138,
|
| 410 |
+
"eval_sickr_spearman": 0.8365469828119875,
|
| 411 |
+
"eval_stsb_spearman": 0.8597171431220402,
|
| 412 |
+
"step": 1400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.39,
|
| 416 |
+
"eval_avg_sts": 0.8493017107452288,
|
| 417 |
+
"eval_sickr_spearman": 0.8375811404570515,
|
| 418 |
+
"eval_stsb_spearman": 0.8610222810334061,
|
| 419 |
+
"step": 1425
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.41,
|
| 423 |
+
"eval_avg_sts": 0.8515707185583519,
|
| 424 |
+
"eval_sickr_spearman": 0.8413120523234598,
|
| 425 |
+
"eval_stsb_spearman": 0.8618293847932439,
|
| 426 |
+
"step": 1450
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.44,
|
| 430 |
+
"eval_avg_sts": 0.8491061717045717,
|
| 431 |
+
"eval_sickr_spearman": 0.8386661630385385,
|
| 432 |
+
"eval_stsb_spearman": 0.8595461803706049,
|
| 433 |
+
"step": 1475
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.46,
|
| 437 |
+
"learning_rate": 5.131450827653359e-06,
|
| 438 |
+
"loss": 0.2965,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.46,
|
| 443 |
+
"eval_avg_sts": 0.849951123911407,
|
| 444 |
+
"eval_sickr_spearman": 0.8403214588874001,
|
| 445 |
+
"eval_stsb_spearman": 0.859580788935414,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.48,
|
| 450 |
+
"eval_avg_sts": 0.8462728434267617,
|
| 451 |
+
"eval_sickr_spearman": 0.8349335220524785,
|
| 452 |
+
"eval_stsb_spearman": 0.8576121648010449,
|
| 453 |
+
"step": 1525
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.51,
|
| 457 |
+
"eval_avg_sts": 0.8478142980726532,
|
| 458 |
+
"eval_sickr_spearman": 0.8355811253931684,
|
| 459 |
+
"eval_stsb_spearman": 0.8600474707521379,
|
| 460 |
+
"step": 1550
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.53,
|
| 464 |
+
"eval_avg_sts": 0.8506859270446779,
|
| 465 |
+
"eval_sickr_spearman": 0.8387632819256463,
|
| 466 |
+
"eval_stsb_spearman": 0.8626085721637096,
|
| 467 |
+
"step": 1575
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.56,
|
| 471 |
+
"eval_avg_sts": 0.8491205822275252,
|
| 472 |
+
"eval_sickr_spearman": 0.8368930468978489,
|
| 473 |
+
"eval_stsb_spearman": 0.8613481175572015,
|
| 474 |
+
"step": 1600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.58,
|
| 478 |
+
"eval_avg_sts": 0.8460304537726628,
|
| 479 |
+
"eval_sickr_spearman": 0.8335511389219881,
|
| 480 |
+
"eval_stsb_spearman": 0.8585097686233377,
|
| 481 |
+
"step": 1625
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.61,
|
| 485 |
+
"eval_avg_sts": 0.8488092782108085,
|
| 486 |
+
"eval_sickr_spearman": 0.8360739244939235,
|
| 487 |
+
"eval_stsb_spearman": 0.8615446319276937,
|
| 488 |
+
"step": 1650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.63,
|
| 492 |
+
"eval_avg_sts": 0.8483771836085118,
|
| 493 |
+
"eval_sickr_spearman": 0.8353614791662919,
|
| 494 |
+
"eval_stsb_spearman": 0.8613928880507317,
|
| 495 |
+
"step": 1675
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.66,
|
| 499 |
+
"eval_avg_sts": 0.8482633646541247,
|
| 500 |
+
"eval_sickr_spearman": 0.835166232738946,
|
| 501 |
+
"eval_stsb_spearman": 0.8613604965693032,
|
| 502 |
+
"step": 1700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.68,
|
| 506 |
+
"eval_avg_sts": 0.8494820125153382,
|
| 507 |
+
"eval_sickr_spearman": 0.8363321877263562,
|
| 508 |
+
"eval_stsb_spearman": 0.8626318373043202,
|
| 509 |
+
"step": 1725
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.7,
|
| 513 |
+
"eval_avg_sts": 0.84774811911999,
|
| 514 |
+
"eval_sickr_spearman": 0.8350676729187949,
|
| 515 |
+
"eval_stsb_spearman": 0.8604285653211853,
|
| 516 |
+
"step": 1750
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.73,
|
| 520 |
+
"eval_avg_sts": 0.8508953589183318,
|
| 521 |
+
"eval_sickr_spearman": 0.8393342276284411,
|
| 522 |
+
"eval_stsb_spearman": 0.8624564902082225,
|
| 523 |
+
"step": 1775
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.75,
|
| 527 |
+
"eval_avg_sts": 0.8497877526052855,
|
| 528 |
+
"eval_sickr_spearman": 0.8380021810922581,
|
| 529 |
+
"eval_stsb_spearman": 0.861573324118313,
|
| 530 |
+
"step": 1800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.78,
|
| 534 |
+
"eval_avg_sts": 0.847915612163006,
|
| 535 |
+
"eval_sickr_spearman": 0.8351774720166826,
|
| 536 |
+
"eval_stsb_spearman": 0.8606537523093295,
|
| 537 |
+
"step": 1825
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.8,
|
| 541 |
+
"eval_avg_sts": 0.8496201121858785,
|
| 542 |
+
"eval_sickr_spearman": 0.8377723042407751,
|
| 543 |
+
"eval_stsb_spearman": 0.861467920130982,
|
| 544 |
+
"step": 1850
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.83,
|
| 548 |
+
"eval_avg_sts": 0.8506282266864784,
|
| 549 |
+
"eval_sickr_spearman": 0.8396311078664301,
|
| 550 |
+
"eval_stsb_spearman": 0.8616253455065267,
|
| 551 |
+
"step": 1875
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.85,
|
| 555 |
+
"eval_avg_sts": 0.8507148324349076,
|
| 556 |
+
"eval_sickr_spearman": 0.8398456147654526,
|
| 557 |
+
"eval_stsb_spearman": 0.8615840501043628,
|
| 558 |
+
"step": 1900
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.87,
|
| 562 |
+
"eval_avg_sts": 0.8528364235468135,
|
| 563 |
+
"eval_sickr_spearman": 0.8424179684340722,
|
| 564 |
+
"eval_stsb_spearman": 0.8632548786595547,
|
| 565 |
+
"step": 1925
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.9,
|
| 569 |
+
"eval_avg_sts": 0.8505338171378869,
|
| 570 |
+
"eval_sickr_spearman": 0.8398606965313044,
|
| 571 |
+
"eval_stsb_spearman": 0.8612069377444695,
|
| 572 |
+
"step": 1950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.92,
|
| 576 |
+
"eval_avg_sts": 0.8481722210917726,
|
| 577 |
+
"eval_sickr_spearman": 0.8373791216444029,
|
| 578 |
+
"eval_stsb_spearman": 0.8589653205391424,
|
| 579 |
+
"step": 1975
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.95,
|
| 583 |
+
"learning_rate": 3.5086011035378126e-06,
|
| 584 |
+
"loss": 0.284,
|
| 585 |
+
"step": 2000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.95,
|
| 589 |
+
"eval_avg_sts": 0.8482272752573701,
|
| 590 |
+
"eval_sickr_spearman": 0.8377695664679932,
|
| 591 |
+
"eval_stsb_spearman": 0.858684984046747,
|
| 592 |
+
"step": 2000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.97,
|
| 596 |
+
"eval_avg_sts": 0.8480501028062337,
|
| 597 |
+
"eval_sickr_spearman": 0.837576385378009,
|
| 598 |
+
"eval_stsb_spearman": 0.8585238202344584,
|
| 599 |
+
"step": 2025
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.0,
|
| 603 |
+
"eval_avg_sts": 0.8480832424004543,
|
| 604 |
+
"eval_sickr_spearman": 0.8374597658637174,
|
| 605 |
+
"eval_stsb_spearman": 0.8587067189371913,
|
| 606 |
+
"step": 2050
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.02,
|
| 610 |
+
"eval_avg_sts": 0.8499478012984727,
|
| 611 |
+
"eval_sickr_spearman": 0.8390217853135862,
|
| 612 |
+
"eval_stsb_spearman": 0.8608738172833591,
|
| 613 |
+
"step": 2075
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.04,
|
| 617 |
+
"eval_avg_sts": 0.8491869466527012,
|
| 618 |
+
"eval_sickr_spearman": 0.8378290289715736,
|
| 619 |
+
"eval_stsb_spearman": 0.8605448643338288,
|
| 620 |
+
"step": 2100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.07,
|
| 624 |
+
"eval_avg_sts": 0.8477584257424788,
|
| 625 |
+
"eval_sickr_spearman": 0.8359002920622246,
|
| 626 |
+
"eval_stsb_spearman": 0.8596165594227332,
|
| 627 |
+
"step": 2125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.09,
|
| 631 |
+
"eval_avg_sts": 0.848914705769936,
|
| 632 |
+
"eval_sickr_spearman": 0.837553906822536,
|
| 633 |
+
"eval_stsb_spearman": 0.860275504717336,
|
| 634 |
+
"step": 2150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.12,
|
| 638 |
+
"eval_avg_sts": 0.849736568959095,
|
| 639 |
+
"eval_sickr_spearman": 0.8393637187247242,
|
| 640 |
+
"eval_stsb_spearman": 0.860109419193466,
|
| 641 |
+
"step": 2175
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.14,
|
| 645 |
+
"eval_avg_sts": 0.8495688115163362,
|
| 646 |
+
"eval_sickr_spearman": 0.8389394600057214,
|
| 647 |
+
"eval_stsb_spearman": 0.860198163026951,
|
| 648 |
+
"step": 2200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.17,
|
| 652 |
+
"eval_avg_sts": 0.8483895280681955,
|
| 653 |
+
"eval_sickr_spearman": 0.8374167780279301,
|
| 654 |
+
"eval_stsb_spearman": 0.8593622781084608,
|
| 655 |
+
"step": 2225
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.19,
|
| 659 |
+
"eval_avg_sts": 0.8490834154561102,
|
| 660 |
+
"eval_sickr_spearman": 0.8387396506237387,
|
| 661 |
+
"eval_stsb_spearman": 0.8594271802884818,
|
| 662 |
+
"step": 2250
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.22,
|
| 666 |
+
"eval_avg_sts": 0.8485035624729105,
|
| 667 |
+
"eval_sickr_spearman": 0.8381763418660725,
|
| 668 |
+
"eval_stsb_spearman": 0.8588307830797486,
|
| 669 |
+
"step": 2275
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.24,
|
| 673 |
+
"eval_avg_sts": 0.8476220200458998,
|
| 674 |
+
"eval_sickr_spearman": 0.8364356947499554,
|
| 675 |
+
"eval_stsb_spearman": 0.8588083453418442,
|
| 676 |
+
"step": 2300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.26,
|
| 680 |
+
"eval_avg_sts": 0.8471502937152022,
|
| 681 |
+
"eval_sickr_spearman": 0.8358850662030688,
|
| 682 |
+
"eval_stsb_spearman": 0.8584155212273358,
|
| 683 |
+
"step": 2325
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.29,
|
| 687 |
+
"eval_avg_sts": 0.8481508305259742,
|
| 688 |
+
"eval_sickr_spearman": 0.8369382921954037,
|
| 689 |
+
"eval_stsb_spearman": 0.8593633688565446,
|
| 690 |
+
"step": 2350
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.31,
|
| 694 |
+
"eval_avg_sts": 0.8478439833733975,
|
| 695 |
+
"eval_sickr_spearman": 0.8367764273835573,
|
| 696 |
+
"eval_stsb_spearman": 0.8589115393632376,
|
| 697 |
+
"step": 2375
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.34,
|
| 701 |
+
"eval_avg_sts": 0.8466942437126351,
|
| 702 |
+
"eval_sickr_spearman": 0.8354506248905611,
|
| 703 |
+
"eval_stsb_spearman": 0.8579378625347092,
|
| 704 |
+
"step": 2400
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.36,
|
| 708 |
+
"eval_avg_sts": 0.8477441088420843,
|
| 709 |
+
"eval_sickr_spearman": 0.8366948705733154,
|
| 710 |
+
"eval_stsb_spearman": 0.8587933471108533,
|
| 711 |
+
"step": 2425
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.39,
|
| 715 |
+
"eval_avg_sts": 0.8488516946426614,
|
| 716 |
+
"eval_sickr_spearman": 0.8377335431419145,
|
| 717 |
+
"eval_stsb_spearman": 0.8599698461434083,
|
| 718 |
+
"step": 2450
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.41,
|
| 722 |
+
"eval_avg_sts": 0.8480771808294114,
|
| 723 |
+
"eval_sickr_spearman": 0.8370132207136473,
|
| 724 |
+
"eval_stsb_spearman": 0.8591411409451756,
|
| 725 |
+
"step": 2475
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.43,
|
| 729 |
+
"learning_rate": 1.8857513794222658e-06,
|
| 730 |
+
"loss": 0.2655,
|
| 731 |
+
"step": 2500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.43,
|
| 735 |
+
"eval_avg_sts": 0.8487999481558521,
|
| 736 |
+
"eval_sickr_spearman": 0.8377923812411763,
|
| 737 |
+
"eval_stsb_spearman": 0.8598075150705279,
|
| 738 |
+
"step": 2500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.46,
|
| 742 |
+
"eval_avg_sts": 0.848399750999945,
|
| 743 |
+
"eval_sickr_spearman": 0.8369205206878717,
|
| 744 |
+
"eval_stsb_spearman": 0.8598789813120182,
|
| 745 |
+
"step": 2525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.48,
|
| 749 |
+
"eval_avg_sts": 0.8485584973593749,
|
| 750 |
+
"eval_sickr_spearman": 0.8373407447943537,
|
| 751 |
+
"eval_stsb_spearman": 0.8597762499243962,
|
| 752 |
+
"step": 2550
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.51,
|
| 756 |
+
"eval_avg_sts": 0.8484553378772859,
|
| 757 |
+
"eval_sickr_spearman": 0.8371878137673748,
|
| 758 |
+
"eval_stsb_spearman": 0.8597228619871968,
|
| 759 |
+
"step": 2575
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.53,
|
| 763 |
+
"eval_avg_sts": 0.8480636244098692,
|
| 764 |
+
"eval_sickr_spearman": 0.8368399244996585,
|
| 765 |
+
"eval_stsb_spearman": 0.8592873243200797,
|
| 766 |
+
"step": 2600
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.56,
|
| 770 |
+
"eval_avg_sts": 0.8487639345972604,
|
| 771 |
+
"eval_sickr_spearman": 0.8379995874127802,
|
| 772 |
+
"eval_stsb_spearman": 0.8595282817817406,
|
| 773 |
+
"step": 2625
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.58,
|
| 777 |
+
"eval_avg_sts": 0.8484073121905233,
|
| 778 |
+
"eval_sickr_spearman": 0.8373334920980365,
|
| 779 |
+
"eval_stsb_spearman": 0.85948113228301,
|
| 780 |
+
"step": 2650
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.6,
|
| 784 |
+
"eval_avg_sts": 0.8495353514397407,
|
| 785 |
+
"eval_sickr_spearman": 0.8388814384351839,
|
| 786 |
+
"eval_stsb_spearman": 0.8601892644442974,
|
| 787 |
+
"step": 2675
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.63,
|
| 791 |
+
"eval_avg_sts": 0.8488734860883285,
|
| 792 |
+
"eval_sickr_spearman": 0.8376559248819906,
|
| 793 |
+
"eval_stsb_spearman": 0.8600910472946663,
|
| 794 |
+
"step": 2700
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.65,
|
| 798 |
+
"eval_avg_sts": 0.8485291479370792,
|
| 799 |
+
"eval_sickr_spearman": 0.8370302717546578,
|
| 800 |
+
"eval_stsb_spearman": 0.8600280241195006,
|
| 801 |
+
"step": 2725
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.68,
|
| 805 |
+
"eval_avg_sts": 0.8484609936724099,
|
| 806 |
+
"eval_sickr_spearman": 0.8370401181304525,
|
| 807 |
+
"eval_stsb_spearman": 0.8598818692143673,
|
| 808 |
+
"step": 2750
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.7,
|
| 812 |
+
"eval_avg_sts": 0.8487467947632423,
|
| 813 |
+
"eval_sickr_spearman": 0.8374640886628467,
|
| 814 |
+
"eval_stsb_spearman": 0.8600295008636379,
|
| 815 |
+
"step": 2775
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.73,
|
| 819 |
+
"eval_avg_sts": 0.8487549703295775,
|
| 820 |
+
"eval_sickr_spearman": 0.8377412761492462,
|
| 821 |
+
"eval_stsb_spearman": 0.8597686645099087,
|
| 822 |
+
"step": 2800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.75,
|
| 826 |
+
"eval_avg_sts": 0.8483512050356906,
|
| 827 |
+
"eval_sickr_spearman": 0.8371601478529463,
|
| 828 |
+
"eval_stsb_spearman": 0.8595422622184349,
|
| 829 |
+
"step": 2825
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.78,
|
| 833 |
+
"eval_avg_sts": 0.8487416863586705,
|
| 834 |
+
"eval_sickr_spearman": 0.8376103433667258,
|
| 835 |
+
"eval_stsb_spearman": 0.8598730293506154,
|
| 836 |
+
"step": 2850
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.8,
|
| 840 |
+
"eval_avg_sts": 0.8486695192263061,
|
| 841 |
+
"eval_sickr_spearman": 0.8374840215699435,
|
| 842 |
+
"eval_stsb_spearman": 0.8598550168826687,
|
| 843 |
+
"step": 2875
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.82,
|
| 847 |
+
"eval_avg_sts": 0.8490062168713867,
|
| 848 |
+
"eval_sickr_spearman": 0.8380430075284804,
|
| 849 |
+
"eval_stsb_spearman": 0.859969426214293,
|
| 850 |
+
"step": 2900
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.85,
|
| 854 |
+
"eval_avg_sts": 0.8488936976734611,
|
| 855 |
+
"eval_sickr_spearman": 0.8378850332358503,
|
| 856 |
+
"eval_stsb_spearman": 0.859902362111072,
|
| 857 |
+
"step": 2925
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.87,
|
| 861 |
+
"eval_avg_sts": 0.8489709020581676,
|
| 862 |
+
"eval_sickr_spearman": 0.8379462248590827,
|
| 863 |
+
"eval_stsb_spearman": 0.8599955792572526,
|
| 864 |
+
"step": 2950
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.9,
|
| 868 |
+
"eval_avg_sts": 0.8487957508450565,
|
| 869 |
+
"eval_sickr_spearman": 0.8376585185614683,
|
| 870 |
+
"eval_stsb_spearman": 0.8599329831286449,
|
| 871 |
+
"step": 2975
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.92,
|
| 875 |
+
"learning_rate": 2.6290165530671865e-07,
|
| 876 |
+
"loss": 0.263,
|
| 877 |
+
"step": 3000
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.92,
|
| 881 |
+
"eval_avg_sts": 0.8485199174178477,
|
| 882 |
+
"eval_sickr_spearman": 0.837266008400516,
|
| 883 |
+
"eval_stsb_spearman": 0.8597738264351793,
|
| 884 |
+
"step": 3000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.95,
|
| 888 |
+
"eval_avg_sts": 0.8483285540592784,
|
| 889 |
+
"eval_sickr_spearman": 0.837077006016357,
|
| 890 |
+
"eval_stsb_spearman": 0.8595801021021999,
|
| 891 |
+
"step": 3025
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.97,
|
| 895 |
+
"eval_avg_sts": 0.8483039392081567,
|
| 896 |
+
"eval_sickr_spearman": 0.8370466464338976,
|
| 897 |
+
"eval_stsb_spearman": 0.8595612319824159,
|
| 898 |
+
"step": 3050
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.99,
|
| 902 |
+
"eval_avg_sts": 0.8482931559093356,
|
| 903 |
+
"eval_sickr_spearman": 0.837029215070426,
|
| 904 |
+
"eval_stsb_spearman": 0.8595570967482453,
|
| 905 |
+
"step": 3075
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.0,
|
| 909 |
+
"step": 3081,
|
| 910 |
+
"train_runtime": 8699.7484,
|
| 911 |
+
"train_samples_per_second": 0.354
|
| 912 |
+
}
|
| 913 |
+
],
|
| 914 |
+
"max_steps": 3081,
|
| 915 |
+
"num_train_epochs": 3,
|
| 916 |
+
"total_flos": 333879495592513536,
|
| 917 |
+
"trial_name": null,
|
| 918 |
+
"trial_params": null
|
| 919 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864a98bc0117934b9f37e527ccfbfef287c1f6ba63f3578b5eafd7d7adeffcfe
|
| 3 |
+
size 2488
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|