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 +808 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/multicse-bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.2.1",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 6.0
|
| 2 |
+
eval_CR = 88.58
|
| 3 |
+
eval_MPQA = 89.58
|
| 4 |
+
eval_MR = 81.09
|
| 5 |
+
eval_MRPC = 75.1
|
| 6 |
+
eval_SST2 = 86.58
|
| 7 |
+
eval_SUBJ = 93.96
|
| 8 |
+
eval_TREC = 77.73
|
| 9 |
+
eval_avg_sts = 0.8362939444102149
|
| 10 |
+
eval_avg_transfer = 84.66
|
| 11 |
+
eval_sickr_spearman = 0.8178701370488788
|
| 12 |
+
eval_stsb_spearman = 0.8547177517715511
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf03dbe1d532b1587652859a6f262a3ba76c53292c414f98118d25acd1151028
|
| 3 |
+
size 534271106
|
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-base-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 6.0
|
| 2 |
+
train_runtime = 3739.6542
|
| 3 |
+
train_samples_per_second = 0.724
|
trainer_state.json
ADDED
|
@@ -0,0 +1,808 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8362939444102149,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/multicse-bert-base-uncased",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 2706,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"eval_avg_sts": 0.808172199263909,
|
| 13 |
+
"eval_sickr_spearman": 0.783590147828092,
|
| 14 |
+
"eval_stsb_spearman": 0.8327542506997261,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"eval_avg_sts": 0.820794223239678,
|
| 20 |
+
"eval_sickr_spearman": 0.8053590918084821,
|
| 21 |
+
"eval_stsb_spearman": 0.8362293546708739,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.17,
|
| 26 |
+
"eval_avg_sts": 0.8218985782625993,
|
| 27 |
+
"eval_sickr_spearman": 0.8010904717614742,
|
| 28 |
+
"eval_stsb_spearman": 0.8427066847637243,
|
| 29 |
+
"step": 75
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.22,
|
| 33 |
+
"eval_avg_sts": 0.8212197665999863,
|
| 34 |
+
"eval_sickr_spearman": 0.7985843529817378,
|
| 35 |
+
"eval_stsb_spearman": 0.8438551802182349,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.28,
|
| 40 |
+
"eval_avg_sts": 0.8263710498747726,
|
| 41 |
+
"eval_sickr_spearman": 0.8055955008897605,
|
| 42 |
+
"eval_stsb_spearman": 0.8471465988597847,
|
| 43 |
+
"step": 125
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.33,
|
| 47 |
+
"eval_avg_sts": 0.8263231728376124,
|
| 48 |
+
"eval_sickr_spearman": 0.8046682604764976,
|
| 49 |
+
"eval_stsb_spearman": 0.8479780851987271,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.39,
|
| 54 |
+
"eval_avg_sts": 0.8240636839647479,
|
| 55 |
+
"eval_sickr_spearman": 0.80153019649514,
|
| 56 |
+
"eval_stsb_spearman": 0.8465971714343559,
|
| 57 |
+
"step": 175
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.44,
|
| 61 |
+
"eval_avg_sts": 0.8305466429958255,
|
| 62 |
+
"eval_sickr_spearman": 0.8140019522945605,
|
| 63 |
+
"eval_stsb_spearman": 0.8470913336970906,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5,
|
| 68 |
+
"eval_avg_sts": 0.8212438683719858,
|
| 69 |
+
"eval_sickr_spearman": 0.796099127731127,
|
| 70 |
+
"eval_stsb_spearman": 0.8463886090128445,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.55,
|
| 75 |
+
"eval_avg_sts": 0.8290131151517519,
|
| 76 |
+
"eval_sickr_spearman": 0.8127541523102997,
|
| 77 |
+
"eval_stsb_spearman": 0.8452720779932043,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.61,
|
| 82 |
+
"eval_avg_sts": 0.8291875600829677,
|
| 83 |
+
"eval_sickr_spearman": 0.8103600420591169,
|
| 84 |
+
"eval_stsb_spearman": 0.8480150781068185,
|
| 85 |
+
"step": 275
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.67,
|
| 89 |
+
"eval_avg_sts": 0.8327962239942688,
|
| 90 |
+
"eval_sickr_spearman": 0.816952310731498,
|
| 91 |
+
"eval_stsb_spearman": 0.8486401372570397,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.72,
|
| 96 |
+
"eval_avg_sts": 0.8330122790068915,
|
| 97 |
+
"eval_sickr_spearman": 0.8143033474560845,
|
| 98 |
+
"eval_stsb_spearman": 0.8517212105576986,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.78,
|
| 103 |
+
"eval_avg_sts": 0.8334940457333329,
|
| 104 |
+
"eval_sickr_spearman": 0.8149612294524823,
|
| 105 |
+
"eval_stsb_spearman": 0.8520268620141834,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.83,
|
| 110 |
+
"eval_avg_sts": 0.8359867680300406,
|
| 111 |
+
"eval_sickr_spearman": 0.8166730579077367,
|
| 112 |
+
"eval_stsb_spearman": 0.8553004781523443,
|
| 113 |
+
"step": 375
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.89,
|
| 117 |
+
"eval_avg_sts": 0.8362939444102149,
|
| 118 |
+
"eval_sickr_spearman": 0.8178701370488788,
|
| 119 |
+
"eval_stsb_spearman": 0.8547177517715511,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.94,
|
| 124 |
+
"eval_avg_sts": 0.8269789550924258,
|
| 125 |
+
"eval_sickr_spearman": 0.8014972471595535,
|
| 126 |
+
"eval_stsb_spearman": 0.852460663025298,
|
| 127 |
+
"step": 425
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.0,
|
| 131 |
+
"eval_avg_sts": 0.8271598937884023,
|
| 132 |
+
"eval_sickr_spearman": 0.8061173588068856,
|
| 133 |
+
"eval_stsb_spearman": 0.8482024287699189,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.05,
|
| 138 |
+
"eval_avg_sts": 0.8282927205714137,
|
| 139 |
+
"eval_sickr_spearman": 0.8104696010014973,
|
| 140 |
+
"eval_stsb_spearman": 0.84611584014133,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.11,
|
| 145 |
+
"learning_rate": 4.076127124907613e-05,
|
| 146 |
+
"loss": 0.4303,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.11,
|
| 151 |
+
"eval_avg_sts": 0.8274629650840639,
|
| 152 |
+
"eval_sickr_spearman": 0.8056994401932726,
|
| 153 |
+
"eval_stsb_spearman": 0.8492264899748552,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.16,
|
| 158 |
+
"eval_avg_sts": 0.8274341455051789,
|
| 159 |
+
"eval_sickr_spearman": 0.8072793272128764,
|
| 160 |
+
"eval_stsb_spearman": 0.8475889637974814,
|
| 161 |
+
"step": 525
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.22,
|
| 165 |
+
"eval_avg_sts": 0.8269940468993253,
|
| 166 |
+
"eval_sickr_spearman": 0.803170506640353,
|
| 167 |
+
"eval_stsb_spearman": 0.8508175871582977,
|
| 168 |
+
"step": 550
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.27,
|
| 172 |
+
"eval_avg_sts": 0.8288643821143353,
|
| 173 |
+
"eval_sickr_spearman": 0.8083313524276753,
|
| 174 |
+
"eval_stsb_spearman": 0.8493974118009953,
|
| 175 |
+
"step": 575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.33,
|
| 179 |
+
"eval_avg_sts": 0.8342864948337284,
|
| 180 |
+
"eval_sickr_spearman": 0.8138802895146177,
|
| 181 |
+
"eval_stsb_spearman": 0.8546927001528392,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.39,
|
| 186 |
+
"eval_avg_sts": 0.8270151161624402,
|
| 187 |
+
"eval_sickr_spearman": 0.8041265176833771,
|
| 188 |
+
"eval_stsb_spearman": 0.8499037146415034,
|
| 189 |
+
"step": 625
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.44,
|
| 193 |
+
"eval_avg_sts": 0.8279455772988316,
|
| 194 |
+
"eval_sickr_spearman": 0.8036888102559718,
|
| 195 |
+
"eval_stsb_spearman": 0.8522023443416914,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.5,
|
| 200 |
+
"eval_avg_sts": 0.829012477308678,
|
| 201 |
+
"eval_sickr_spearman": 0.808486444854219,
|
| 202 |
+
"eval_stsb_spearman": 0.849538509763137,
|
| 203 |
+
"step": 675
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.55,
|
| 207 |
+
"eval_avg_sts": 0.8288300235840231,
|
| 208 |
+
"eval_sickr_spearman": 0.8088525379093803,
|
| 209 |
+
"eval_stsb_spearman": 0.848807509258666,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.61,
|
| 214 |
+
"eval_avg_sts": 0.8305859335486241,
|
| 215 |
+
"eval_sickr_spearman": 0.8107295453224803,
|
| 216 |
+
"eval_stsb_spearman": 0.8504423217747678,
|
| 217 |
+
"step": 725
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.66,
|
| 221 |
+
"eval_avg_sts": 0.8280931139956361,
|
| 222 |
+
"eval_sickr_spearman": 0.8061409420776917,
|
| 223 |
+
"eval_stsb_spearman": 0.8500452859135805,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.72,
|
| 228 |
+
"eval_avg_sts": 0.8302899379899211,
|
| 229 |
+
"eval_sickr_spearman": 0.8096262228913453,
|
| 230 |
+
"eval_stsb_spearman": 0.850953653088497,
|
| 231 |
+
"step": 775
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.77,
|
| 235 |
+
"eval_avg_sts": 0.8312188464560427,
|
| 236 |
+
"eval_sickr_spearman": 0.8104490436900817,
|
| 237 |
+
"eval_stsb_spearman": 0.8519886492220037,
|
| 238 |
+
"step": 800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.83,
|
| 242 |
+
"eval_avg_sts": 0.8302662907658385,
|
| 243 |
+
"eval_sickr_spearman": 0.8117301772587404,
|
| 244 |
+
"eval_stsb_spearman": 0.8488024042729365,
|
| 245 |
+
"step": 825
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.88,
|
| 249 |
+
"eval_avg_sts": 0.83177529644248,
|
| 250 |
+
"eval_sickr_spearman": 0.8116331544338355,
|
| 251 |
+
"eval_stsb_spearman": 0.8519174384511247,
|
| 252 |
+
"step": 850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.94,
|
| 256 |
+
"eval_avg_sts": 0.8342887017337668,
|
| 257 |
+
"eval_sickr_spearman": 0.8159248294095337,
|
| 258 |
+
"eval_stsb_spearman": 0.8526525740579998,
|
| 259 |
+
"step": 875
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.0,
|
| 263 |
+
"eval_avg_sts": 0.8335303856286564,
|
| 264 |
+
"eval_sickr_spearman": 0.8152034983281362,
|
| 265 |
+
"eval_stsb_spearman": 0.8518572729291767,
|
| 266 |
+
"step": 900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.05,
|
| 270 |
+
"eval_avg_sts": 0.8316736063387226,
|
| 271 |
+
"eval_sickr_spearman": 0.8125293667555692,
|
| 272 |
+
"eval_stsb_spearman": 0.8508178459218759,
|
| 273 |
+
"step": 925
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.11,
|
| 277 |
+
"eval_avg_sts": 0.8280586113483762,
|
| 278 |
+
"eval_sickr_spearman": 0.809915706339713,
|
| 279 |
+
"eval_stsb_spearman": 0.8462015163570394,
|
| 280 |
+
"step": 950
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.16,
|
| 284 |
+
"eval_avg_sts": 0.8285809844295435,
|
| 285 |
+
"eval_sickr_spearman": 0.8105551443931586,
|
| 286 |
+
"eval_stsb_spearman": 0.8466068244659284,
|
| 287 |
+
"step": 975
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.22,
|
| 291 |
+
"learning_rate": 3.152254249815226e-05,
|
| 292 |
+
"loss": 0.2628,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.22,
|
| 297 |
+
"eval_avg_sts": 0.8304703081697632,
|
| 298 |
+
"eval_sickr_spearman": 0.8108091328575633,
|
| 299 |
+
"eval_stsb_spearman": 0.8501314834819631,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.27,
|
| 304 |
+
"eval_avg_sts": 0.8246676161757887,
|
| 305 |
+
"eval_sickr_spearman": 0.8022548417225369,
|
| 306 |
+
"eval_stsb_spearman": 0.8470803906290405,
|
| 307 |
+
"step": 1025
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.33,
|
| 311 |
+
"eval_avg_sts": 0.8247542776319872,
|
| 312 |
+
"eval_sickr_spearman": 0.8023693478683652,
|
| 313 |
+
"eval_stsb_spearman": 0.8471392073956092,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.38,
|
| 318 |
+
"eval_avg_sts": 0.8284712817725378,
|
| 319 |
+
"eval_sickr_spearman": 0.8063077540929862,
|
| 320 |
+
"eval_stsb_spearman": 0.8506348094520895,
|
| 321 |
+
"step": 1075
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.44,
|
| 325 |
+
"eval_avg_sts": 0.8267581222566869,
|
| 326 |
+
"eval_sickr_spearman": 0.8023707888014083,
|
| 327 |
+
"eval_stsb_spearman": 0.8511454557119653,
|
| 328 |
+
"step": 1100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.49,
|
| 332 |
+
"eval_avg_sts": 0.8245678399799343,
|
| 333 |
+
"eval_sickr_spearman": 0.8010677050193924,
|
| 334 |
+
"eval_stsb_spearman": 0.8480679749404763,
|
| 335 |
+
"step": 1125
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.55,
|
| 339 |
+
"eval_avg_sts": 0.8264893834503197,
|
| 340 |
+
"eval_sickr_spearman": 0.8047740249618645,
|
| 341 |
+
"eval_stsb_spearman": 0.848204741938775,
|
| 342 |
+
"step": 1150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.61,
|
| 346 |
+
"eval_avg_sts": 0.8239740308575658,
|
| 347 |
+
"eval_sickr_spearman": 0.802257483433116,
|
| 348 |
+
"eval_stsb_spearman": 0.8456905782820158,
|
| 349 |
+
"step": 1175
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.66,
|
| 353 |
+
"eval_avg_sts": 0.8252898688219781,
|
| 354 |
+
"eval_sickr_spearman": 0.8059969928666816,
|
| 355 |
+
"eval_stsb_spearman": 0.8445827447772745,
|
| 356 |
+
"step": 1200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.72,
|
| 360 |
+
"eval_avg_sts": 0.8218363555031618,
|
| 361 |
+
"eval_sickr_spearman": 0.7991245587796122,
|
| 362 |
+
"eval_stsb_spearman": 0.8445481522267114,
|
| 363 |
+
"step": 1225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.77,
|
| 367 |
+
"eval_avg_sts": 0.8265232671423588,
|
| 368 |
+
"eval_sickr_spearman": 0.8062044391937928,
|
| 369 |
+
"eval_stsb_spearman": 0.8468420950909247,
|
| 370 |
+
"step": 1250
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.83,
|
| 374 |
+
"eval_avg_sts": 0.8286104291951198,
|
| 375 |
+
"eval_sickr_spearman": 0.8096378464178936,
|
| 376 |
+
"eval_stsb_spearman": 0.8475830119723461,
|
| 377 |
+
"step": 1275
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.88,
|
| 381 |
+
"eval_avg_sts": 0.8314342022111989,
|
| 382 |
+
"eval_sickr_spearman": 0.8138266387743112,
|
| 383 |
+
"eval_stsb_spearman": 0.8490417656480866,
|
| 384 |
+
"step": 1300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.94,
|
| 388 |
+
"eval_avg_sts": 0.8285621943597675,
|
| 389 |
+
"eval_sickr_spearman": 0.807191478328346,
|
| 390 |
+
"eval_stsb_spearman": 0.849932910391189,
|
| 391 |
+
"step": 1325
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.99,
|
| 395 |
+
"eval_avg_sts": 0.8284116030199242,
|
| 396 |
+
"eval_sickr_spearman": 0.8073644383246247,
|
| 397 |
+
"eval_stsb_spearman": 0.8494587677152238,
|
| 398 |
+
"step": 1350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.05,
|
| 402 |
+
"eval_avg_sts": 0.8247221665272242,
|
| 403 |
+
"eval_sickr_spearman": 0.8022067145588959,
|
| 404 |
+
"eval_stsb_spearman": 0.8472376184955523,
|
| 405 |
+
"step": 1375
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.1,
|
| 409 |
+
"eval_avg_sts": 0.826858184586315,
|
| 410 |
+
"eval_sickr_spearman": 0.8056980472913309,
|
| 411 |
+
"eval_stsb_spearman": 0.848018321881299,
|
| 412 |
+
"step": 1400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 3.16,
|
| 416 |
+
"eval_avg_sts": 0.8262245909726973,
|
| 417 |
+
"eval_sickr_spearman": 0.8059310941955087,
|
| 418 |
+
"eval_stsb_spearman": 0.846518087749886,
|
| 419 |
+
"step": 1425
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.22,
|
| 423 |
+
"eval_avg_sts": 0.8271328383994965,
|
| 424 |
+
"eval_sickr_spearman": 0.8059575113012996,
|
| 425 |
+
"eval_stsb_spearman": 0.8483081654976934,
|
| 426 |
+
"step": 1450
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.27,
|
| 430 |
+
"eval_avg_sts": 0.8262273295933256,
|
| 431 |
+
"eval_sickr_spearman": 0.8045855028887199,
|
| 432 |
+
"eval_stsb_spearman": 0.8478691562979312,
|
| 433 |
+
"step": 1475
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.33,
|
| 437 |
+
"learning_rate": 2.2283813747228384e-05,
|
| 438 |
+
"loss": 0.2284,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.33,
|
| 443 |
+
"eval_avg_sts": 0.8290942209780299,
|
| 444 |
+
"eval_sickr_spearman": 0.8098024490025217,
|
| 445 |
+
"eval_stsb_spearman": 0.848385992953538,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.38,
|
| 450 |
+
"eval_avg_sts": 0.8271287520959363,
|
| 451 |
+
"eval_sickr_spearman": 0.8068388820126888,
|
| 452 |
+
"eval_stsb_spearman": 0.8474186221791836,
|
| 453 |
+
"step": 1525
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.44,
|
| 457 |
+
"eval_avg_sts": 0.8284906943060749,
|
| 458 |
+
"eval_sickr_spearman": 0.8083666552872324,
|
| 459 |
+
"eval_stsb_spearman": 0.8486147333249174,
|
| 460 |
+
"step": 1550
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.49,
|
| 464 |
+
"eval_avg_sts": 0.8247556311383242,
|
| 465 |
+
"eval_sickr_spearman": 0.8033069629995387,
|
| 466 |
+
"eval_stsb_spearman": 0.8462042992771095,
|
| 467 |
+
"step": 1575
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.55,
|
| 471 |
+
"eval_avg_sts": 0.8256788195546352,
|
| 472 |
+
"eval_sickr_spearman": 0.8046946295511871,
|
| 473 |
+
"eval_stsb_spearman": 0.8466630095580832,
|
| 474 |
+
"step": 1600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.6,
|
| 478 |
+
"eval_avg_sts": 0.8246935620550073,
|
| 479 |
+
"eval_sickr_spearman": 0.8025401944961806,
|
| 480 |
+
"eval_stsb_spearman": 0.8468469296138341,
|
| 481 |
+
"step": 1625
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 3.66,
|
| 485 |
+
"eval_avg_sts": 0.8263329601931413,
|
| 486 |
+
"eval_sickr_spearman": 0.8045876162571832,
|
| 487 |
+
"eval_stsb_spearman": 0.8480783041290992,
|
| 488 |
+
"step": 1650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.71,
|
| 492 |
+
"eval_avg_sts": 0.8264865724885355,
|
| 493 |
+
"eval_sickr_spearman": 0.8057473272014063,
|
| 494 |
+
"eval_stsb_spearman": 0.8472258177756647,
|
| 495 |
+
"step": 1675
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.77,
|
| 499 |
+
"eval_avg_sts": 0.8254423729673166,
|
| 500 |
+
"eval_sickr_spearman": 0.8031947143154778,
|
| 501 |
+
"eval_stsb_spearman": 0.8476900316191552,
|
| 502 |
+
"step": 1700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 3.82,
|
| 506 |
+
"eval_avg_sts": 0.8264107919338515,
|
| 507 |
+
"eval_sickr_spearman": 0.8053674972512337,
|
| 508 |
+
"eval_stsb_spearman": 0.8474540866164694,
|
| 509 |
+
"step": 1725
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 3.88,
|
| 513 |
+
"eval_avg_sts": 0.8264776461929313,
|
| 514 |
+
"eval_sickr_spearman": 0.8059907968545961,
|
| 515 |
+
"eval_stsb_spearman": 0.8469644955312665,
|
| 516 |
+
"step": 1750
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 3.94,
|
| 520 |
+
"eval_avg_sts": 0.8240221134684459,
|
| 521 |
+
"eval_sickr_spearman": 0.8008853789583333,
|
| 522 |
+
"eval_stsb_spearman": 0.8471588479785584,
|
| 523 |
+
"step": 1775
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 3.99,
|
| 527 |
+
"eval_avg_sts": 0.8260093129727113,
|
| 528 |
+
"eval_sickr_spearman": 0.8032525437616094,
|
| 529 |
+
"eval_stsb_spearman": 0.8487660821838133,
|
| 530 |
+
"step": 1800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.05,
|
| 534 |
+
"eval_avg_sts": 0.8251871747358858,
|
| 535 |
+
"eval_sickr_spearman": 0.8022517677320448,
|
| 536 |
+
"eval_stsb_spearman": 0.8481225817397268,
|
| 537 |
+
"step": 1825
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.1,
|
| 541 |
+
"eval_avg_sts": 0.8236068675958164,
|
| 542 |
+
"eval_sickr_spearman": 0.8001952680928707,
|
| 543 |
+
"eval_stsb_spearman": 0.8470184670987619,
|
| 544 |
+
"step": 1850
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.16,
|
| 548 |
+
"eval_avg_sts": 0.8238228114044301,
|
| 549 |
+
"eval_sickr_spearman": 0.8002784579605614,
|
| 550 |
+
"eval_stsb_spearman": 0.8473671648482989,
|
| 551 |
+
"step": 1875
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.21,
|
| 555 |
+
"eval_avg_sts": 0.8236955591912043,
|
| 556 |
+
"eval_sickr_spearman": 0.7999801848206307,
|
| 557 |
+
"eval_stsb_spearman": 0.847410933561778,
|
| 558 |
+
"step": 1900
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.27,
|
| 562 |
+
"eval_avg_sts": 0.8217179921122288,
|
| 563 |
+
"eval_sickr_spearman": 0.7976729628319497,
|
| 564 |
+
"eval_stsb_spearman": 0.8457630213925079,
|
| 565 |
+
"step": 1925
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 4.32,
|
| 569 |
+
"eval_avg_sts": 0.8218133292332199,
|
| 570 |
+
"eval_sickr_spearman": 0.7972407309501078,
|
| 571 |
+
"eval_stsb_spearman": 0.8463859275163321,
|
| 572 |
+
"step": 1950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.38,
|
| 576 |
+
"eval_avg_sts": 0.82307986157595,
|
| 577 |
+
"eval_sickr_spearman": 0.7997425269307149,
|
| 578 |
+
"eval_stsb_spearman": 0.846417196221185,
|
| 579 |
+
"step": 1975
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.43,
|
| 583 |
+
"learning_rate": 1.3045084996304511e-05,
|
| 584 |
+
"loss": 0.2149,
|
| 585 |
+
"step": 2000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.43,
|
| 589 |
+
"eval_avg_sts": 0.8251845211566629,
|
| 590 |
+
"eval_sickr_spearman": 0.803791356657542,
|
| 591 |
+
"eval_stsb_spearman": 0.8465776856557838,
|
| 592 |
+
"step": 2000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 4.49,
|
| 596 |
+
"eval_avg_sts": 0.8244897261222982,
|
| 597 |
+
"eval_sickr_spearman": 0.8012433547573516,
|
| 598 |
+
"eval_stsb_spearman": 0.8477360974872448,
|
| 599 |
+
"step": 2025
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 4.55,
|
| 603 |
+
"eval_avg_sts": 0.8248464356555265,
|
| 604 |
+
"eval_sickr_spearman": 0.80196872045127,
|
| 605 |
+
"eval_stsb_spearman": 0.847724150859783,
|
| 606 |
+
"step": 2050
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 4.6,
|
| 610 |
+
"eval_avg_sts": 0.8236282342217962,
|
| 611 |
+
"eval_sickr_spearman": 0.801061412945104,
|
| 612 |
+
"eval_stsb_spearman": 0.8461950554984884,
|
| 613 |
+
"step": 2075
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 4.66,
|
| 617 |
+
"eval_avg_sts": 0.8241232806486489,
|
| 618 |
+
"eval_sickr_spearman": 0.8016284200975811,
|
| 619 |
+
"eval_stsb_spearman": 0.8466181411997169,
|
| 620 |
+
"step": 2100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.71,
|
| 624 |
+
"eval_avg_sts": 0.8240448338930326,
|
| 625 |
+
"eval_sickr_spearman": 0.8024957657273504,
|
| 626 |
+
"eval_stsb_spearman": 0.845593902058715,
|
| 627 |
+
"step": 2125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 4.77,
|
| 631 |
+
"eval_avg_sts": 0.8252602189328375,
|
| 632 |
+
"eval_sickr_spearman": 0.8031946662843764,
|
| 633 |
+
"eval_stsb_spearman": 0.8473257715812985,
|
| 634 |
+
"step": 2150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 4.82,
|
| 638 |
+
"eval_avg_sts": 0.8237954063381605,
|
| 639 |
+
"eval_sickr_spearman": 0.8006036285172974,
|
| 640 |
+
"eval_stsb_spearman": 0.8469871841590237,
|
| 641 |
+
"step": 2175
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 4.88,
|
| 645 |
+
"eval_avg_sts": 0.8238382480785117,
|
| 646 |
+
"eval_sickr_spearman": 0.8008013245308166,
|
| 647 |
+
"eval_stsb_spearman": 0.8468751716262067,
|
| 648 |
+
"step": 2200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 4.93,
|
| 652 |
+
"eval_avg_sts": 0.8226554353280054,
|
| 653 |
+
"eval_sickr_spearman": 0.79934425303759,
|
| 654 |
+
"eval_stsb_spearman": 0.8459666176184208,
|
| 655 |
+
"step": 2225
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 4.99,
|
| 659 |
+
"eval_avg_sts": 0.8221324924350076,
|
| 660 |
+
"eval_sickr_spearman": 0.7977314166823997,
|
| 661 |
+
"eval_stsb_spearman": 0.8465335681876156,
|
| 662 |
+
"step": 2250
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 5.04,
|
| 666 |
+
"eval_avg_sts": 0.8230411082185226,
|
| 667 |
+
"eval_sickr_spearman": 0.7989547688360285,
|
| 668 |
+
"eval_stsb_spearman": 0.8471274476010168,
|
| 669 |
+
"step": 2275
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.1,
|
| 673 |
+
"eval_avg_sts": 0.8228022688627314,
|
| 674 |
+
"eval_sickr_spearman": 0.7994119768906178,
|
| 675 |
+
"eval_stsb_spearman": 0.846192560834845,
|
| 676 |
+
"step": 2300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 5.16,
|
| 680 |
+
"eval_avg_sts": 0.8228479899857558,
|
| 681 |
+
"eval_sickr_spearman": 0.7989381981060323,
|
| 682 |
+
"eval_stsb_spearman": 0.8467577818654793,
|
| 683 |
+
"step": 2325
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 5.21,
|
| 687 |
+
"eval_avg_sts": 0.8221050116430979,
|
| 688 |
+
"eval_sickr_spearman": 0.7985421816746751,
|
| 689 |
+
"eval_stsb_spearman": 0.8456678416115206,
|
| 690 |
+
"step": 2350
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 5.27,
|
| 694 |
+
"eval_avg_sts": 0.822383318476755,
|
| 695 |
+
"eval_sickr_spearman": 0.7986474658490273,
|
| 696 |
+
"eval_stsb_spearman": 0.8461191711044828,
|
| 697 |
+
"step": 2375
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 5.32,
|
| 701 |
+
"eval_avg_sts": 0.823048712126393,
|
| 702 |
+
"eval_sickr_spearman": 0.7993529466669504,
|
| 703 |
+
"eval_stsb_spearman": 0.8467444775858354,
|
| 704 |
+
"step": 2400
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 5.38,
|
| 708 |
+
"eval_avg_sts": 0.8228378854074433,
|
| 709 |
+
"eval_sickr_spearman": 0.799309382457946,
|
| 710 |
+
"eval_stsb_spearman": 0.8463663883569406,
|
| 711 |
+
"step": 2425
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 5.43,
|
| 715 |
+
"eval_avg_sts": 0.8229990938054758,
|
| 716 |
+
"eval_sickr_spearman": 0.7993526104492402,
|
| 717 |
+
"eval_stsb_spearman": 0.8466455771617113,
|
| 718 |
+
"step": 2450
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 5.49,
|
| 722 |
+
"eval_avg_sts": 0.8223080164546823,
|
| 723 |
+
"eval_sickr_spearman": 0.7985109614587403,
|
| 724 |
+
"eval_stsb_spearman": 0.8461050714506243,
|
| 725 |
+
"step": 2475
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 5.54,
|
| 729 |
+
"learning_rate": 3.806356245380636e-06,
|
| 730 |
+
"loss": 0.2074,
|
| 731 |
+
"step": 2500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 5.54,
|
| 735 |
+
"eval_avg_sts": 0.8224706658462584,
|
| 736 |
+
"eval_sickr_spearman": 0.7986079842836452,
|
| 737 |
+
"eval_stsb_spearman": 0.8463333474088716,
|
| 738 |
+
"step": 2500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 5.6,
|
| 742 |
+
"eval_avg_sts": 0.8228255546038069,
|
| 743 |
+
"eval_sickr_spearman": 0.7993520821071245,
|
| 744 |
+
"eval_stsb_spearman": 0.8462990271004893,
|
| 745 |
+
"step": 2525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 5.65,
|
| 749 |
+
"eval_avg_sts": 0.8222772197799051,
|
| 750 |
+
"eval_sickr_spearman": 0.7986904536848144,
|
| 751 |
+
"eval_stsb_spearman": 0.8458639858749959,
|
| 752 |
+
"step": 2550
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 5.71,
|
| 756 |
+
"eval_avg_sts": 0.822395438556291,
|
| 757 |
+
"eval_sickr_spearman": 0.7987432398652949,
|
| 758 |
+
"eval_stsb_spearman": 0.8460476372472872,
|
| 759 |
+
"step": 2575
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.76,
|
| 763 |
+
"eval_avg_sts": 0.8229151972681052,
|
| 764 |
+
"eval_sickr_spearman": 0.7992985754601224,
|
| 765 |
+
"eval_stsb_spearman": 0.8465318190760882,
|
| 766 |
+
"step": 2600
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 5.82,
|
| 770 |
+
"eval_avg_sts": 0.8227679691163096,
|
| 771 |
+
"eval_sickr_spearman": 0.7989778237647187,
|
| 772 |
+
"eval_stsb_spearman": 0.8465581144679004,
|
| 773 |
+
"step": 2625
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 5.88,
|
| 777 |
+
"eval_avg_sts": 0.8231044151175362,
|
| 778 |
+
"eval_sickr_spearman": 0.7993373845900845,
|
| 779 |
+
"eval_stsb_spearman": 0.8468714456449877,
|
| 780 |
+
"step": 2650
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 5.93,
|
| 784 |
+
"eval_avg_sts": 0.8230968701740264,
|
| 785 |
+
"eval_sickr_spearman": 0.7993484797745166,
|
| 786 |
+
"eval_stsb_spearman": 0.8468452605735363,
|
| 787 |
+
"step": 2675
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 5.99,
|
| 791 |
+
"eval_avg_sts": 0.8230334553806065,
|
| 792 |
+
"eval_sickr_spearman": 0.7992910345771966,
|
| 793 |
+
"eval_stsb_spearman": 0.8467758761840164,
|
| 794 |
+
"step": 2700
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 6.0,
|
| 798 |
+
"step": 2706,
|
| 799 |
+
"train_runtime": 3739.6542,
|
| 800 |
+
"train_samples_per_second": 0.724
|
| 801 |
+
}
|
| 802 |
+
],
|
| 803 |
+
"max_steps": 2706,
|
| 804 |
+
"num_train_epochs": 6,
|
| 805 |
+
"total_flos": 212939896792195584,
|
| 806 |
+
"trial_name": null,
|
| 807 |
+
"trial_params": null
|
| 808 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21f4dafcf83d4a4c8f881c6ba7bacc09924e13edc076cd101214b5e873ed3573
|
| 3 |
+
size 2552
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|