Upload 10 files
Browse files- config.json +26 -0
- eval_results.txt +12 -0
- merges.txt +0 -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.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/multicse-roberta-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 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 = 3.0
|
| 2 |
+
eval_CR = 91.86
|
| 3 |
+
eval_MPQA = 89.67
|
| 4 |
+
eval_MR = 86.08
|
| 5 |
+
eval_MRPC = 74.75
|
| 6 |
+
eval_SST2 = 90.71
|
| 7 |
+
eval_SUBJ = 93.8
|
| 8 |
+
eval_TREC = 78.12
|
| 9 |
+
eval_avg_sts = 0.8592533976547048
|
| 10 |
+
eval_avg_transfer = 86.42714285714285
|
| 11 |
+
eval_sickr_spearman = 0.8491095173931258
|
| 12 |
+
eval_stsb_spearman = 0.8693972779162836
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7be59a7ab59ab8c1f15a2e8d7d97d18f84956a86369a3c35113750725929b16
|
| 3 |
+
size 1631900994
|
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, "special_tokens_map_file": null, "name_or_path": "/data/lyhe/data/roberta-large"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_runtime = 7654.807
|
| 3 |
+
train_samples_per_second = 0.354
|
trainer_state.json
ADDED
|
@@ -0,0 +1,808 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8592533976547048,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/multicse-roberta-large-uncased",
|
| 4 |
+
"epoch": 3.0,
|
| 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": 0.03,
|
| 12 |
+
"eval_avg_sts": 0.5258570395156345,
|
| 13 |
+
"eval_sickr_spearman": 0.5533369246344159,
|
| 14 |
+
"eval_stsb_spearman": 0.4983771543968531,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"eval_avg_sts": 0.7850148023693055,
|
| 20 |
+
"eval_sickr_spearman": 0.7550652932127213,
|
| 21 |
+
"eval_stsb_spearman": 0.8149643115258898,
|
| 22 |
+
"step": 50
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.08,
|
| 26 |
+
"eval_avg_sts": 0.8230417971117017,
|
| 27 |
+
"eval_sickr_spearman": 0.8039761803358758,
|
| 28 |
+
"eval_stsb_spearman": 0.8421074138875275,
|
| 29 |
+
"step": 75
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.11,
|
| 33 |
+
"eval_avg_sts": 0.8229977066254568,
|
| 34 |
+
"eval_sickr_spearman": 0.8013150171606973,
|
| 35 |
+
"eval_stsb_spearman": 0.8446803960902164,
|
| 36 |
+
"step": 100
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.14,
|
| 40 |
+
"eval_avg_sts": 0.8250867364664243,
|
| 41 |
+
"eval_sickr_spearman": 0.8020941296571249,
|
| 42 |
+
"eval_stsb_spearman": 0.8480793432757237,
|
| 43 |
+
"step": 125
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.17,
|
| 47 |
+
"eval_avg_sts": 0.8343038041059325,
|
| 48 |
+
"eval_sickr_spearman": 0.8130164981863546,
|
| 49 |
+
"eval_stsb_spearman": 0.8555911100255104,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"eval_avg_sts": 0.8341218485661299,
|
| 55 |
+
"eval_sickr_spearman": 0.8137427764712003,
|
| 56 |
+
"eval_stsb_spearman": 0.8545009206610595,
|
| 57 |
+
"step": 175
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.22,
|
| 61 |
+
"eval_avg_sts": 0.8292804411707589,
|
| 62 |
+
"eval_sickr_spearman": 0.8028885640749114,
|
| 63 |
+
"eval_stsb_spearman": 0.8556723182666065,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.25,
|
| 68 |
+
"eval_avg_sts": 0.8343114076624676,
|
| 69 |
+
"eval_sickr_spearman": 0.8119119269465824,
|
| 70 |
+
"eval_stsb_spearman": 0.8567108883783526,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.28,
|
| 75 |
+
"eval_avg_sts": 0.8374413121168582,
|
| 76 |
+
"eval_sickr_spearman": 0.8194021370603487,
|
| 77 |
+
"eval_stsb_spearman": 0.8554804871733678,
|
| 78 |
+
"step": 250
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.3,
|
| 82 |
+
"eval_avg_sts": 0.790030690165741,
|
| 83 |
+
"eval_sickr_spearman": 0.7826885079918957,
|
| 84 |
+
"eval_stsb_spearman": 0.7973728723395863,
|
| 85 |
+
"step": 275
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.33,
|
| 89 |
+
"eval_avg_sts": 0.8296463453278495,
|
| 90 |
+
"eval_sickr_spearman": 0.813207854094484,
|
| 91 |
+
"eval_stsb_spearman": 0.846084836561215,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"eval_avg_sts": 0.8310185376263133,
|
| 97 |
+
"eval_sickr_spearman": 0.81294286650785,
|
| 98 |
+
"eval_stsb_spearman": 0.8490942087447765,
|
| 99 |
+
"step": 325
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.39,
|
| 103 |
+
"eval_avg_sts": 0.8143706216478173,
|
| 104 |
+
"eval_sickr_spearman": 0.8089154106211628,
|
| 105 |
+
"eval_stsb_spearman": 0.8198258326744716,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.42,
|
| 110 |
+
"eval_avg_sts": 0.8350372402041332,
|
| 111 |
+
"eval_sickr_spearman": 0.8196295643256583,
|
| 112 |
+
"eval_stsb_spearman": 0.8504449160826081,
|
| 113 |
+
"step": 375
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.44,
|
| 117 |
+
"eval_avg_sts": 0.8164152692168181,
|
| 118 |
+
"eval_sickr_spearman": 0.7969415932503514,
|
| 119 |
+
"eval_stsb_spearman": 0.8358889451832846,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.47,
|
| 124 |
+
"eval_avg_sts": 0.8336510848982669,
|
| 125 |
+
"eval_sickr_spearman": 0.8124280691626363,
|
| 126 |
+
"eval_stsb_spearman": 0.8548741006338975,
|
| 127 |
+
"step": 425
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.5,
|
| 131 |
+
"eval_avg_sts": 0.8287756211043293,
|
| 132 |
+
"eval_sickr_spearman": 0.8041324735399555,
|
| 133 |
+
"eval_stsb_spearman": 0.8534187686687033,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.53,
|
| 138 |
+
"eval_avg_sts": 0.7419793879287948,
|
| 139 |
+
"eval_sickr_spearman": 0.7170895028606776,
|
| 140 |
+
"eval_stsb_spearman": 0.766869272996912,
|
| 141 |
+
"step": 475
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.55,
|
| 145 |
+
"learning_rate": 8.152254249815226e-06,
|
| 146 |
+
"loss": 0.6723,
|
| 147 |
+
"step": 500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.55,
|
| 151 |
+
"eval_avg_sts": 0.8448102989750537,
|
| 152 |
+
"eval_sickr_spearman": 0.8239814222714584,
|
| 153 |
+
"eval_stsb_spearman": 0.865639175678649,
|
| 154 |
+
"step": 500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.58,
|
| 158 |
+
"eval_avg_sts": 0.8357715679368597,
|
| 159 |
+
"eval_sickr_spearman": 0.8123892120015728,
|
| 160 |
+
"eval_stsb_spearman": 0.8591539238721466,
|
| 161 |
+
"step": 525
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.61,
|
| 165 |
+
"eval_avg_sts": 0.7209666511512107,
|
| 166 |
+
"eval_sickr_spearman": 0.6828403015759127,
|
| 167 |
+
"eval_stsb_spearman": 0.7590930007265089,
|
| 168 |
+
"step": 550
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.64,
|
| 172 |
+
"eval_avg_sts": 0.8322843696635686,
|
| 173 |
+
"eval_sickr_spearman": 0.8107304579134076,
|
| 174 |
+
"eval_stsb_spearman": 0.8538382814137295,
|
| 175 |
+
"step": 575
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.67,
|
| 179 |
+
"eval_avg_sts": 0.8417184990226367,
|
| 180 |
+
"eval_sickr_spearman": 0.8216292912029326,
|
| 181 |
+
"eval_stsb_spearman": 0.8618077068423408,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.69,
|
| 186 |
+
"eval_avg_sts": 0.8001972328140533,
|
| 187 |
+
"eval_sickr_spearman": 0.7744180806663685,
|
| 188 |
+
"eval_stsb_spearman": 0.8259763849617381,
|
| 189 |
+
"step": 625
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.72,
|
| 193 |
+
"eval_avg_sts": 0.8280003805677492,
|
| 194 |
+
"eval_sickr_spearman": 0.8052124048246901,
|
| 195 |
+
"eval_stsb_spearman": 0.8507883563108082,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.75,
|
| 200 |
+
"eval_avg_sts": 0.8502864910727694,
|
| 201 |
+
"eval_sickr_spearman": 0.8340239570845448,
|
| 202 |
+
"eval_stsb_spearman": 0.8665490250609942,
|
| 203 |
+
"step": 675
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.78,
|
| 207 |
+
"eval_avg_sts": 0.8491384622588354,
|
| 208 |
+
"eval_sickr_spearman": 0.8335061337799405,
|
| 209 |
+
"eval_stsb_spearman": 0.8647707907377303,
|
| 210 |
+
"step": 700
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.8,
|
| 214 |
+
"eval_avg_sts": 0.833430245079678,
|
| 215 |
+
"eval_sickr_spearman": 0.8096134946494643,
|
| 216 |
+
"eval_stsb_spearman": 0.8572469955098916,
|
| 217 |
+
"step": 725
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.83,
|
| 221 |
+
"eval_avg_sts": 0.8440579172879747,
|
| 222 |
+
"eval_sickr_spearman": 0.825622452883193,
|
| 223 |
+
"eval_stsb_spearman": 0.8624933816927564,
|
| 224 |
+
"step": 750
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.86,
|
| 228 |
+
"eval_avg_sts": 0.7868824796982673,
|
| 229 |
+
"eval_sickr_spearman": 0.7489995895054065,
|
| 230 |
+
"eval_stsb_spearman": 0.8247653698911281,
|
| 231 |
+
"step": 775
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.89,
|
| 235 |
+
"eval_avg_sts": 0.8339843444164832,
|
| 236 |
+
"eval_sickr_spearman": 0.8106915046901414,
|
| 237 |
+
"eval_stsb_spearman": 0.8572771841428249,
|
| 238 |
+
"step": 800
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.91,
|
| 242 |
+
"eval_avg_sts": 0.8184786625842368,
|
| 243 |
+
"eval_sickr_spearman": 0.7940952221480274,
|
| 244 |
+
"eval_stsb_spearman": 0.8428621030204463,
|
| 245 |
+
"step": 825
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.94,
|
| 249 |
+
"eval_avg_sts": 0.8413785182540383,
|
| 250 |
+
"eval_sickr_spearman": 0.8238849758197707,
|
| 251 |
+
"eval_stsb_spearman": 0.858872060688306,
|
| 252 |
+
"step": 850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.97,
|
| 256 |
+
"eval_avg_sts": 0.8450123523064677,
|
| 257 |
+
"eval_sickr_spearman": 0.8247908904239951,
|
| 258 |
+
"eval_stsb_spearman": 0.8652338141889402,
|
| 259 |
+
"step": 875
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.0,
|
| 263 |
+
"eval_avg_sts": 0.836423550431332,
|
| 264 |
+
"eval_sickr_spearman": 0.8192137110494071,
|
| 265 |
+
"eval_stsb_spearman": 0.8536333898132569,
|
| 266 |
+
"step": 900
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.03,
|
| 270 |
+
"eval_avg_sts": 0.8230741682060118,
|
| 271 |
+
"eval_sickr_spearman": 0.8026094553444544,
|
| 272 |
+
"eval_stsb_spearman": 0.8435388810675691,
|
| 273 |
+
"step": 925
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.05,
|
| 277 |
+
"eval_avg_sts": 0.8500639069789373,
|
| 278 |
+
"eval_sickr_spearman": 0.8328587225636562,
|
| 279 |
+
"eval_stsb_spearman": 0.8672690913942185,
|
| 280 |
+
"step": 950
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.08,
|
| 284 |
+
"eval_avg_sts": 0.8323002280574656,
|
| 285 |
+
"eval_sickr_spearman": 0.8130526656057375,
|
| 286 |
+
"eval_stsb_spearman": 0.8515477905091938,
|
| 287 |
+
"step": 975
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.11,
|
| 291 |
+
"learning_rate": 6.304508499630452e-06,
|
| 292 |
+
"loss": 0.2548,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.11,
|
| 297 |
+
"eval_avg_sts": 0.8239924175524644,
|
| 298 |
+
"eval_sickr_spearman": 0.8011878788351906,
|
| 299 |
+
"eval_stsb_spearman": 0.8467969562697383,
|
| 300 |
+
"step": 1000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.14,
|
| 304 |
+
"eval_avg_sts": 0.8430266753860738,
|
| 305 |
+
"eval_sickr_spearman": 0.8271581993205753,
|
| 306 |
+
"eval_stsb_spearman": 0.8588951514515721,
|
| 307 |
+
"step": 1025
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.16,
|
| 311 |
+
"eval_avg_sts": 0.8592533976547048,
|
| 312 |
+
"eval_sickr_spearman": 0.8491095173931258,
|
| 313 |
+
"eval_stsb_spearman": 0.8693972779162836,
|
| 314 |
+
"step": 1050
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.19,
|
| 318 |
+
"eval_avg_sts": 0.8411301121031662,
|
| 319 |
+
"eval_sickr_spearman": 0.8243206659409158,
|
| 320 |
+
"eval_stsb_spearman": 0.8579395582654168,
|
| 321 |
+
"step": 1075
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.22,
|
| 325 |
+
"eval_avg_sts": 0.847249395072464,
|
| 326 |
+
"eval_sickr_spearman": 0.8336754434125099,
|
| 327 |
+
"eval_stsb_spearman": 0.8608233467324182,
|
| 328 |
+
"step": 1100
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.25,
|
| 332 |
+
"eval_avg_sts": 0.8526050717559741,
|
| 333 |
+
"eval_sickr_spearman": 0.8367417969594204,
|
| 334 |
+
"eval_stsb_spearman": 0.8684683465525278,
|
| 335 |
+
"step": 1125
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.27,
|
| 339 |
+
"eval_avg_sts": 0.844364830879988,
|
| 340 |
+
"eval_sickr_spearman": 0.8298262309432596,
|
| 341 |
+
"eval_stsb_spearman": 0.8589034308167164,
|
| 342 |
+
"step": 1150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.3,
|
| 346 |
+
"eval_avg_sts": 0.848322685283306,
|
| 347 |
+
"eval_sickr_spearman": 0.8344140656904253,
|
| 348 |
+
"eval_stsb_spearman": 0.8622313048761867,
|
| 349 |
+
"step": 1175
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.33,
|
| 353 |
+
"eval_avg_sts": 0.8556312662617278,
|
| 354 |
+
"eval_sickr_spearman": 0.8397956143888556,
|
| 355 |
+
"eval_stsb_spearman": 0.8714669181346,
|
| 356 |
+
"step": 1200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.36,
|
| 360 |
+
"eval_avg_sts": 0.8410090445747178,
|
| 361 |
+
"eval_sickr_spearman": 0.8271102162502385,
|
| 362 |
+
"eval_stsb_spearman": 0.854907872899197,
|
| 363 |
+
"step": 1225
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.39,
|
| 367 |
+
"eval_avg_sts": 0.8433567077421059,
|
| 368 |
+
"eval_sickr_spearman": 0.8297940981363974,
|
| 369 |
+
"eval_stsb_spearman": 0.8569193173478145,
|
| 370 |
+
"step": 1250
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.41,
|
| 374 |
+
"eval_avg_sts": 0.8482515472422293,
|
| 375 |
+
"eval_sickr_spearman": 0.8282899081326601,
|
| 376 |
+
"eval_stsb_spearman": 0.8682131863517984,
|
| 377 |
+
"step": 1275
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.44,
|
| 381 |
+
"eval_avg_sts": 0.8255461568624773,
|
| 382 |
+
"eval_sickr_spearman": 0.8016815905268729,
|
| 383 |
+
"eval_stsb_spearman": 0.8494107231980819,
|
| 384 |
+
"step": 1300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.47,
|
| 388 |
+
"eval_avg_sts": 0.8414977629623656,
|
| 389 |
+
"eval_sickr_spearman": 0.8257801870203159,
|
| 390 |
+
"eval_stsb_spearman": 0.8572153389044153,
|
| 391 |
+
"step": 1325
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.5,
|
| 395 |
+
"eval_avg_sts": 0.8378396186869672,
|
| 396 |
+
"eval_sickr_spearman": 0.818870768985139,
|
| 397 |
+
"eval_stsb_spearman": 0.8568084683887955,
|
| 398 |
+
"step": 1350
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.52,
|
| 402 |
+
"eval_avg_sts": 0.8388588093044617,
|
| 403 |
+
"eval_sickr_spearman": 0.8194774978585052,
|
| 404 |
+
"eval_stsb_spearman": 0.8582401207504181,
|
| 405 |
+
"step": 1375
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.55,
|
| 409 |
+
"eval_avg_sts": 0.8105082650410843,
|
| 410 |
+
"eval_sickr_spearman": 0.7798514549232508,
|
| 411 |
+
"eval_stsb_spearman": 0.8411650751589178,
|
| 412 |
+
"step": 1400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.58,
|
| 416 |
+
"eval_avg_sts": 0.8317602737815382,
|
| 417 |
+
"eval_sickr_spearman": 0.808493025115116,
|
| 418 |
+
"eval_stsb_spearman": 0.8550275224479604,
|
| 419 |
+
"step": 1425
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.61,
|
| 423 |
+
"eval_avg_sts": 0.8302226748348518,
|
| 424 |
+
"eval_sickr_spearman": 0.8096536486502666,
|
| 425 |
+
"eval_stsb_spearman": 0.8507917010194369,
|
| 426 |
+
"step": 1450
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.64,
|
| 430 |
+
"eval_avg_sts": 0.8389729127479303,
|
| 431 |
+
"eval_sickr_spearman": 0.82068802570805,
|
| 432 |
+
"eval_stsb_spearman": 0.8572577997878106,
|
| 433 |
+
"step": 1475
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.66,
|
| 437 |
+
"learning_rate": 4.456762749445676e-06,
|
| 438 |
+
"loss": 0.2263,
|
| 439 |
+
"step": 1500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.66,
|
| 443 |
+
"eval_avg_sts": 0.8369919843777802,
|
| 444 |
+
"eval_sickr_spearman": 0.8199678954041884,
|
| 445 |
+
"eval_stsb_spearman": 0.8540160733513722,
|
| 446 |
+
"step": 1500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.69,
|
| 450 |
+
"eval_avg_sts": 0.8419013805527449,
|
| 451 |
+
"eval_sickr_spearman": 0.8240405485573288,
|
| 452 |
+
"eval_stsb_spearman": 0.859762212548161,
|
| 453 |
+
"step": 1525
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.72,
|
| 457 |
+
"eval_avg_sts": 0.8480363963137308,
|
| 458 |
+
"eval_sickr_spearman": 0.8348668548836823,
|
| 459 |
+
"eval_stsb_spearman": 0.8612059377437794,
|
| 460 |
+
"step": 1550
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.75,
|
| 464 |
+
"eval_avg_sts": 0.8091657034677889,
|
| 465 |
+
"eval_sickr_spearman": 0.7825481611134937,
|
| 466 |
+
"eval_stsb_spearman": 0.8357832458220842,
|
| 467 |
+
"step": 1575
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.77,
|
| 471 |
+
"eval_avg_sts": 0.8226090989602317,
|
| 472 |
+
"eval_sickr_spearman": 0.8031343872520715,
|
| 473 |
+
"eval_stsb_spearman": 0.8420838106683919,
|
| 474 |
+
"step": 1600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8,
|
| 478 |
+
"eval_avg_sts": 0.8462010311383265,
|
| 479 |
+
"eval_sickr_spearman": 0.8290648419232626,
|
| 480 |
+
"eval_stsb_spearman": 0.8633372203533903,
|
| 481 |
+
"step": 1625
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.83,
|
| 485 |
+
"eval_avg_sts": 0.8425324447977967,
|
| 486 |
+
"eval_sickr_spearman": 0.8293013470667437,
|
| 487 |
+
"eval_stsb_spearman": 0.8557635425288497,
|
| 488 |
+
"step": 1650
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.86,
|
| 492 |
+
"eval_avg_sts": 0.8380198548580302,
|
| 493 |
+
"eval_sickr_spearman": 0.8243921362198557,
|
| 494 |
+
"eval_stsb_spearman": 0.8516475734962046,
|
| 495 |
+
"step": 1675
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.88,
|
| 499 |
+
"eval_avg_sts": 0.8132086349641947,
|
| 500 |
+
"eval_sickr_spearman": 0.7851564900770903,
|
| 501 |
+
"eval_stsb_spearman": 0.8412607798512991,
|
| 502 |
+
"step": 1700
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.91,
|
| 506 |
+
"eval_avg_sts": 0.8097006725652637,
|
| 507 |
+
"eval_sickr_spearman": 0.7851859811733733,
|
| 508 |
+
"eval_stsb_spearman": 0.834215363957154,
|
| 509 |
+
"step": 1725
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.94,
|
| 513 |
+
"eval_avg_sts": 0.8376290282716883,
|
| 514 |
+
"eval_sickr_spearman": 0.8213424974962457,
|
| 515 |
+
"eval_stsb_spearman": 0.8539155590471308,
|
| 516 |
+
"step": 1750
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.97,
|
| 520 |
+
"eval_avg_sts": 0.842835929581756,
|
| 521 |
+
"eval_sickr_spearman": 0.8281722319341366,
|
| 522 |
+
"eval_stsb_spearman": 0.8574996272293754,
|
| 523 |
+
"step": 1775
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.0,
|
| 527 |
+
"eval_avg_sts": 0.8359820146737951,
|
| 528 |
+
"eval_sickr_spearman": 0.8189481951206572,
|
| 529 |
+
"eval_stsb_spearman": 0.8530158342269328,
|
| 530 |
+
"step": 1800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.02,
|
| 534 |
+
"eval_avg_sts": 0.8468289826472446,
|
| 535 |
+
"eval_sickr_spearman": 0.833371886851421,
|
| 536 |
+
"eval_stsb_spearman": 0.8602860784430681,
|
| 537 |
+
"step": 1825
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.05,
|
| 541 |
+
"eval_avg_sts": 0.8338277707857178,
|
| 542 |
+
"eval_sickr_spearman": 0.8164911160954891,
|
| 543 |
+
"eval_stsb_spearman": 0.8511644254759464,
|
| 544 |
+
"step": 1850
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.08,
|
| 548 |
+
"eval_avg_sts": 0.8341757574943203,
|
| 549 |
+
"eval_sickr_spearman": 0.8175209029103222,
|
| 550 |
+
"eval_stsb_spearman": 0.8508306120783183,
|
| 551 |
+
"step": 1875
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.11,
|
| 555 |
+
"eval_avg_sts": 0.8453760865720144,
|
| 556 |
+
"eval_sickr_spearman": 0.8318047761047997,
|
| 557 |
+
"eval_stsb_spearman": 0.8589473970392288,
|
| 558 |
+
"step": 1900
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.13,
|
| 562 |
+
"eval_avg_sts": 0.8316563095078086,
|
| 563 |
+
"eval_sickr_spearman": 0.8132579505332841,
|
| 564 |
+
"eval_stsb_spearman": 0.850054668482333,
|
| 565 |
+
"step": 1925
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.16,
|
| 569 |
+
"eval_avg_sts": 0.8418222098580312,
|
| 570 |
+
"eval_sickr_spearman": 0.825691617669264,
|
| 571 |
+
"eval_stsb_spearman": 0.8579528020467985,
|
| 572 |
+
"step": 1950
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.19,
|
| 576 |
+
"eval_avg_sts": 0.8282466528439865,
|
| 577 |
+
"eval_sickr_spearman": 0.8085680016644609,
|
| 578 |
+
"eval_stsb_spearman": 0.8479253040235121,
|
| 579 |
+
"step": 1975
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.22,
|
| 583 |
+
"learning_rate": 2.609016999260902e-06,
|
| 584 |
+
"loss": 0.2138,
|
| 585 |
+
"step": 2000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.22,
|
| 589 |
+
"eval_avg_sts": 0.8395154203911175,
|
| 590 |
+
"eval_sickr_spearman": 0.8241901654383085,
|
| 591 |
+
"eval_stsb_spearman": 0.8548406753439265,
|
| 592 |
+
"step": 2000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.25,
|
| 596 |
+
"eval_avg_sts": 0.8354243601616307,
|
| 597 |
+
"eval_sickr_spearman": 0.8186561660239136,
|
| 598 |
+
"eval_stsb_spearman": 0.8521925542993478,
|
| 599 |
+
"step": 2025
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.27,
|
| 603 |
+
"eval_avg_sts": 0.8361344462215647,
|
| 604 |
+
"eval_sickr_spearman": 0.8192864781680858,
|
| 605 |
+
"eval_stsb_spearman": 0.8529824142750437,
|
| 606 |
+
"step": 2050
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.3,
|
| 610 |
+
"eval_avg_sts": 0.8303651499407738,
|
| 611 |
+
"eval_sickr_spearman": 0.8091401961758931,
|
| 612 |
+
"eval_stsb_spearman": 0.8515901037056545,
|
| 613 |
+
"step": 2075
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.33,
|
| 617 |
+
"eval_avg_sts": 0.8314677597128309,
|
| 618 |
+
"eval_sickr_spearman": 0.8115453535804066,
|
| 619 |
+
"eval_stsb_spearman": 0.8513901658452553,
|
| 620 |
+
"step": 2100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.36,
|
| 624 |
+
"eval_avg_sts": 0.8406198858453933,
|
| 625 |
+
"eval_sickr_spearman": 0.8232477471969915,
|
| 626 |
+
"eval_stsb_spearman": 0.8579920244937951,
|
| 627 |
+
"step": 2125
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.38,
|
| 631 |
+
"eval_avg_sts": 0.8310127908616497,
|
| 632 |
+
"eval_sickr_spearman": 0.808406521101426,
|
| 633 |
+
"eval_stsb_spearman": 0.8536190606218734,
|
| 634 |
+
"step": 2150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.41,
|
| 638 |
+
"eval_avg_sts": 0.8360186536704766,
|
| 639 |
+
"eval_sickr_spearman": 0.8149144951907831,
|
| 640 |
+
"eval_stsb_spearman": 0.85712281215017,
|
| 641 |
+
"step": 2175
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.44,
|
| 645 |
+
"eval_avg_sts": 0.8310352588949227,
|
| 646 |
+
"eval_sickr_spearman": 0.8092654612884438,
|
| 647 |
+
"eval_stsb_spearman": 0.8528050565014016,
|
| 648 |
+
"step": 2200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.47,
|
| 652 |
+
"eval_avg_sts": 0.820254245514857,
|
| 653 |
+
"eval_sickr_spearman": 0.7949483986028726,
|
| 654 |
+
"eval_stsb_spearman": 0.8455600924268415,
|
| 655 |
+
"step": 2225
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.49,
|
| 659 |
+
"eval_avg_sts": 0.8271707424843158,
|
| 660 |
+
"eval_sickr_spearman": 0.8042670566861851,
|
| 661 |
+
"eval_stsb_spearman": 0.8500744282824465,
|
| 662 |
+
"step": 2250
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.52,
|
| 666 |
+
"eval_avg_sts": 0.831725837948319,
|
| 667 |
+
"eval_sickr_spearman": 0.8097772326742668,
|
| 668 |
+
"eval_stsb_spearman": 0.8536744432223711,
|
| 669 |
+
"step": 2275
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.55,
|
| 673 |
+
"eval_avg_sts": 0.8478084080683095,
|
| 674 |
+
"eval_sickr_spearman": 0.833967952820268,
|
| 675 |
+
"eval_stsb_spearman": 0.8616488633163509,
|
| 676 |
+
"step": 2300
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.58,
|
| 680 |
+
"eval_avg_sts": 0.8417932529667509,
|
| 681 |
+
"eval_sickr_spearman": 0.824586422025173,
|
| 682 |
+
"eval_stsb_spearman": 0.8590000839083288,
|
| 683 |
+
"step": 2325
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.61,
|
| 687 |
+
"eval_avg_sts": 0.8443266422798352,
|
| 688 |
+
"eval_sickr_spearman": 0.8284084008599079,
|
| 689 |
+
"eval_stsb_spearman": 0.8602448836997627,
|
| 690 |
+
"step": 2350
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.63,
|
| 694 |
+
"eval_avg_sts": 0.8414441103010829,
|
| 695 |
+
"eval_sickr_spearman": 0.8235661453684245,
|
| 696 |
+
"eval_stsb_spearman": 0.8593220752337413,
|
| 697 |
+
"step": 2375
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.66,
|
| 701 |
+
"eval_avg_sts": 0.8332215941917105,
|
| 702 |
+
"eval_sickr_spearman": 0.8123268676319063,
|
| 703 |
+
"eval_stsb_spearman": 0.8541163207515148,
|
| 704 |
+
"step": 2400
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.69,
|
| 708 |
+
"eval_avg_sts": 0.8352256220211349,
|
| 709 |
+
"eval_sickr_spearman": 0.8149729490412333,
|
| 710 |
+
"eval_stsb_spearman": 0.8554782950010364,
|
| 711 |
+
"step": 2425
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.72,
|
| 715 |
+
"eval_avg_sts": 0.8367509129954576,
|
| 716 |
+
"eval_sickr_spearman": 0.8170744538224549,
|
| 717 |
+
"eval_stsb_spearman": 0.8564273721684602,
|
| 718 |
+
"step": 2450
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.74,
|
| 722 |
+
"eval_avg_sts": 0.8332216363076352,
|
| 723 |
+
"eval_sickr_spearman": 0.8119204284515368,
|
| 724 |
+
"eval_stsb_spearman": 0.8545228441637336,
|
| 725 |
+
"step": 2475
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.77,
|
| 729 |
+
"learning_rate": 7.612712490761272e-07,
|
| 730 |
+
"loss": 0.2031,
|
| 731 |
+
"step": 2500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.77,
|
| 735 |
+
"eval_avg_sts": 0.8372319946443687,
|
| 736 |
+
"eval_sickr_spearman": 0.8181658645404332,
|
| 737 |
+
"eval_stsb_spearman": 0.8562981247483044,
|
| 738 |
+
"step": 2500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.8,
|
| 742 |
+
"eval_avg_sts": 0.8296643440620797,
|
| 743 |
+
"eval_sickr_spearman": 0.8083195367767216,
|
| 744 |
+
"eval_stsb_spearman": 0.8510091513474377,
|
| 745 |
+
"step": 2525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.83,
|
| 749 |
+
"eval_avg_sts": 0.8263914133784362,
|
| 750 |
+
"eval_sickr_spearman": 0.8030280944245891,
|
| 751 |
+
"eval_stsb_spearman": 0.8497547323322834,
|
| 752 |
+
"step": 2550
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.85,
|
| 756 |
+
"eval_avg_sts": 0.8200950718061857,
|
| 757 |
+
"eval_sickr_spearman": 0.7943617467299074,
|
| 758 |
+
"eval_stsb_spearman": 0.845828396882464,
|
| 759 |
+
"step": 2575
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.88,
|
| 763 |
+
"eval_avg_sts": 0.8200823058439606,
|
| 764 |
+
"eval_sickr_spearman": 0.7944934480100508,
|
| 765 |
+
"eval_stsb_spearman": 0.8456711636778702,
|
| 766 |
+
"step": 2600
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.91,
|
| 770 |
+
"eval_avg_sts": 0.8192258345292275,
|
| 771 |
+
"eval_sickr_spearman": 0.7934071285888249,
|
| 772 |
+
"eval_stsb_spearman": 0.8450445404696301,
|
| 773 |
+
"step": 2625
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.94,
|
| 777 |
+
"eval_avg_sts": 0.824292679030638,
|
| 778 |
+
"eval_sickr_spearman": 0.8000518952550778,
|
| 779 |
+
"eval_stsb_spearman": 0.8485334628061982,
|
| 780 |
+
"step": 2650
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.97,
|
| 784 |
+
"eval_avg_sts": 0.8236712234461467,
|
| 785 |
+
"eval_sickr_spearman": 0.7990280162657215,
|
| 786 |
+
"eval_stsb_spearman": 0.8483144306265721,
|
| 787 |
+
"step": 2675
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.99,
|
| 791 |
+
"eval_avg_sts": 0.8240279287421932,
|
| 792 |
+
"eval_sickr_spearman": 0.7991273445834955,
|
| 793 |
+
"eval_stsb_spearman": 0.8489285129008908,
|
| 794 |
+
"step": 2700
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.0,
|
| 798 |
+
"step": 2706,
|
| 799 |
+
"train_runtime": 7654.807,
|
| 800 |
+
"train_samples_per_second": 0.354
|
| 801 |
+
}
|
| 802 |
+
],
|
| 803 |
+
"max_steps": 2706,
|
| 804 |
+
"num_train_epochs": 3,
|
| 805 |
+
"total_flos": 325226340493098624,
|
| 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 sha256:09d97e009c1be75deb928a0479f6c585962d7fb163ac95daf9f566b26e769c45
|
| 3 |
+
size 2552
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|