Tianyu Gao
commited on
Commit
·
af2163e
1
Parent(s):
3e6465f
init
Browse files- config.json +24 -0
- eval_results.txt +14 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +1072 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "result/bert-large-uncased-bs512-lr1e-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForCL"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.2.1",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
eval_CR = 91.05
|
| 3 |
+
eval_MPQA = 89.6
|
| 4 |
+
eval_MR = 84.85
|
| 5 |
+
eval_MRPC = 75.98
|
| 6 |
+
eval_SICKEntailment = 83.8
|
| 7 |
+
eval_SST2 = 89.91
|
| 8 |
+
eval_SST5 = 48.77
|
| 9 |
+
eval_SUBJ = 95.52
|
| 10 |
+
eval_TREC = 82.46
|
| 11 |
+
eval_avg_sts = 0.8477483274295515
|
| 12 |
+
eval_avg_transfer = 82.43777777777777
|
| 13 |
+
eval_sickr_spearman = 0.8258941648240284
|
| 14 |
+
eval_stsb_spearman = 0.8696024900350746
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a60e2e1f8cfc51df2931886d39c9a7b5ef39f8ca04fb2a21eeb2d5d1d6e541b
|
| 3 |
+
size 2681374404
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2fd679c1ceea7fceae6f8faa2cfdd02c985b85d2815c2d6d8fc99b880da13a9
|
| 3 |
+
size 1340700103
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb6a0f6bef3bcdf9b762cffc006b4f5e91c0aeb7f43e07d7f187706c7dcbfa5d
|
| 3 |
+
size 623
|
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, "name_or_path": "bert-large-uncased"}
|
train_results.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
epoch = 3.0
|
| 2 |
+
train_runtime = 1994.4448
|
| 3 |
+
train_samples_per_second = 0.811
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1072 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8696024900350746,
|
| 3 |
+
"best_model_checkpoint": "result/bert-large-uncased-bs512-lr1e-5",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1617,
|
| 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 |
+
"learning_rate": 9.938157081014226e-06,
|
| 13 |
+
"loss": 5.2117,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 9.876314162028449e-06,
|
| 19 |
+
"loss": 2.7303,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 9.814471243042673e-06,
|
| 25 |
+
"loss": 1.8126,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 9.752628324056896e-06,
|
| 31 |
+
"loss": 1.482,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09,
|
| 36 |
+
"learning_rate": 9.690785405071121e-06,
|
| 37 |
+
"loss": 1.3545,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 9.628942486085344e-06,
|
| 43 |
+
"loss": 1.2558,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"learning_rate": 9.567099567099569e-06,
|
| 49 |
+
"loss": 1.1597,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
+
"learning_rate": 9.505256648113792e-06,
|
| 55 |
+
"loss": 1.0949,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17,
|
| 60 |
+
"learning_rate": 9.443413729128017e-06,
|
| 61 |
+
"loss": 1.1096,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"learning_rate": 9.38157081014224e-06,
|
| 67 |
+
"loss": 1.0072,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 9.319727891156464e-06,
|
| 73 |
+
"loss": 1.0697,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.22,
|
| 78 |
+
"learning_rate": 9.257884972170687e-06,
|
| 79 |
+
"loss": 1.0235,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.23,
|
| 84 |
+
"eval_avg_sts": 0.835670676836703,
|
| 85 |
+
"eval_sickr_spearman": 0.8174356477052697,
|
| 86 |
+
"eval_stsb_spearman": 0.8539057059681365,
|
| 87 |
+
"step": 125
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"learning_rate": 9.196042053184912e-06,
|
| 92 |
+
"loss": 1.0064,
|
| 93 |
+
"step": 130
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.26,
|
| 97 |
+
"learning_rate": 9.134199134199135e-06,
|
| 98 |
+
"loss": 0.9805,
|
| 99 |
+
"step": 140
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.28,
|
| 103 |
+
"learning_rate": 9.07235621521336e-06,
|
| 104 |
+
"loss": 0.9327,
|
| 105 |
+
"step": 150
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.3,
|
| 109 |
+
"learning_rate": 9.010513296227583e-06,
|
| 110 |
+
"loss": 0.9818,
|
| 111 |
+
"step": 160
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.32,
|
| 115 |
+
"learning_rate": 8.948670377241808e-06,
|
| 116 |
+
"loss": 0.9391,
|
| 117 |
+
"step": 170
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.33,
|
| 121 |
+
"learning_rate": 8.88682745825603e-06,
|
| 122 |
+
"loss": 0.9709,
|
| 123 |
+
"step": 180
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.35,
|
| 127 |
+
"learning_rate": 8.824984539270254e-06,
|
| 128 |
+
"loss": 0.8995,
|
| 129 |
+
"step": 190
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.37,
|
| 133 |
+
"learning_rate": 8.763141620284478e-06,
|
| 134 |
+
"loss": 0.9076,
|
| 135 |
+
"step": 200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.39,
|
| 139 |
+
"learning_rate": 8.701298701298701e-06,
|
| 140 |
+
"loss": 0.9185,
|
| 141 |
+
"step": 210
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.41,
|
| 145 |
+
"learning_rate": 8.639455782312926e-06,
|
| 146 |
+
"loss": 0.9286,
|
| 147 |
+
"step": 220
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.43,
|
| 151 |
+
"learning_rate": 8.577612863327149e-06,
|
| 152 |
+
"loss": 0.9184,
|
| 153 |
+
"step": 230
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.45,
|
| 157 |
+
"learning_rate": 8.515769944341374e-06,
|
| 158 |
+
"loss": 0.9211,
|
| 159 |
+
"step": 240
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.46,
|
| 163 |
+
"learning_rate": 8.453927025355597e-06,
|
| 164 |
+
"loss": 0.9251,
|
| 165 |
+
"step": 250
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.46,
|
| 169 |
+
"eval_avg_sts": 0.8411396152471846,
|
| 170 |
+
"eval_sickr_spearman": 0.8226138807513125,
|
| 171 |
+
"eval_stsb_spearman": 0.8596653497430569,
|
| 172 |
+
"step": 250
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.48,
|
| 176 |
+
"learning_rate": 8.392084106369822e-06,
|
| 177 |
+
"loss": 0.8951,
|
| 178 |
+
"step": 260
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5,
|
| 182 |
+
"learning_rate": 8.330241187384045e-06,
|
| 183 |
+
"loss": 0.8781,
|
| 184 |
+
"step": 270
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.52,
|
| 188 |
+
"learning_rate": 8.26839826839827e-06,
|
| 189 |
+
"loss": 0.8797,
|
| 190 |
+
"step": 280
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.54,
|
| 194 |
+
"learning_rate": 8.206555349412492e-06,
|
| 195 |
+
"loss": 0.8636,
|
| 196 |
+
"step": 290
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.56,
|
| 200 |
+
"learning_rate": 8.144712430426717e-06,
|
| 201 |
+
"loss": 0.8805,
|
| 202 |
+
"step": 300
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.58,
|
| 206 |
+
"learning_rate": 8.08286951144094e-06,
|
| 207 |
+
"loss": 0.8727,
|
| 208 |
+
"step": 310
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.59,
|
| 212 |
+
"learning_rate": 8.021026592455165e-06,
|
| 213 |
+
"loss": 0.8553,
|
| 214 |
+
"step": 320
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.61,
|
| 218 |
+
"learning_rate": 7.959183673469388e-06,
|
| 219 |
+
"loss": 0.8563,
|
| 220 |
+
"step": 330
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.63,
|
| 224 |
+
"learning_rate": 7.897340754483613e-06,
|
| 225 |
+
"loss": 0.8791,
|
| 226 |
+
"step": 340
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.65,
|
| 230 |
+
"learning_rate": 7.835497835497836e-06,
|
| 231 |
+
"loss": 0.8768,
|
| 232 |
+
"step": 350
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.67,
|
| 236 |
+
"learning_rate": 7.77365491651206e-06,
|
| 237 |
+
"loss": 0.9132,
|
| 238 |
+
"step": 360
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.69,
|
| 242 |
+
"learning_rate": 7.711811997526283e-06,
|
| 243 |
+
"loss": 0.8531,
|
| 244 |
+
"step": 370
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.7,
|
| 248 |
+
"eval_avg_sts": 0.8443297683636638,
|
| 249 |
+
"eval_sickr_spearman": 0.8256352291561755,
|
| 250 |
+
"eval_stsb_spearman": 0.8630243075711521,
|
| 251 |
+
"step": 375
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.71,
|
| 255 |
+
"learning_rate": 7.649969078540508e-06,
|
| 256 |
+
"loss": 0.8604,
|
| 257 |
+
"step": 380
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.72,
|
| 261 |
+
"learning_rate": 7.588126159554732e-06,
|
| 262 |
+
"loss": 0.8272,
|
| 263 |
+
"step": 390
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.74,
|
| 267 |
+
"learning_rate": 7.526283240568956e-06,
|
| 268 |
+
"loss": 0.8352,
|
| 269 |
+
"step": 400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.76,
|
| 273 |
+
"learning_rate": 7.46444032158318e-06,
|
| 274 |
+
"loss": 0.8819,
|
| 275 |
+
"step": 410
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.78,
|
| 279 |
+
"learning_rate": 7.402597402597404e-06,
|
| 280 |
+
"loss": 0.8073,
|
| 281 |
+
"step": 420
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.8,
|
| 285 |
+
"learning_rate": 7.3407544836116275e-06,
|
| 286 |
+
"loss": 0.8457,
|
| 287 |
+
"step": 430
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.82,
|
| 291 |
+
"learning_rate": 7.278911564625851e-06,
|
| 292 |
+
"loss": 0.8393,
|
| 293 |
+
"step": 440
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.83,
|
| 297 |
+
"learning_rate": 7.217068645640075e-06,
|
| 298 |
+
"loss": 0.81,
|
| 299 |
+
"step": 450
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.85,
|
| 303 |
+
"learning_rate": 7.155225726654299e-06,
|
| 304 |
+
"loss": 0.8133,
|
| 305 |
+
"step": 460
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.87,
|
| 309 |
+
"learning_rate": 7.093382807668523e-06,
|
| 310 |
+
"loss": 0.8193,
|
| 311 |
+
"step": 470
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.89,
|
| 315 |
+
"learning_rate": 7.031539888682747e-06,
|
| 316 |
+
"loss": 0.7912,
|
| 317 |
+
"step": 480
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.91,
|
| 321 |
+
"learning_rate": 6.969696969696971e-06,
|
| 322 |
+
"loss": 0.7821,
|
| 323 |
+
"step": 490
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.93,
|
| 327 |
+
"learning_rate": 6.907854050711195e-06,
|
| 328 |
+
"loss": 0.7864,
|
| 329 |
+
"step": 500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.93,
|
| 333 |
+
"eval_avg_sts": 0.8462257647791973,
|
| 334 |
+
"eval_sickr_spearman": 0.8268360547232299,
|
| 335 |
+
"eval_stsb_spearman": 0.8656154748351649,
|
| 336 |
+
"step": 500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.95,
|
| 340 |
+
"learning_rate": 6.8460111317254185e-06,
|
| 341 |
+
"loss": 0.8478,
|
| 342 |
+
"step": 510
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.96,
|
| 346 |
+
"learning_rate": 6.7841682127396415e-06,
|
| 347 |
+
"loss": 0.7763,
|
| 348 |
+
"step": 520
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.98,
|
| 352 |
+
"learning_rate": 6.722325293753865e-06,
|
| 353 |
+
"loss": 0.8213,
|
| 354 |
+
"step": 530
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0,
|
| 358 |
+
"learning_rate": 6.660482374768089e-06,
|
| 359 |
+
"loss": 0.7716,
|
| 360 |
+
"step": 540
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.02,
|
| 364 |
+
"learning_rate": 6.598639455782313e-06,
|
| 365 |
+
"loss": 0.7478,
|
| 366 |
+
"step": 550
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.04,
|
| 370 |
+
"learning_rate": 6.536796536796537e-06,
|
| 371 |
+
"loss": 0.7475,
|
| 372 |
+
"step": 560
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.06,
|
| 376 |
+
"learning_rate": 6.474953617810761e-06,
|
| 377 |
+
"loss": 0.7442,
|
| 378 |
+
"step": 570
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.08,
|
| 382 |
+
"learning_rate": 6.413110698824985e-06,
|
| 383 |
+
"loss": 0.7604,
|
| 384 |
+
"step": 580
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.09,
|
| 388 |
+
"learning_rate": 6.351267779839209e-06,
|
| 389 |
+
"loss": 0.742,
|
| 390 |
+
"step": 590
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.11,
|
| 394 |
+
"learning_rate": 6.2894248608534325e-06,
|
| 395 |
+
"loss": 0.7343,
|
| 396 |
+
"step": 600
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.13,
|
| 400 |
+
"learning_rate": 6.227581941867656e-06,
|
| 401 |
+
"loss": 0.734,
|
| 402 |
+
"step": 610
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.15,
|
| 406 |
+
"learning_rate": 6.16573902288188e-06,
|
| 407 |
+
"loss": 0.7441,
|
| 408 |
+
"step": 620
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.16,
|
| 412 |
+
"eval_avg_sts": 0.8465997739356157,
|
| 413 |
+
"eval_sickr_spearman": 0.8266303855468717,
|
| 414 |
+
"eval_stsb_spearman": 0.8665691623243595,
|
| 415 |
+
"step": 625
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.17,
|
| 419 |
+
"learning_rate": 6.103896103896104e-06,
|
| 420 |
+
"loss": 0.7822,
|
| 421 |
+
"step": 630
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.19,
|
| 425 |
+
"learning_rate": 6.042053184910328e-06,
|
| 426 |
+
"loss": 0.7358,
|
| 427 |
+
"step": 640
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.21,
|
| 431 |
+
"learning_rate": 5.980210265924552e-06,
|
| 432 |
+
"loss": 0.749,
|
| 433 |
+
"step": 650
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.22,
|
| 437 |
+
"learning_rate": 5.918367346938776e-06,
|
| 438 |
+
"loss": 0.7475,
|
| 439 |
+
"step": 660
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.24,
|
| 443 |
+
"learning_rate": 5.856524427953e-06,
|
| 444 |
+
"loss": 0.7897,
|
| 445 |
+
"step": 670
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.26,
|
| 449 |
+
"learning_rate": 5.7946815089672236e-06,
|
| 450 |
+
"loss": 0.7362,
|
| 451 |
+
"step": 680
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.28,
|
| 455 |
+
"learning_rate": 5.7328385899814474e-06,
|
| 456 |
+
"loss": 0.7563,
|
| 457 |
+
"step": 690
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.3,
|
| 461 |
+
"learning_rate": 5.670995670995671e-06,
|
| 462 |
+
"loss": 0.7491,
|
| 463 |
+
"step": 700
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.32,
|
| 467 |
+
"learning_rate": 5.609152752009895e-06,
|
| 468 |
+
"loss": 0.7776,
|
| 469 |
+
"step": 710
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.34,
|
| 473 |
+
"learning_rate": 5.547309833024119e-06,
|
| 474 |
+
"loss": 0.7346,
|
| 475 |
+
"step": 720
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.35,
|
| 479 |
+
"learning_rate": 5.485466914038343e-06,
|
| 480 |
+
"loss": 0.737,
|
| 481 |
+
"step": 730
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.37,
|
| 485 |
+
"learning_rate": 5.423623995052567e-06,
|
| 486 |
+
"loss": 0.7341,
|
| 487 |
+
"step": 740
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.39,
|
| 491 |
+
"learning_rate": 5.361781076066791e-06,
|
| 492 |
+
"loss": 0.7293,
|
| 493 |
+
"step": 750
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.39,
|
| 497 |
+
"eval_avg_sts": 0.8490029126462879,
|
| 498 |
+
"eval_sickr_spearman": 0.8293255067107672,
|
| 499 |
+
"eval_stsb_spearman": 0.8686803185818085,
|
| 500 |
+
"step": 750
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.41,
|
| 504 |
+
"learning_rate": 5.2999381570810146e-06,
|
| 505 |
+
"loss": 0.7347,
|
| 506 |
+
"step": 760
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.43,
|
| 510 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 511 |
+
"loss": 0.742,
|
| 512 |
+
"step": 770
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.45,
|
| 516 |
+
"learning_rate": 5.176252319109462e-06,
|
| 517 |
+
"loss": 0.7423,
|
| 518 |
+
"step": 780
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.47,
|
| 522 |
+
"learning_rate": 5.114409400123686e-06,
|
| 523 |
+
"loss": 0.7141,
|
| 524 |
+
"step": 790
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.48,
|
| 528 |
+
"learning_rate": 5.05256648113791e-06,
|
| 529 |
+
"loss": 0.75,
|
| 530 |
+
"step": 800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.5,
|
| 534 |
+
"learning_rate": 4.990723562152134e-06,
|
| 535 |
+
"loss": 0.7373,
|
| 536 |
+
"step": 810
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.52,
|
| 540 |
+
"learning_rate": 4.928880643166358e-06,
|
| 541 |
+
"loss": 0.7547,
|
| 542 |
+
"step": 820
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.54,
|
| 546 |
+
"learning_rate": 4.867037724180582e-06,
|
| 547 |
+
"loss": 0.7347,
|
| 548 |
+
"step": 830
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.56,
|
| 552 |
+
"learning_rate": 4.805194805194806e-06,
|
| 553 |
+
"loss": 0.7323,
|
| 554 |
+
"step": 840
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.58,
|
| 558 |
+
"learning_rate": 4.7433518862090295e-06,
|
| 559 |
+
"loss": 0.762,
|
| 560 |
+
"step": 850
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.6,
|
| 564 |
+
"learning_rate": 4.681508967223253e-06,
|
| 565 |
+
"loss": 0.763,
|
| 566 |
+
"step": 860
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.61,
|
| 570 |
+
"learning_rate": 4.619666048237477e-06,
|
| 571 |
+
"loss": 0.7183,
|
| 572 |
+
"step": 870
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.62,
|
| 576 |
+
"eval_avg_sts": 0.8478878233181263,
|
| 577 |
+
"eval_sickr_spearman": 0.8271554615477934,
|
| 578 |
+
"eval_stsb_spearman": 0.8686201850884592,
|
| 579 |
+
"step": 875
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.63,
|
| 583 |
+
"learning_rate": 4.557823129251701e-06,
|
| 584 |
+
"loss": 0.7052,
|
| 585 |
+
"step": 880
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.65,
|
| 589 |
+
"learning_rate": 4.495980210265925e-06,
|
| 590 |
+
"loss": 0.7586,
|
| 591 |
+
"step": 890
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.67,
|
| 595 |
+
"learning_rate": 4.434137291280149e-06,
|
| 596 |
+
"loss": 0.7303,
|
| 597 |
+
"step": 900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.69,
|
| 601 |
+
"learning_rate": 4.372294372294373e-06,
|
| 602 |
+
"loss": 0.711,
|
| 603 |
+
"step": 910
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.71,
|
| 607 |
+
"learning_rate": 4.310451453308597e-06,
|
| 608 |
+
"loss": 0.7505,
|
| 609 |
+
"step": 920
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.73,
|
| 613 |
+
"learning_rate": 4.2486085343228205e-06,
|
| 614 |
+
"loss": 0.7287,
|
| 615 |
+
"step": 930
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.74,
|
| 619 |
+
"learning_rate": 4.186765615337044e-06,
|
| 620 |
+
"loss": 0.7288,
|
| 621 |
+
"step": 940
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.76,
|
| 625 |
+
"learning_rate": 4.124922696351268e-06,
|
| 626 |
+
"loss": 0.7317,
|
| 627 |
+
"step": 950
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.78,
|
| 631 |
+
"learning_rate": 4.063079777365492e-06,
|
| 632 |
+
"loss": 0.7456,
|
| 633 |
+
"step": 960
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.8,
|
| 637 |
+
"learning_rate": 4.001236858379716e-06,
|
| 638 |
+
"loss": 0.7247,
|
| 639 |
+
"step": 970
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.82,
|
| 643 |
+
"learning_rate": 3.93939393939394e-06,
|
| 644 |
+
"loss": 0.7423,
|
| 645 |
+
"step": 980
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.84,
|
| 649 |
+
"learning_rate": 3.877551020408164e-06,
|
| 650 |
+
"loss": 0.7257,
|
| 651 |
+
"step": 990
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.86,
|
| 655 |
+
"learning_rate": 3.815708101422388e-06,
|
| 656 |
+
"loss": 0.7655,
|
| 657 |
+
"step": 1000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.86,
|
| 661 |
+
"eval_avg_sts": 0.8485790233693684,
|
| 662 |
+
"eval_sickr_spearman": 0.8282474486389888,
|
| 663 |
+
"eval_stsb_spearman": 0.868910598099748,
|
| 664 |
+
"step": 1000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.87,
|
| 668 |
+
"learning_rate": 3.753865182436611e-06,
|
| 669 |
+
"loss": 0.6967,
|
| 670 |
+
"step": 1010
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.89,
|
| 674 |
+
"learning_rate": 3.6920222634508353e-06,
|
| 675 |
+
"loss": 0.6964,
|
| 676 |
+
"step": 1020
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.91,
|
| 680 |
+
"learning_rate": 3.6301793444650592e-06,
|
| 681 |
+
"loss": 0.6989,
|
| 682 |
+
"step": 1030
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.93,
|
| 686 |
+
"learning_rate": 3.568336425479283e-06,
|
| 687 |
+
"loss": 0.7278,
|
| 688 |
+
"step": 1040
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.95,
|
| 692 |
+
"learning_rate": 3.506493506493507e-06,
|
| 693 |
+
"loss": 0.7235,
|
| 694 |
+
"step": 1050
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.97,
|
| 698 |
+
"learning_rate": 3.444650587507731e-06,
|
| 699 |
+
"loss": 0.7041,
|
| 700 |
+
"step": 1060
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.99,
|
| 704 |
+
"learning_rate": 3.3828076685219547e-06,
|
| 705 |
+
"loss": 0.7118,
|
| 706 |
+
"step": 1070
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.0,
|
| 710 |
+
"learning_rate": 3.3209647495361786e-06,
|
| 711 |
+
"loss": 0.6951,
|
| 712 |
+
"step": 1080
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.02,
|
| 716 |
+
"learning_rate": 3.2591218305504025e-06,
|
| 717 |
+
"loss": 0.6957,
|
| 718 |
+
"step": 1090
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.04,
|
| 722 |
+
"learning_rate": 3.1972789115646264e-06,
|
| 723 |
+
"loss": 0.7068,
|
| 724 |
+
"step": 1100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.06,
|
| 728 |
+
"learning_rate": 3.1354359925788502e-06,
|
| 729 |
+
"loss": 0.6662,
|
| 730 |
+
"step": 1110
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.08,
|
| 734 |
+
"learning_rate": 3.0735930735930737e-06,
|
| 735 |
+
"loss": 0.7002,
|
| 736 |
+
"step": 1120
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.09,
|
| 740 |
+
"eval_avg_sts": 0.847001402508377,
|
| 741 |
+
"eval_sickr_spearman": 0.8256772563699338,
|
| 742 |
+
"eval_stsb_spearman": 0.86832554864682,
|
| 743 |
+
"step": 1125
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.1,
|
| 747 |
+
"learning_rate": 3.0117501546072976e-06,
|
| 748 |
+
"loss": 0.6668,
|
| 749 |
+
"step": 1130
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 2.12,
|
| 753 |
+
"learning_rate": 2.9499072356215214e-06,
|
| 754 |
+
"loss": 0.695,
|
| 755 |
+
"step": 1140
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.13,
|
| 759 |
+
"learning_rate": 2.8880643166357453e-06,
|
| 760 |
+
"loss": 0.718,
|
| 761 |
+
"step": 1150
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.15,
|
| 765 |
+
"learning_rate": 2.826221397649969e-06,
|
| 766 |
+
"loss": 0.6953,
|
| 767 |
+
"step": 1160
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.17,
|
| 771 |
+
"learning_rate": 2.764378478664193e-06,
|
| 772 |
+
"loss": 0.6716,
|
| 773 |
+
"step": 1170
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.19,
|
| 777 |
+
"learning_rate": 2.702535559678417e-06,
|
| 778 |
+
"loss": 0.6765,
|
| 779 |
+
"step": 1180
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.21,
|
| 783 |
+
"learning_rate": 2.640692640692641e-06,
|
| 784 |
+
"loss": 0.6645,
|
| 785 |
+
"step": 1190
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.23,
|
| 789 |
+
"learning_rate": 2.5788497217068647e-06,
|
| 790 |
+
"loss": 0.6946,
|
| 791 |
+
"step": 1200
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.24,
|
| 795 |
+
"learning_rate": 2.5170068027210886e-06,
|
| 796 |
+
"loss": 0.6971,
|
| 797 |
+
"step": 1210
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.26,
|
| 801 |
+
"learning_rate": 2.4551638837353125e-06,
|
| 802 |
+
"loss": 0.7074,
|
| 803 |
+
"step": 1220
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.28,
|
| 807 |
+
"learning_rate": 2.3933209647495363e-06,
|
| 808 |
+
"loss": 0.6894,
|
| 809 |
+
"step": 1230
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.3,
|
| 813 |
+
"learning_rate": 2.33147804576376e-06,
|
| 814 |
+
"loss": 0.6821,
|
| 815 |
+
"step": 1240
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.32,
|
| 819 |
+
"learning_rate": 2.269635126777984e-06,
|
| 820 |
+
"loss": 0.6948,
|
| 821 |
+
"step": 1250
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.32,
|
| 825 |
+
"eval_avg_sts": 0.8472029429037058,
|
| 826 |
+
"eval_sickr_spearman": 0.8261643397696178,
|
| 827 |
+
"eval_stsb_spearman": 0.8682415460377939,
|
| 828 |
+
"step": 1250
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.34,
|
| 832 |
+
"learning_rate": 2.207792207792208e-06,
|
| 833 |
+
"loss": 0.7039,
|
| 834 |
+
"step": 1260
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.36,
|
| 838 |
+
"learning_rate": 2.145949288806432e-06,
|
| 839 |
+
"loss": 0.6647,
|
| 840 |
+
"step": 1270
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.37,
|
| 844 |
+
"learning_rate": 2.0841063698206557e-06,
|
| 845 |
+
"loss": 0.6775,
|
| 846 |
+
"step": 1280
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.39,
|
| 850 |
+
"learning_rate": 2.0222634508348796e-06,
|
| 851 |
+
"loss": 0.6639,
|
| 852 |
+
"step": 1290
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.41,
|
| 856 |
+
"learning_rate": 1.9604205318491035e-06,
|
| 857 |
+
"loss": 0.6936,
|
| 858 |
+
"step": 1300
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.43,
|
| 862 |
+
"learning_rate": 1.8985776128633273e-06,
|
| 863 |
+
"loss": 0.6936,
|
| 864 |
+
"step": 1310
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.45,
|
| 868 |
+
"learning_rate": 1.8367346938775512e-06,
|
| 869 |
+
"loss": 0.6833,
|
| 870 |
+
"step": 1320
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.47,
|
| 874 |
+
"learning_rate": 1.774891774891775e-06,
|
| 875 |
+
"loss": 0.6785,
|
| 876 |
+
"step": 1330
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.49,
|
| 880 |
+
"learning_rate": 1.7130488559059988e-06,
|
| 881 |
+
"loss": 0.6837,
|
| 882 |
+
"step": 1340
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.5,
|
| 886 |
+
"learning_rate": 1.6512059369202226e-06,
|
| 887 |
+
"loss": 0.6743,
|
| 888 |
+
"step": 1350
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.52,
|
| 892 |
+
"learning_rate": 1.5893630179344465e-06,
|
| 893 |
+
"loss": 0.6912,
|
| 894 |
+
"step": 1360
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.54,
|
| 898 |
+
"learning_rate": 1.5275200989486704e-06,
|
| 899 |
+
"loss": 0.6798,
|
| 900 |
+
"step": 1370
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.55,
|
| 904 |
+
"eval_avg_sts": 0.8477483274295515,
|
| 905 |
+
"eval_sickr_spearman": 0.8258941648240284,
|
| 906 |
+
"eval_stsb_spearman": 0.8696024900350746,
|
| 907 |
+
"step": 1375
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.56,
|
| 911 |
+
"learning_rate": 1.4656771799628945e-06,
|
| 912 |
+
"loss": 0.697,
|
| 913 |
+
"step": 1380
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.58,
|
| 917 |
+
"learning_rate": 1.4038342609771183e-06,
|
| 918 |
+
"loss": 0.6815,
|
| 919 |
+
"step": 1390
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.6,
|
| 923 |
+
"learning_rate": 1.3419913419913422e-06,
|
| 924 |
+
"loss": 0.6678,
|
| 925 |
+
"step": 1400
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 2.62,
|
| 929 |
+
"learning_rate": 1.280148423005566e-06,
|
| 930 |
+
"loss": 0.6709,
|
| 931 |
+
"step": 1410
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 2.63,
|
| 935 |
+
"learning_rate": 1.2183055040197898e-06,
|
| 936 |
+
"loss": 0.661,
|
| 937 |
+
"step": 1420
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 2.65,
|
| 941 |
+
"learning_rate": 1.1564625850340136e-06,
|
| 942 |
+
"loss": 0.6829,
|
| 943 |
+
"step": 1430
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.67,
|
| 947 |
+
"learning_rate": 1.0946196660482377e-06,
|
| 948 |
+
"loss": 0.6987,
|
| 949 |
+
"step": 1440
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 2.69,
|
| 953 |
+
"learning_rate": 1.0327767470624614e-06,
|
| 954 |
+
"loss": 0.696,
|
| 955 |
+
"step": 1450
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.71,
|
| 959 |
+
"learning_rate": 9.709338280766853e-07,
|
| 960 |
+
"loss": 0.7002,
|
| 961 |
+
"step": 1460
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.73,
|
| 965 |
+
"learning_rate": 9.090909090909091e-07,
|
| 966 |
+
"loss": 0.709,
|
| 967 |
+
"step": 1470
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.75,
|
| 971 |
+
"learning_rate": 8.472479901051331e-07,
|
| 972 |
+
"loss": 0.6794,
|
| 973 |
+
"step": 1480
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 2.76,
|
| 977 |
+
"learning_rate": 7.854050711193569e-07,
|
| 978 |
+
"loss": 0.6784,
|
| 979 |
+
"step": 1490
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 2.78,
|
| 983 |
+
"learning_rate": 7.235621521335808e-07,
|
| 984 |
+
"loss": 0.6644,
|
| 985 |
+
"step": 1500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.78,
|
| 989 |
+
"eval_avg_sts": 0.8478596119891653,
|
| 990 |
+
"eval_sickr_spearman": 0.8263944087455064,
|
| 991 |
+
"eval_stsb_spearman": 0.8693248152328242,
|
| 992 |
+
"step": 1500
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.8,
|
| 996 |
+
"learning_rate": 6.617192331478047e-07,
|
| 997 |
+
"loss": 0.6888,
|
| 998 |
+
"step": 1510
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.82,
|
| 1002 |
+
"learning_rate": 5.998763141620285e-07,
|
| 1003 |
+
"loss": 0.6594,
|
| 1004 |
+
"step": 1520
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.84,
|
| 1008 |
+
"learning_rate": 5.380333951762524e-07,
|
| 1009 |
+
"loss": 0.6909,
|
| 1010 |
+
"step": 1530
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.86,
|
| 1014 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 1015 |
+
"loss": 0.6693,
|
| 1016 |
+
"step": 1540
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.88,
|
| 1020 |
+
"learning_rate": 4.143475572047001e-07,
|
| 1021 |
+
"loss": 0.6671,
|
| 1022 |
+
"step": 1550
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.89,
|
| 1026 |
+
"learning_rate": 3.5250463821892393e-07,
|
| 1027 |
+
"loss": 0.6589,
|
| 1028 |
+
"step": 1560
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.91,
|
| 1032 |
+
"learning_rate": 2.9066171923314786e-07,
|
| 1033 |
+
"loss": 0.6687,
|
| 1034 |
+
"step": 1570
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.93,
|
| 1038 |
+
"learning_rate": 2.288188002473717e-07,
|
| 1039 |
+
"loss": 0.659,
|
| 1040 |
+
"step": 1580
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.95,
|
| 1044 |
+
"learning_rate": 1.6697588126159556e-07,
|
| 1045 |
+
"loss": 0.6724,
|
| 1046 |
+
"step": 1590
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.97,
|
| 1050 |
+
"learning_rate": 1.0513296227581942e-07,
|
| 1051 |
+
"loss": 0.6762,
|
| 1052 |
+
"step": 1600
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.99,
|
| 1056 |
+
"learning_rate": 4.3290043290043295e-08,
|
| 1057 |
+
"loss": 0.7098,
|
| 1058 |
+
"step": 1610
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.0,
|
| 1062 |
+
"step": 1617,
|
| 1063 |
+
"train_runtime": 1994.4448,
|
| 1064 |
+
"train_samples_per_second": 0.811
|
| 1065 |
+
}
|
| 1066 |
+
],
|
| 1067 |
+
"max_steps": 1617,
|
| 1068 |
+
"num_train_epochs": 3,
|
| 1069 |
+
"total_flos": 160111061011021824,
|
| 1070 |
+
"trial_name": null,
|
| 1071 |
+
"trial_params": null
|
| 1072 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89102fa3a6128cc19f6f105290915e7d4359d37ceecb3c465eecd4f5ca98a945
|
| 3 |
+
size 2159
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|