Commit
·
86c1bc3
1
Parent(s):
65ae105
from Google Colab
Browse files- config.json +40 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1716 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4,
|
| 27 |
+
"LABEL_5": 5,
|
| 28 |
+
"LABEL_6": 6
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"qa_dropout": 0.1,
|
| 36 |
+
"seq_classif_dropout": 0.2,
|
| 37 |
+
"sinusoidal_pos_embds": false,
|
| 38 |
+
"tie_weights_": true,
|
| 39 |
+
"vocab_size": 30522
|
| 40 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7f5a34470e88f249bc1b8b57234529a087bd84f8f6e37a12ce8e9c8a7609294
|
| 3 |
+
size 6291456
|
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": "distilbert-base-uncased"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1716 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7449912424577604,
|
| 3 |
+
"best_model_checkpoint": "./results/classi_distilbert/checkpoint-137775",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 137775,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.018145527127563055,
|
| 12 |
+
"learning_rate": 4e-05,
|
| 13 |
+
"loss": 0.84686328125,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03629105425512611,
|
| 18 |
+
"learning_rate": 3.9854307047896564e-05,
|
| 19 |
+
"loss": 0.7841121826171875,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05443658138268917,
|
| 24 |
+
"learning_rate": 3.970861409579312e-05,
|
| 25 |
+
"loss": 0.7334760131835938,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07258210851025222,
|
| 30 |
+
"learning_rate": 3.956292114368968e-05,
|
| 31 |
+
"loss": 0.6972730712890625,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.09072763563781527,
|
| 36 |
+
"learning_rate": 3.941722819158623e-05,
|
| 37 |
+
"loss": 0.7338438720703125,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10887316276537834,
|
| 42 |
+
"learning_rate": 3.927153523948279e-05,
|
| 43 |
+
"loss": 0.7204794921875,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12701868989294138,
|
| 48 |
+
"learning_rate": 3.912584228737935e-05,
|
| 49 |
+
"loss": 0.654921630859375,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.14516421702050444,
|
| 54 |
+
"learning_rate": 3.898014933527591e-05,
|
| 55 |
+
"loss": 0.6844443359375,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.1633097441480675,
|
| 60 |
+
"learning_rate": 3.8834456383172466e-05,
|
| 61 |
+
"loss": 0.7079535522460938,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.18145527127563055,
|
| 66 |
+
"learning_rate": 3.8688763431069026e-05,
|
| 67 |
+
"loss": 0.6477606201171875,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.1996007984031936,
|
| 72 |
+
"learning_rate": 3.8543070478965586e-05,
|
| 73 |
+
"loss": 0.6153006591796875,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21774632553075668,
|
| 78 |
+
"learning_rate": 3.839737752686214e-05,
|
| 79 |
+
"loss": 0.6489894409179687,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.23589185265831972,
|
| 84 |
+
"learning_rate": 3.82516845747587e-05,
|
| 85 |
+
"loss": 0.678625244140625,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.25403737978588276,
|
| 90 |
+
"learning_rate": 3.8105991622655254e-05,
|
| 91 |
+
"loss": 0.65478857421875,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.2721829069134458,
|
| 96 |
+
"learning_rate": 3.7960298670551814e-05,
|
| 97 |
+
"loss": 0.63389208984375,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.2903284340410089,
|
| 102 |
+
"learning_rate": 3.7814605718448375e-05,
|
| 103 |
+
"loss": 0.5931556396484375,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.30847396116857195,
|
| 108 |
+
"learning_rate": 3.7668912766344935e-05,
|
| 109 |
+
"loss": 0.5931373291015625,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.326619488296135,
|
| 114 |
+
"learning_rate": 3.752321981424149e-05,
|
| 115 |
+
"loss": 0.570529296875,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.3447650154236981,
|
| 120 |
+
"learning_rate": 3.737752686213805e-05,
|
| 121 |
+
"loss": 1.0059749145507813,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3629105425512611,
|
| 126 |
+
"learning_rate": 3.723183391003461e-05,
|
| 127 |
+
"loss": 0.8932774658203125,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.38105606967882416,
|
| 132 |
+
"learning_rate": 3.708614095793116e-05,
|
| 133 |
+
"loss": 0.9196145629882813,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.3992015968063872,
|
| 138 |
+
"learning_rate": 3.694044800582772e-05,
|
| 139 |
+
"loss": 0.8962069702148437,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.4173471239339503,
|
| 144 |
+
"learning_rate": 3.679475505372428e-05,
|
| 145 |
+
"loss": 0.899446044921875,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.43549265106151336,
|
| 150 |
+
"learning_rate": 3.664906210162084e-05,
|
| 151 |
+
"loss": 0.8438430786132812,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.45363817818907637,
|
| 156 |
+
"learning_rate": 3.650336914951739e-05,
|
| 157 |
+
"loss": 0.8932066040039063,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.47178370531663943,
|
| 162 |
+
"learning_rate": 3.635767619741395e-05,
|
| 163 |
+
"loss": 0.8947886962890625,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.4899292324442025,
|
| 168 |
+
"learning_rate": 3.621198324531051e-05,
|
| 169 |
+
"loss": 0.8659691772460938,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5080747595717655,
|
| 174 |
+
"learning_rate": 3.606629029320707e-05,
|
| 175 |
+
"loss": 0.8590133666992188,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.5262202866993286,
|
| 180 |
+
"learning_rate": 3.592059734110363e-05,
|
| 181 |
+
"loss": 0.826283447265625,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.5443658138268916,
|
| 186 |
+
"learning_rate": 3.5774904389000186e-05,
|
| 187 |
+
"loss": 0.8533541870117187,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.5625113409544548,
|
| 192 |
+
"learning_rate": 3.5629211436896746e-05,
|
| 193 |
+
"loss": 0.8348355102539062,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.5806568680820178,
|
| 198 |
+
"learning_rate": 3.54835184847933e-05,
|
| 199 |
+
"loss": 0.837393310546875,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.5988023952095808,
|
| 204 |
+
"learning_rate": 3.533782553268986e-05,
|
| 205 |
+
"loss": 0.8255460205078125,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6169479223371439,
|
| 210 |
+
"learning_rate": 3.519213258058641e-05,
|
| 211 |
+
"loss": 0.850743896484375,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6350934494647069,
|
| 216 |
+
"learning_rate": 3.5046439628482974e-05,
|
| 217 |
+
"loss": 0.822864501953125,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.65323897659227,
|
| 222 |
+
"learning_rate": 3.4900746676379534e-05,
|
| 223 |
+
"loss": 0.848374267578125,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.671384503719833,
|
| 228 |
+
"learning_rate": 3.4755053724276094e-05,
|
| 229 |
+
"loss": 0.8317371826171875,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.6895300308473962,
|
| 234 |
+
"learning_rate": 3.460936077217265e-05,
|
| 235 |
+
"loss": 0.8403475341796875,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.7076755579749592,
|
| 240 |
+
"learning_rate": 3.446366782006921e-05,
|
| 241 |
+
"loss": 0.8143458862304688,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.7258210851025222,
|
| 246 |
+
"learning_rate": 3.431797486796577e-05,
|
| 247 |
+
"loss": 0.834985595703125,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7439666122300853,
|
| 252 |
+
"learning_rate": 3.417228191586232e-05,
|
| 253 |
+
"loss": 0.80064453125,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7621121393576483,
|
| 258 |
+
"learning_rate": 3.402658896375888e-05,
|
| 259 |
+
"loss": 0.8269353637695313,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.7802576664852114,
|
| 264 |
+
"learning_rate": 3.3880896011655436e-05,
|
| 265 |
+
"loss": 0.8046528930664063,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.7984031936127745,
|
| 270 |
+
"learning_rate": 3.3735203059551996e-05,
|
| 271 |
+
"loss": 0.7941847534179688,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.8165487207403375,
|
| 276 |
+
"learning_rate": 3.358951010744855e-05,
|
| 277 |
+
"loss": 0.8443350219726562,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.8346942478679006,
|
| 282 |
+
"learning_rate": 3.344381715534511e-05,
|
| 283 |
+
"loss": 0.8400850219726562,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.8528397749954636,
|
| 288 |
+
"learning_rate": 3.329812420324167e-05,
|
| 289 |
+
"loss": 0.7925293579101562,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.8709853021230267,
|
| 294 |
+
"learning_rate": 3.315243125113823e-05,
|
| 295 |
+
"loss": 0.809871337890625,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8891308292505897,
|
| 300 |
+
"learning_rate": 3.300673829903479e-05,
|
| 301 |
+
"loss": 0.8267896728515625,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.9072763563781527,
|
| 306 |
+
"learning_rate": 3.2861045346931345e-05,
|
| 307 |
+
"loss": 0.7969192504882813,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.9254218835057159,
|
| 312 |
+
"learning_rate": 3.2715352394827905e-05,
|
| 313 |
+
"loss": 0.821365234375,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.9435674106332789,
|
| 318 |
+
"learning_rate": 3.256965944272446e-05,
|
| 319 |
+
"loss": 0.8019456787109375,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.961712937760842,
|
| 324 |
+
"learning_rate": 3.242396649062102e-05,
|
| 325 |
+
"loss": 0.7933065795898437,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.979858464888405,
|
| 330 |
+
"learning_rate": 3.227827353851757e-05,
|
| 331 |
+
"loss": 0.833029296875,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.998003992015968,
|
| 336 |
+
"learning_rate": 3.213258058641413e-05,
|
| 337 |
+
"loss": 0.8048839111328125,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.0,
|
| 342 |
+
"eval_accuracy": 0.673336556959681,
|
| 343 |
+
"eval_accuracy_not_balanced": 0.719448871523315,
|
| 344 |
+
"eval_f1": 0.7166208604108357,
|
| 345 |
+
"eval_loss": 0.8470854759216309,
|
| 346 |
+
"eval_precision": 0.721835226975883,
|
| 347 |
+
"eval_recall": 0.719448871523315,
|
| 348 |
+
"step": 27555
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.016149519143531,
|
| 352 |
+
"learning_rate": 3.1986887634310694e-05,
|
| 353 |
+
"loss": 0.6081535034179687,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0342950462710943,
|
| 358 |
+
"learning_rate": 3.184119468220725e-05,
|
| 359 |
+
"loss": 0.6581923217773438,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.0524405733986573,
|
| 364 |
+
"learning_rate": 3.169550173010381e-05,
|
| 365 |
+
"loss": 0.6415296020507812,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.0705861005262203,
|
| 370 |
+
"learning_rate": 3.154980877800037e-05,
|
| 371 |
+
"loss": 0.636827392578125,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.0887316276537833,
|
| 376 |
+
"learning_rate": 3.140411582589693e-05,
|
| 377 |
+
"loss": 0.6284669189453125,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.1068771547813463,
|
| 382 |
+
"learning_rate": 3.125842287379348e-05,
|
| 383 |
+
"loss": 0.6636114501953125,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.1250226819089095,
|
| 388 |
+
"learning_rate": 3.111272992169004e-05,
|
| 389 |
+
"loss": 0.7081345825195312,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.1431682090364725,
|
| 394 |
+
"learning_rate": 3.0967036969586596e-05,
|
| 395 |
+
"loss": 0.6273524169921875,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.1613137361640355,
|
| 400 |
+
"learning_rate": 3.0821344017483156e-05,
|
| 401 |
+
"loss": 0.6474124145507812,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.1794592632915986,
|
| 406 |
+
"learning_rate": 3.0675651065379716e-05,
|
| 407 |
+
"loss": 0.624934326171875,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.1976047904191618,
|
| 412 |
+
"learning_rate": 3.052995811327627e-05,
|
| 413 |
+
"loss": 0.627742431640625,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.2157503175467248,
|
| 418 |
+
"learning_rate": 3.0384265161172834e-05,
|
| 419 |
+
"loss": 0.6321390380859375,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.2338958446742878,
|
| 424 |
+
"learning_rate": 3.0238572209069387e-05,
|
| 425 |
+
"loss": 0.6632438354492187,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.2520413718018508,
|
| 430 |
+
"learning_rate": 3.0092879256965948e-05,
|
| 431 |
+
"loss": 0.687524169921875,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.2701868989294138,
|
| 436 |
+
"learning_rate": 2.9947186304862504e-05,
|
| 437 |
+
"loss": 0.6545087280273437,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.2883324260569768,
|
| 442 |
+
"learning_rate": 2.9801493352759065e-05,
|
| 443 |
+
"loss": 0.67624365234375,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.30647795318454,
|
| 448 |
+
"learning_rate": 2.965580040065562e-05,
|
| 449 |
+
"loss": 0.6588964233398438,
|
| 450 |
+
"step": 36000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.324623480312103,
|
| 454 |
+
"learning_rate": 2.951010744855218e-05,
|
| 455 |
+
"loss": 0.696208251953125,
|
| 456 |
+
"step": 36500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.342769007439666,
|
| 460 |
+
"learning_rate": 2.936441449644874e-05,
|
| 461 |
+
"loss": 0.6372421264648438,
|
| 462 |
+
"step": 37000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.360914534567229,
|
| 466 |
+
"learning_rate": 2.9218721544345293e-05,
|
| 467 |
+
"loss": 0.7146538696289062,
|
| 468 |
+
"step": 37500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.3790600616947923,
|
| 472 |
+
"learning_rate": 2.9073028592241853e-05,
|
| 473 |
+
"loss": 0.626543212890625,
|
| 474 |
+
"step": 38000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.3972055888223553,
|
| 478 |
+
"learning_rate": 2.892733564013841e-05,
|
| 479 |
+
"loss": 0.6519877319335937,
|
| 480 |
+
"step": 38500
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.4153511159499184,
|
| 484 |
+
"learning_rate": 2.878164268803497e-05,
|
| 485 |
+
"loss": 0.653167724609375,
|
| 486 |
+
"step": 39000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.4334966430774814,
|
| 490 |
+
"learning_rate": 2.8635949735931524e-05,
|
| 491 |
+
"loss": 0.6557488403320313,
|
| 492 |
+
"step": 39500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.4516421702050444,
|
| 496 |
+
"learning_rate": 2.8490256783828084e-05,
|
| 497 |
+
"loss": 0.6946817016601563,
|
| 498 |
+
"step": 40000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.4697876973326074,
|
| 502 |
+
"learning_rate": 2.834456383172464e-05,
|
| 503 |
+
"loss": 0.6515726318359375,
|
| 504 |
+
"step": 40500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.4879332244601706,
|
| 508 |
+
"learning_rate": 2.81988708796212e-05,
|
| 509 |
+
"loss": 0.6651732177734375,
|
| 510 |
+
"step": 41000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.5060787515877336,
|
| 514 |
+
"learning_rate": 2.8053177927517762e-05,
|
| 515 |
+
"loss": 0.6083211669921875,
|
| 516 |
+
"step": 41500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.5242242787152966,
|
| 520 |
+
"learning_rate": 2.7907484975414315e-05,
|
| 521 |
+
"loss": 0.6926116943359375,
|
| 522 |
+
"step": 42000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.5423698058428599,
|
| 526 |
+
"learning_rate": 2.7761792023310876e-05,
|
| 527 |
+
"loss": 0.6213585815429687,
|
| 528 |
+
"step": 42500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.5605153329704229,
|
| 532 |
+
"learning_rate": 2.7616099071207433e-05,
|
| 533 |
+
"loss": 0.6704981079101563,
|
| 534 |
+
"step": 43000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.578660860097986,
|
| 538 |
+
"learning_rate": 2.7470406119103993e-05,
|
| 539 |
+
"loss": 0.6157642822265625,
|
| 540 |
+
"step": 43500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.596806387225549,
|
| 544 |
+
"learning_rate": 2.7324713167000547e-05,
|
| 545 |
+
"loss": 0.6634461059570312,
|
| 546 |
+
"step": 44000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.614951914353112,
|
| 550 |
+
"learning_rate": 2.7179020214897107e-05,
|
| 551 |
+
"loss": 0.600257080078125,
|
| 552 |
+
"step": 44500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.633097441480675,
|
| 556 |
+
"learning_rate": 2.7033327262793664e-05,
|
| 557 |
+
"loss": 0.6623485107421875,
|
| 558 |
+
"step": 45000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.651242968608238,
|
| 562 |
+
"learning_rate": 2.6887634310690224e-05,
|
| 563 |
+
"loss": 0.5999126586914062,
|
| 564 |
+
"step": 45500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.6693884957358012,
|
| 568 |
+
"learning_rate": 2.674194135858678e-05,
|
| 569 |
+
"loss": 0.69545458984375,
|
| 570 |
+
"step": 46000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.6875340228633642,
|
| 574 |
+
"learning_rate": 2.6596248406483338e-05,
|
| 575 |
+
"loss": 0.607707763671875,
|
| 576 |
+
"step": 46500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.7056795499909272,
|
| 580 |
+
"learning_rate": 2.64505554543799e-05,
|
| 581 |
+
"loss": 0.616205322265625,
|
| 582 |
+
"step": 47000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.7238250771184904,
|
| 586 |
+
"learning_rate": 2.6304862502276452e-05,
|
| 587 |
+
"loss": 0.6300867309570313,
|
| 588 |
+
"step": 47500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.7419706042460534,
|
| 592 |
+
"learning_rate": 2.6159169550173012e-05,
|
| 593 |
+
"loss": 0.6011024780273437,
|
| 594 |
+
"step": 48000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.7601161313736164,
|
| 598 |
+
"learning_rate": 2.601347659806957e-05,
|
| 599 |
+
"loss": 0.640543212890625,
|
| 600 |
+
"step": 48500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.7782616585011795,
|
| 604 |
+
"learning_rate": 2.586778364596613e-05,
|
| 605 |
+
"loss": 0.6576856079101563,
|
| 606 |
+
"step": 49000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.7964071856287425,
|
| 610 |
+
"learning_rate": 2.5722090693862683e-05,
|
| 611 |
+
"loss": 0.6559103393554687,
|
| 612 |
+
"step": 49500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.8145527127563055,
|
| 616 |
+
"learning_rate": 2.5576397741759244e-05,
|
| 617 |
+
"loss": 0.5990095825195313,
|
| 618 |
+
"step": 50000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.8326982398838685,
|
| 622 |
+
"learning_rate": 2.5430704789655804e-05,
|
| 623 |
+
"loss": 0.665473876953125,
|
| 624 |
+
"step": 50500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.8508437670114317,
|
| 628 |
+
"learning_rate": 2.528501183755236e-05,
|
| 629 |
+
"loss": 0.6510874633789062,
|
| 630 |
+
"step": 51000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.8689892941389947,
|
| 634 |
+
"learning_rate": 2.513931888544892e-05,
|
| 635 |
+
"loss": 0.6525092163085937,
|
| 636 |
+
"step": 51500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.8871348212665577,
|
| 640 |
+
"learning_rate": 2.4993625933345475e-05,
|
| 641 |
+
"loss": 0.621588623046875,
|
| 642 |
+
"step": 52000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.905280348394121,
|
| 646 |
+
"learning_rate": 2.4847932981242035e-05,
|
| 647 |
+
"loss": 0.6466250610351563,
|
| 648 |
+
"step": 52500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.923425875521684,
|
| 652 |
+
"learning_rate": 2.4702240029138592e-05,
|
| 653 |
+
"loss": 0.6506993408203126,
|
| 654 |
+
"step": 53000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.941571402649247,
|
| 658 |
+
"learning_rate": 2.4556547077035153e-05,
|
| 659 |
+
"loss": 0.63045458984375,
|
| 660 |
+
"step": 53500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.95971692977681,
|
| 664 |
+
"learning_rate": 2.4410854124931706e-05,
|
| 665 |
+
"loss": 0.6722386474609375,
|
| 666 |
+
"step": 54000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.977862456904373,
|
| 670 |
+
"learning_rate": 2.4265161172828266e-05,
|
| 671 |
+
"loss": 0.6592996826171875,
|
| 672 |
+
"step": 54500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.996007984031936,
|
| 676 |
+
"learning_rate": 2.4119468220724827e-05,
|
| 677 |
+
"loss": 0.6505784301757812,
|
| 678 |
+
"step": 55000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.0,
|
| 682 |
+
"eval_accuracy": 0.7065592633230761,
|
| 683 |
+
"eval_accuracy_not_balanced": 0.7466968279265848,
|
| 684 |
+
"eval_f1": 0.7461387954715045,
|
| 685 |
+
"eval_loss": 1.030800700187683,
|
| 686 |
+
"eval_precision": 0.7471414389441547,
|
| 687 |
+
"eval_recall": 0.7466968279265848,
|
| 688 |
+
"step": 55110
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.014153511159499,
|
| 692 |
+
"learning_rate": 2.397377526862138e-05,
|
| 693 |
+
"loss": 0.4738241882324219,
|
| 694 |
+
"step": 55500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.032299038287062,
|
| 698 |
+
"learning_rate": 2.382808231651794e-05,
|
| 699 |
+
"loss": 0.4202625427246094,
|
| 700 |
+
"step": 56000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.0504445654146255,
|
| 704 |
+
"learning_rate": 2.3682389364414498e-05,
|
| 705 |
+
"loss": 0.45609054565429685,
|
| 706 |
+
"step": 56500
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.0685900925421885,
|
| 710 |
+
"learning_rate": 2.3536696412311058e-05,
|
| 711 |
+
"loss": 0.47380087280273436,
|
| 712 |
+
"step": 57000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.0867356196697515,
|
| 716 |
+
"learning_rate": 2.339100346020761e-05,
|
| 717 |
+
"loss": 0.43297515869140624,
|
| 718 |
+
"step": 57500
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.1048811467973145,
|
| 722 |
+
"learning_rate": 2.3245310508104172e-05,
|
| 723 |
+
"loss": 0.45876251220703124,
|
| 724 |
+
"step": 58000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.1230266739248775,
|
| 728 |
+
"learning_rate": 2.309961755600073e-05,
|
| 729 |
+
"loss": 0.43873019409179687,
|
| 730 |
+
"step": 58500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.1411722010524405,
|
| 734 |
+
"learning_rate": 2.295392460389729e-05,
|
| 735 |
+
"loss": 0.4506067810058594,
|
| 736 |
+
"step": 59000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.1593177281800036,
|
| 740 |
+
"learning_rate": 2.280823165179385e-05,
|
| 741 |
+
"loss": 0.434221923828125,
|
| 742 |
+
"step": 59500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.1774632553075666,
|
| 746 |
+
"learning_rate": 2.2662538699690403e-05,
|
| 747 |
+
"loss": 0.4482630615234375,
|
| 748 |
+
"step": 60000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.1956087824351296,
|
| 752 |
+
"learning_rate": 2.2516845747586964e-05,
|
| 753 |
+
"loss": 0.42872335815429685,
|
| 754 |
+
"step": 60500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.2137543095626926,
|
| 758 |
+
"learning_rate": 2.237115279548352e-05,
|
| 759 |
+
"loss": 0.5074381103515625,
|
| 760 |
+
"step": 61000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.231899836690256,
|
| 764 |
+
"learning_rate": 2.222545984338008e-05,
|
| 765 |
+
"loss": 0.4730833740234375,
|
| 766 |
+
"step": 61500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.250045363817819,
|
| 770 |
+
"learning_rate": 2.2079766891276634e-05,
|
| 771 |
+
"loss": 0.5002789001464844,
|
| 772 |
+
"step": 62000
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.268190890945382,
|
| 776 |
+
"learning_rate": 2.1934073939173195e-05,
|
| 777 |
+
"loss": 0.5009871215820313,
|
| 778 |
+
"step": 62500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.286336418072945,
|
| 782 |
+
"learning_rate": 2.178838098706975e-05,
|
| 783 |
+
"loss": 0.42858175659179687,
|
| 784 |
+
"step": 63000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.304481945200508,
|
| 788 |
+
"learning_rate": 2.1642688034966312e-05,
|
| 789 |
+
"loss": 0.47521218872070314,
|
| 790 |
+
"step": 63500
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.322627472328071,
|
| 794 |
+
"learning_rate": 2.149699508286287e-05,
|
| 795 |
+
"loss": 0.44123291015625,
|
| 796 |
+
"step": 64000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.340772999455634,
|
| 800 |
+
"learning_rate": 2.1351302130759426e-05,
|
| 801 |
+
"loss": 0.5162994384765625,
|
| 802 |
+
"step": 64500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.358918526583197,
|
| 806 |
+
"learning_rate": 2.1205609178655986e-05,
|
| 807 |
+
"loss": 0.4803743896484375,
|
| 808 |
+
"step": 65000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.37706405371076,
|
| 812 |
+
"learning_rate": 2.105991622655254e-05,
|
| 813 |
+
"loss": 0.43930706787109375,
|
| 814 |
+
"step": 65500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.3952095808383236,
|
| 818 |
+
"learning_rate": 2.09142232744491e-05,
|
| 819 |
+
"loss": 0.4680689697265625,
|
| 820 |
+
"step": 66000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.4133551079658866,
|
| 824 |
+
"learning_rate": 2.0768530322345657e-05,
|
| 825 |
+
"loss": 0.47557147216796875,
|
| 826 |
+
"step": 66500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.4315006350934496,
|
| 830 |
+
"learning_rate": 2.0622837370242218e-05,
|
| 831 |
+
"loss": 0.45378570556640624,
|
| 832 |
+
"step": 67000
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.4496461622210126,
|
| 836 |
+
"learning_rate": 2.047714441813877e-05,
|
| 837 |
+
"loss": 0.49939556884765623,
|
| 838 |
+
"step": 67500
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.4677916893485756,
|
| 842 |
+
"learning_rate": 2.033145146603533e-05,
|
| 843 |
+
"loss": 0.46348507690429686,
|
| 844 |
+
"step": 68000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.4859372164761386,
|
| 848 |
+
"learning_rate": 2.0185758513931892e-05,
|
| 849 |
+
"loss": 0.4665544128417969,
|
| 850 |
+
"step": 68500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.5040827436037016,
|
| 854 |
+
"learning_rate": 2.004006556182845e-05,
|
| 855 |
+
"loss": 0.5064073486328124,
|
| 856 |
+
"step": 69000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.5222282707312647,
|
| 860 |
+
"learning_rate": 1.9894372609725006e-05,
|
| 861 |
+
"loss": 0.4335787658691406,
|
| 862 |
+
"step": 69500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.5403737978588277,
|
| 866 |
+
"learning_rate": 1.9748679657621563e-05,
|
| 867 |
+
"loss": 0.4678582458496094,
|
| 868 |
+
"step": 70000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.558519324986391,
|
| 872 |
+
"learning_rate": 1.960298670551812e-05,
|
| 873 |
+
"loss": 0.44978302001953124,
|
| 874 |
+
"step": 70500
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.5766648521139537,
|
| 878 |
+
"learning_rate": 1.945729375341468e-05,
|
| 879 |
+
"loss": 0.4275310363769531,
|
| 880 |
+
"step": 71000
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.594810379241517,
|
| 884 |
+
"learning_rate": 1.931160080131124e-05,
|
| 885 |
+
"loss": 0.4475072326660156,
|
| 886 |
+
"step": 71500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.61295590636908,
|
| 890 |
+
"learning_rate": 1.9165907849207797e-05,
|
| 891 |
+
"loss": 0.4803515625,
|
| 892 |
+
"step": 72000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.631101433496643,
|
| 896 |
+
"learning_rate": 1.9020214897104354e-05,
|
| 897 |
+
"loss": 0.48513922119140623,
|
| 898 |
+
"step": 72500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.649246960624206,
|
| 902 |
+
"learning_rate": 1.887452194500091e-05,
|
| 903 |
+
"loss": 0.509461669921875,
|
| 904 |
+
"step": 73000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.667392487751769,
|
| 908 |
+
"learning_rate": 1.8728828992897468e-05,
|
| 909 |
+
"loss": 0.439398681640625,
|
| 910 |
+
"step": 73500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.685538014879332,
|
| 914 |
+
"learning_rate": 1.858313604079403e-05,
|
| 915 |
+
"loss": 0.49060055541992187,
|
| 916 |
+
"step": 74000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 2.703683542006895,
|
| 920 |
+
"learning_rate": 1.8437443088690585e-05,
|
| 921 |
+
"loss": 0.4656755676269531,
|
| 922 |
+
"step": 74500
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.721829069134458,
|
| 926 |
+
"learning_rate": 1.8291750136587142e-05,
|
| 927 |
+
"loss": 0.45277435302734376,
|
| 928 |
+
"step": 75000
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.7399745962620212,
|
| 932 |
+
"learning_rate": 1.8146057184483703e-05,
|
| 933 |
+
"loss": 0.4694291381835938,
|
| 934 |
+
"step": 75500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.7581201233895847,
|
| 938 |
+
"learning_rate": 1.800036423238026e-05,
|
| 939 |
+
"loss": 0.4835218811035156,
|
| 940 |
+
"step": 76000
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.7762656505171477,
|
| 944 |
+
"learning_rate": 1.785467128027682e-05,
|
| 945 |
+
"loss": 0.4075122680664062,
|
| 946 |
+
"step": 76500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.7944111776447107,
|
| 950 |
+
"learning_rate": 1.7708978328173377e-05,
|
| 951 |
+
"loss": 0.48038003540039065,
|
| 952 |
+
"step": 77000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.8125567047722737,
|
| 956 |
+
"learning_rate": 1.7563285376069934e-05,
|
| 957 |
+
"loss": 0.48810946655273435,
|
| 958 |
+
"step": 77500
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 2.8307022318998367,
|
| 962 |
+
"learning_rate": 1.741759242396649e-05,
|
| 963 |
+
"loss": 0.479569580078125,
|
| 964 |
+
"step": 78000
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.8488477590273997,
|
| 968 |
+
"learning_rate": 1.7271899471863048e-05,
|
| 969 |
+
"loss": 0.43540292358398436,
|
| 970 |
+
"step": 78500
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.8669932861549627,
|
| 974 |
+
"learning_rate": 1.7126206519759608e-05,
|
| 975 |
+
"loss": 0.448812744140625,
|
| 976 |
+
"step": 79000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.8851388132825257,
|
| 980 |
+
"learning_rate": 1.6980513567656165e-05,
|
| 981 |
+
"loss": 0.4721513671875,
|
| 982 |
+
"step": 79500
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.9032843404100888,
|
| 986 |
+
"learning_rate": 1.6834820615552726e-05,
|
| 987 |
+
"loss": 0.49795864868164064,
|
| 988 |
+
"step": 80000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.921429867537652,
|
| 992 |
+
"learning_rate": 1.6689127663449282e-05,
|
| 993 |
+
"loss": 0.43135833740234375,
|
| 994 |
+
"step": 80500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.939575394665215,
|
| 998 |
+
"learning_rate": 1.654343471134584e-05,
|
| 999 |
+
"loss": 0.4152744445800781,
|
| 1000 |
+
"step": 81000
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.9577209217927782,
|
| 1004 |
+
"learning_rate": 1.63977417592424e-05,
|
| 1005 |
+
"loss": 0.4627979736328125,
|
| 1006 |
+
"step": 81500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.9758664489203412,
|
| 1010 |
+
"learning_rate": 1.6252048807138957e-05,
|
| 1011 |
+
"loss": 0.5032968444824218,
|
| 1012 |
+
"step": 82000
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 2.9940119760479043,
|
| 1016 |
+
"learning_rate": 1.6106355855035514e-05,
|
| 1017 |
+
"loss": 0.44907989501953127,
|
| 1018 |
+
"step": 82500
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 3.0,
|
| 1022 |
+
"eval_accuracy": 0.719967526681318,
|
| 1023 |
+
"eval_accuracy_not_balanced": 0.7567220194334482,
|
| 1024 |
+
"eval_f1": 0.7562519073319182,
|
| 1025 |
+
"eval_loss": 1.2266414165496826,
|
| 1026 |
+
"eval_precision": 0.7566245119201862,
|
| 1027 |
+
"eval_recall": 0.7567220194334482,
|
| 1028 |
+
"step": 82665
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.0121575031754673,
|
| 1032 |
+
"learning_rate": 1.596066290293207e-05,
|
| 1033 |
+
"loss": 0.3230574645996094,
|
| 1034 |
+
"step": 83000
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.0303030303030303,
|
| 1038 |
+
"learning_rate": 1.5814969950828628e-05,
|
| 1039 |
+
"loss": 0.2732647399902344,
|
| 1040 |
+
"step": 83500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.0484485574305933,
|
| 1044 |
+
"learning_rate": 1.5669276998725188e-05,
|
| 1045 |
+
"loss": 0.2596098327636719,
|
| 1046 |
+
"step": 84000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.0665940845581563,
|
| 1050 |
+
"learning_rate": 1.5523584046621748e-05,
|
| 1051 |
+
"loss": 0.2204219970703125,
|
| 1052 |
+
"step": 84500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.0847396116857193,
|
| 1056 |
+
"learning_rate": 1.5377891094518305e-05,
|
| 1057 |
+
"loss": 0.2841182861328125,
|
| 1058 |
+
"step": 85000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.1028851388132823,
|
| 1062 |
+
"learning_rate": 1.5232198142414862e-05,
|
| 1063 |
+
"loss": 0.2811924133300781,
|
| 1064 |
+
"step": 85500
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.1210306659408458,
|
| 1068 |
+
"learning_rate": 1.5086505190311421e-05,
|
| 1069 |
+
"loss": 0.2654357604980469,
|
| 1070 |
+
"step": 86000
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.139176193068409,
|
| 1074 |
+
"learning_rate": 1.4940812238207978e-05,
|
| 1075 |
+
"loss": 0.28281610107421873,
|
| 1076 |
+
"step": 86500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.157321720195972,
|
| 1080 |
+
"learning_rate": 1.4795119286104536e-05,
|
| 1081 |
+
"loss": 0.2979160461425781,
|
| 1082 |
+
"step": 87000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.175467247323535,
|
| 1086 |
+
"learning_rate": 1.4649426334001093e-05,
|
| 1087 |
+
"loss": 0.30940216064453124,
|
| 1088 |
+
"step": 87500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.193612774451098,
|
| 1092 |
+
"learning_rate": 1.450373338189765e-05,
|
| 1093 |
+
"loss": 0.2786048278808594,
|
| 1094 |
+
"step": 88000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.211758301578661,
|
| 1098 |
+
"learning_rate": 1.4358040429794209e-05,
|
| 1099 |
+
"loss": 0.3191018981933594,
|
| 1100 |
+
"step": 88500
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.229903828706224,
|
| 1104 |
+
"learning_rate": 1.421234747769077e-05,
|
| 1105 |
+
"loss": 0.2721468200683594,
|
| 1106 |
+
"step": 89000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.248049355833787,
|
| 1110 |
+
"learning_rate": 1.4066654525587326e-05,
|
| 1111 |
+
"loss": 0.2782774963378906,
|
| 1112 |
+
"step": 89500
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 3.26619488296135,
|
| 1116 |
+
"learning_rate": 1.3920961573483885e-05,
|
| 1117 |
+
"loss": 0.24969586181640624,
|
| 1118 |
+
"step": 90000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.2843404100889133,
|
| 1122 |
+
"learning_rate": 1.3775268621380442e-05,
|
| 1123 |
+
"loss": 0.3144935302734375,
|
| 1124 |
+
"step": 90500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 3.3024859372164763,
|
| 1128 |
+
"learning_rate": 1.3629575669277e-05,
|
| 1129 |
+
"loss": 0.3104676208496094,
|
| 1130 |
+
"step": 91000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.3206314643440393,
|
| 1134 |
+
"learning_rate": 1.3483882717173558e-05,
|
| 1135 |
+
"loss": 0.31101416015625,
|
| 1136 |
+
"step": 91500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.3387769914716023,
|
| 1140 |
+
"learning_rate": 1.3338189765070115e-05,
|
| 1141 |
+
"loss": 0.2874825744628906,
|
| 1142 |
+
"step": 92000
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.3569225185991654,
|
| 1146 |
+
"learning_rate": 1.3192496812966673e-05,
|
| 1147 |
+
"loss": 0.30249465942382814,
|
| 1148 |
+
"step": 92500
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.3750680457267284,
|
| 1152 |
+
"learning_rate": 1.304680386086323e-05,
|
| 1153 |
+
"loss": 0.3033802185058594,
|
| 1154 |
+
"step": 93000
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 3.3932135728542914,
|
| 1158 |
+
"learning_rate": 1.290111090875979e-05,
|
| 1159 |
+
"loss": 0.2691561279296875,
|
| 1160 |
+
"step": 93500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.4113590999818544,
|
| 1164 |
+
"learning_rate": 1.2755417956656349e-05,
|
| 1165 |
+
"loss": 0.2455874786376953,
|
| 1166 |
+
"step": 94000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 3.4295046271094174,
|
| 1170 |
+
"learning_rate": 1.2609725004552906e-05,
|
| 1171 |
+
"loss": 0.24622802734375,
|
| 1172 |
+
"step": 94500
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.4476501542369804,
|
| 1176 |
+
"learning_rate": 1.2464032052449465e-05,
|
| 1177 |
+
"loss": 0.29979901123046876,
|
| 1178 |
+
"step": 95000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.4657956813645434,
|
| 1182 |
+
"learning_rate": 1.2318339100346022e-05,
|
| 1183 |
+
"loss": 0.28493136596679686,
|
| 1184 |
+
"step": 95500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 3.483941208492107,
|
| 1188 |
+
"learning_rate": 1.217264614824258e-05,
|
| 1189 |
+
"loss": 0.22248597717285157,
|
| 1190 |
+
"step": 96000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.50208673561967,
|
| 1194 |
+
"learning_rate": 1.2026953196139137e-05,
|
| 1195 |
+
"loss": 0.29626983642578125,
|
| 1196 |
+
"step": 96500
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 3.520232262747233,
|
| 1200 |
+
"learning_rate": 1.1881260244035694e-05,
|
| 1201 |
+
"loss": 0.22462777709960938,
|
| 1202 |
+
"step": 97000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.538377789874796,
|
| 1206 |
+
"learning_rate": 1.1735567291932253e-05,
|
| 1207 |
+
"loss": 0.31633203125,
|
| 1208 |
+
"step": 97500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.556523317002359,
|
| 1212 |
+
"learning_rate": 1.1589874339828813e-05,
|
| 1213 |
+
"loss": 0.29999240112304687,
|
| 1214 |
+
"step": 98000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 3.574668844129922,
|
| 1218 |
+
"learning_rate": 1.144418138772537e-05,
|
| 1219 |
+
"loss": 0.3205788879394531,
|
| 1220 |
+
"step": 98500
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.592814371257485,
|
| 1224 |
+
"learning_rate": 1.1298488435621929e-05,
|
| 1225 |
+
"loss": 0.31732611083984374,
|
| 1226 |
+
"step": 99000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.610959898385048,
|
| 1230 |
+
"learning_rate": 1.1152795483518486e-05,
|
| 1231 |
+
"loss": 0.2857419128417969,
|
| 1232 |
+
"step": 99500
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 3.629105425512611,
|
| 1236 |
+
"learning_rate": 1.1007102531415044e-05,
|
| 1237 |
+
"loss": 0.2731871032714844,
|
| 1238 |
+
"step": 100000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 3.6472509526401744,
|
| 1242 |
+
"learning_rate": 1.0861409579311601e-05,
|
| 1243 |
+
"loss": 0.2926119079589844,
|
| 1244 |
+
"step": 100500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.6653964797677374,
|
| 1248 |
+
"learning_rate": 1.0715716627208158e-05,
|
| 1249 |
+
"loss": 0.2275234375,
|
| 1250 |
+
"step": 101000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.6835420068953004,
|
| 1254 |
+
"learning_rate": 1.0570023675104717e-05,
|
| 1255 |
+
"loss": 0.2467783660888672,
|
| 1256 |
+
"step": 101500
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 3.7016875340228634,
|
| 1260 |
+
"learning_rate": 1.0424330723001274e-05,
|
| 1261 |
+
"loss": 0.29310882568359375,
|
| 1262 |
+
"step": 102000
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 3.7198330611504264,
|
| 1266 |
+
"learning_rate": 1.0278637770897834e-05,
|
| 1267 |
+
"loss": 0.2742635803222656,
|
| 1268 |
+
"step": 102500
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 3.7379785882779895,
|
| 1272 |
+
"learning_rate": 1.0132944818794393e-05,
|
| 1273 |
+
"loss": 0.3342573547363281,
|
| 1274 |
+
"step": 103000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 3.7561241154055525,
|
| 1278 |
+
"learning_rate": 9.98725186669095e-06,
|
| 1279 |
+
"loss": 0.2816724548339844,
|
| 1280 |
+
"step": 103500
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 3.7742696425331155,
|
| 1284 |
+
"learning_rate": 9.841558914587509e-06,
|
| 1285 |
+
"loss": 0.2820220947265625,
|
| 1286 |
+
"step": 104000
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.7924151696606785,
|
| 1290 |
+
"learning_rate": 9.695865962484066e-06,
|
| 1291 |
+
"loss": 0.26842498779296875,
|
| 1292 |
+
"step": 104500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.810560696788242,
|
| 1296 |
+
"learning_rate": 9.550173010380624e-06,
|
| 1297 |
+
"loss": 0.2902957458496094,
|
| 1298 |
+
"step": 105000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.8287062239158045,
|
| 1302 |
+
"learning_rate": 9.404480058277181e-06,
|
| 1303 |
+
"loss": 0.2857991943359375,
|
| 1304 |
+
"step": 105500
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 3.846851751043368,
|
| 1308 |
+
"learning_rate": 9.25878710617374e-06,
|
| 1309 |
+
"loss": 0.27429071044921877,
|
| 1310 |
+
"step": 106000
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 3.864997278170931,
|
| 1314 |
+
"learning_rate": 9.113094154070298e-06,
|
| 1315 |
+
"loss": 0.297792724609375,
|
| 1316 |
+
"step": 106500
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 3.883142805298494,
|
| 1320 |
+
"learning_rate": 8.967401201966855e-06,
|
| 1321 |
+
"loss": 0.24031161499023437,
|
| 1322 |
+
"step": 107000
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 3.901288332426057,
|
| 1326 |
+
"learning_rate": 8.821708249863414e-06,
|
| 1327 |
+
"loss": 0.2540105285644531,
|
| 1328 |
+
"step": 107500
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 3.91943385955362,
|
| 1332 |
+
"learning_rate": 8.676015297759973e-06,
|
| 1333 |
+
"loss": 0.19631956481933593,
|
| 1334 |
+
"step": 108000
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 3.937579386681183,
|
| 1338 |
+
"learning_rate": 8.53032234565653e-06,
|
| 1339 |
+
"loss": 0.283151611328125,
|
| 1340 |
+
"step": 108500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.955724913808746,
|
| 1344 |
+
"learning_rate": 8.384629393553088e-06,
|
| 1345 |
+
"loss": 0.25643258666992186,
|
| 1346 |
+
"step": 109000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 3.973870440936309,
|
| 1350 |
+
"learning_rate": 8.238936441449645e-06,
|
| 1351 |
+
"loss": 0.28699124145507815,
|
| 1352 |
+
"step": 109500
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.992015968063872,
|
| 1356 |
+
"learning_rate": 8.093243489346202e-06,
|
| 1357 |
+
"loss": 0.28246923828125,
|
| 1358 |
+
"step": 110000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.0,
|
| 1362 |
+
"eval_accuracy": 0.7364013629648626,
|
| 1363 |
+
"eval_accuracy_not_balanced": 0.7658732198858671,
|
| 1364 |
+
"eval_f1": 0.7663226389044607,
|
| 1365 |
+
"eval_loss": 1.4270503520965576,
|
| 1366 |
+
"eval_precision": 0.7674868056440829,
|
| 1367 |
+
"eval_recall": 0.7658732198858671,
|
| 1368 |
+
"step": 110220
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.0101614951914355,
|
| 1372 |
+
"learning_rate": 7.947550537242763e-06,
|
| 1373 |
+
"loss": 0.1843712615966797,
|
| 1374 |
+
"step": 110500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 4.028307022318998,
|
| 1378 |
+
"learning_rate": 7.80185758513932e-06,
|
| 1379 |
+
"loss": 0.12554346466064453,
|
| 1380 |
+
"step": 111000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 4.0464525494465615,
|
| 1384 |
+
"learning_rate": 7.656164633035878e-06,
|
| 1385 |
+
"loss": 0.1526964111328125,
|
| 1386 |
+
"step": 111500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.064598076574124,
|
| 1390 |
+
"learning_rate": 7.510471680932435e-06,
|
| 1391 |
+
"loss": 0.1175911865234375,
|
| 1392 |
+
"step": 112000
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 4.0827436037016875,
|
| 1396 |
+
"learning_rate": 7.364778728828994e-06,
|
| 1397 |
+
"loss": 0.13503671264648437,
|
| 1398 |
+
"step": 112500
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 4.100889130829251,
|
| 1402 |
+
"learning_rate": 7.219085776725552e-06,
|
| 1403 |
+
"loss": 0.15723780822753905,
|
| 1404 |
+
"step": 113000
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 4.119034657956814,
|
| 1408 |
+
"learning_rate": 7.073392824622109e-06,
|
| 1409 |
+
"loss": 0.14341749572753906,
|
| 1410 |
+
"step": 113500
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 4.137180185084377,
|
| 1414 |
+
"learning_rate": 6.927699872518667e-06,
|
| 1415 |
+
"loss": 0.17015084838867187,
|
| 1416 |
+
"step": 114000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 4.15532571221194,
|
| 1420 |
+
"learning_rate": 6.782006920415225e-06,
|
| 1421 |
+
"loss": 0.1238730239868164,
|
| 1422 |
+
"step": 114500
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 4.173471239339503,
|
| 1426 |
+
"learning_rate": 6.636313968311784e-06,
|
| 1427 |
+
"loss": 0.14837001037597655,
|
| 1428 |
+
"step": 115000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.191616766467066,
|
| 1432 |
+
"learning_rate": 6.4906210162083415e-06,
|
| 1433 |
+
"loss": 0.15362150573730468,
|
| 1434 |
+
"step": 115500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.209762293594629,
|
| 1438 |
+
"learning_rate": 6.344928064104899e-06,
|
| 1439 |
+
"loss": 0.13405267333984375,
|
| 1440 |
+
"step": 116000
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 4.227907820722192,
|
| 1444 |
+
"learning_rate": 6.199235112001457e-06,
|
| 1445 |
+
"loss": 0.13654838562011717,
|
| 1446 |
+
"step": 116500
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 4.246053347849755,
|
| 1450 |
+
"learning_rate": 6.053542159898016e-06,
|
| 1451 |
+
"loss": 0.1306242218017578,
|
| 1452 |
+
"step": 117000
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 4.264198874977318,
|
| 1456 |
+
"learning_rate": 5.9078492077945735e-06,
|
| 1457 |
+
"loss": 0.16896232604980468,
|
| 1458 |
+
"step": 117500
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 4.282344402104881,
|
| 1462 |
+
"learning_rate": 5.762156255691131e-06,
|
| 1463 |
+
"loss": 0.14876005554199218,
|
| 1464 |
+
"step": 118000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 4.3004899292324446,
|
| 1468 |
+
"learning_rate": 5.616463303587689e-06,
|
| 1469 |
+
"loss": 0.18081915283203126,
|
| 1470 |
+
"step": 118500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 4.318635456360007,
|
| 1474 |
+
"learning_rate": 5.470770351484247e-06,
|
| 1475 |
+
"loss": 0.13800569152832032,
|
| 1476 |
+
"step": 119000
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 4.336780983487571,
|
| 1480 |
+
"learning_rate": 5.325077399380806e-06,
|
| 1481 |
+
"loss": 0.12778076934814453,
|
| 1482 |
+
"step": 119500
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 4.354926510615133,
|
| 1486 |
+
"learning_rate": 5.179384447277363e-06,
|
| 1487 |
+
"loss": 0.16787666320800781,
|
| 1488 |
+
"step": 120000
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 4.373072037742697,
|
| 1492 |
+
"learning_rate": 5.033691495173921e-06,
|
| 1493 |
+
"loss": 0.1471616668701172,
|
| 1494 |
+
"step": 120500
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 4.391217564870259,
|
| 1498 |
+
"learning_rate": 4.88799854307048e-06,
|
| 1499 |
+
"loss": 0.14897169494628906,
|
| 1500 |
+
"step": 121000
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 4.409363091997823,
|
| 1504 |
+
"learning_rate": 4.742305590967038e-06,
|
| 1505 |
+
"loss": 0.10772408294677735,
|
| 1506 |
+
"step": 121500
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 4.427508619125385,
|
| 1510 |
+
"learning_rate": 4.5966126388635955e-06,
|
| 1511 |
+
"loss": 0.16820535278320312,
|
| 1512 |
+
"step": 122000
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 4.445654146252949,
|
| 1516 |
+
"learning_rate": 4.450919686760153e-06,
|
| 1517 |
+
"loss": 0.15158670043945313,
|
| 1518 |
+
"step": 122500
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 4.463799673380512,
|
| 1522 |
+
"learning_rate": 4.305226734656711e-06,
|
| 1523 |
+
"loss": 0.1802527618408203,
|
| 1524 |
+
"step": 123000
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 4.481945200508075,
|
| 1528 |
+
"learning_rate": 4.15953378255327e-06,
|
| 1529 |
+
"loss": 0.12233680725097656,
|
| 1530 |
+
"step": 123500
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.500090727635638,
|
| 1534 |
+
"learning_rate": 4.0138408304498275e-06,
|
| 1535 |
+
"loss": 0.13587774658203125,
|
| 1536 |
+
"step": 124000
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 4.518236254763201,
|
| 1540 |
+
"learning_rate": 3.868147878346385e-06,
|
| 1541 |
+
"loss": 0.1264299087524414,
|
| 1542 |
+
"step": 124500
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 4.536381781890764,
|
| 1546 |
+
"learning_rate": 3.722454926242943e-06,
|
| 1547 |
+
"loss": 0.15187008666992188,
|
| 1548 |
+
"step": 125000
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 4.554527309018327,
|
| 1552 |
+
"learning_rate": 3.5767619741395014e-06,
|
| 1553 |
+
"loss": 0.13250352478027344,
|
| 1554 |
+
"step": 125500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 4.57267283614589,
|
| 1558 |
+
"learning_rate": 3.431069022036059e-06,
|
| 1559 |
+
"loss": 0.11472991180419922,
|
| 1560 |
+
"step": 126000
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 4.590818363273453,
|
| 1564 |
+
"learning_rate": 3.285376069932617e-06,
|
| 1565 |
+
"loss": 0.17263003540039062,
|
| 1566 |
+
"step": 126500
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 4.608963890401016,
|
| 1570 |
+
"learning_rate": 3.139683117829175e-06,
|
| 1571 |
+
"loss": 0.1344503173828125,
|
| 1572 |
+
"step": 127000
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 4.62710941752858,
|
| 1576 |
+
"learning_rate": 2.993990165725733e-06,
|
| 1577 |
+
"loss": 0.1357424774169922,
|
| 1578 |
+
"step": 127500
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 4.645254944656142,
|
| 1582 |
+
"learning_rate": 2.8482972136222912e-06,
|
| 1583 |
+
"loss": 0.12101192474365234,
|
| 1584 |
+
"step": 128000
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 4.663400471783706,
|
| 1588 |
+
"learning_rate": 2.702604261518849e-06,
|
| 1589 |
+
"loss": 0.13540719604492188,
|
| 1590 |
+
"step": 128500
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 4.681545998911268,
|
| 1594 |
+
"learning_rate": 2.5569113094154073e-06,
|
| 1595 |
+
"loss": 0.14367697143554686,
|
| 1596 |
+
"step": 129000
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 4.699691526038832,
|
| 1600 |
+
"learning_rate": 2.411218357311965e-06,
|
| 1601 |
+
"loss": 0.13124786376953124,
|
| 1602 |
+
"step": 129500
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 4.717837053166394,
|
| 1606 |
+
"learning_rate": 2.2655254052085233e-06,
|
| 1607 |
+
"loss": 0.147208984375,
|
| 1608 |
+
"step": 130000
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 4.735982580293958,
|
| 1612 |
+
"learning_rate": 2.119832453105081e-06,
|
| 1613 |
+
"loss": 0.15938619995117187,
|
| 1614 |
+
"step": 130500
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 4.75412810742152,
|
| 1618 |
+
"learning_rate": 1.9741395010016393e-06,
|
| 1619 |
+
"loss": 0.1515483093261719,
|
| 1620 |
+
"step": 131000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 4.772273634549084,
|
| 1624 |
+
"learning_rate": 1.8284465488981974e-06,
|
| 1625 |
+
"loss": 0.14191549682617188,
|
| 1626 |
+
"step": 131500
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 4.790419161676647,
|
| 1630 |
+
"learning_rate": 1.6827535967947554e-06,
|
| 1631 |
+
"loss": 0.13431153869628906,
|
| 1632 |
+
"step": 132000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 4.80856468880421,
|
| 1636 |
+
"learning_rate": 1.537060644691313e-06,
|
| 1637 |
+
"loss": 0.16412876892089845,
|
| 1638 |
+
"step": 132500
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 4.826710215931773,
|
| 1642 |
+
"learning_rate": 1.391367692587871e-06,
|
| 1643 |
+
"loss": 0.15667465209960937,
|
| 1644 |
+
"step": 133000
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.844855743059336,
|
| 1648 |
+
"learning_rate": 1.2456747404844292e-06,
|
| 1649 |
+
"loss": 0.11217301940917969,
|
| 1650 |
+
"step": 133500
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 4.863001270186899,
|
| 1654 |
+
"learning_rate": 1.0999817883809872e-06,
|
| 1655 |
+
"loss": 0.13955929565429687,
|
| 1656 |
+
"step": 134000
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 4.881146797314462,
|
| 1660 |
+
"learning_rate": 9.542888362775452e-07,
|
| 1661 |
+
"loss": 0.1466508331298828,
|
| 1662 |
+
"step": 134500
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 4.899292324442025,
|
| 1666 |
+
"learning_rate": 8.085958841741031e-07,
|
| 1667 |
+
"loss": 0.16482601928710938,
|
| 1668 |
+
"step": 135000
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 4.917437851569588,
|
| 1672 |
+
"learning_rate": 6.629029320706612e-07,
|
| 1673 |
+
"loss": 0.1277398147583008,
|
| 1674 |
+
"step": 135500
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 4.935583378697151,
|
| 1678 |
+
"learning_rate": 5.172099799672192e-07,
|
| 1679 |
+
"loss": 0.12898980712890626,
|
| 1680 |
+
"step": 136000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 4.953728905824715,
|
| 1684 |
+
"learning_rate": 3.715170278637771e-07,
|
| 1685 |
+
"loss": 0.16622706604003906,
|
| 1686 |
+
"step": 136500
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 4.971874432952277,
|
| 1690 |
+
"learning_rate": 2.258240757603351e-07,
|
| 1691 |
+
"loss": 0.1129389190673828,
|
| 1692 |
+
"step": 137000
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 4.99001996007984,
|
| 1696 |
+
"learning_rate": 8.013112365689311e-08,
|
| 1697 |
+
"loss": 0.11422783660888672,
|
| 1698 |
+
"step": 137500
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 5.0,
|
| 1702 |
+
"eval_accuracy": 0.7449912424577604,
|
| 1703 |
+
"eval_accuracy_not_balanced": 0.7708601100200504,
|
| 1704 |
+
"eval_f1": 0.771311438926646,
|
| 1705 |
+
"eval_loss": 1.6117682456970215,
|
| 1706 |
+
"eval_precision": 0.7719334049472679,
|
| 1707 |
+
"eval_recall": 0.7708601100200504,
|
| 1708 |
+
"step": 137775
|
| 1709 |
+
}
|
| 1710 |
+
],
|
| 1711 |
+
"max_steps": 137775,
|
| 1712 |
+
"num_train_epochs": 5,
|
| 1713 |
+
"total_flos": 43097270746046340,
|
| 1714 |
+
"trial_name": null,
|
| 1715 |
+
"trial_params": null
|
| 1716 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3a23bfe2a3ae780e4c69e0b4ef3e46a2722538095c4390c2c25afda1cd9b21e
|
| 3 |
+
size 1903
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|