Hugging Face's logo

splitner
/
single-seqtag-bionlp13cg

Transformers
PyTorch
bert
Model card Files
xet
 Community
1
jatinarora2702 commited on
Commit
a78c345
·
1 Parent(s): a83fa4f

first model version

Browse files
Files changed (9) hide show
  1. config.json +126 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +1 -0
  6. tokenizer_config.json +1 -0
  7. trainer_state.json +3442 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/scibert_scivocab_uncased",
3
+ "architectures": [
4
+ "NerModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "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
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "LABEL_0": 0,
66
+ "LABEL_1": 1,
67
+ "LABEL_10": 10,
68
+ "LABEL_11": 11,
69
+ "LABEL_12": 12,
70
+ "LABEL_13": 13,
71
+ "LABEL_14": 14,
72
+ "LABEL_15": 15,
73
+ "LABEL_16": 16,
74
+ "LABEL_17": 17,
75
+ "LABEL_18": 18,
76
+ "LABEL_19": 19,
77
+ "LABEL_2": 2,
78
+ "LABEL_20": 20,
79
+ "LABEL_21": 21,
80
+ "LABEL_22": 22,
81
+ "LABEL_23": 23,
82
+ "LABEL_24": 24,
83
+ "LABEL_25": 25,
84
+ "LABEL_26": 26,
85
+ "LABEL_27": 27,
86
+ "LABEL_28": 28,
87
+ "LABEL_29": 29,
88
+ "LABEL_3": 3,
89
+ "LABEL_30": 30,
90
+ "LABEL_31": 31,
91
+ "LABEL_32": 32,
92
+ "LABEL_33": 33,
93
+ "LABEL_34": 34,
94
+ "LABEL_35": 35,
95
+ "LABEL_36": 36,
96
+ "LABEL_37": 37,
97
+ "LABEL_38": 38,
98
+ "LABEL_39": 39,
99
+ "LABEL_4": 4,
100
+ "LABEL_40": 40,
101
+ "LABEL_41": 41,
102
+ "LABEL_42": 42,
103
+ "LABEL_43": 43,
104
+ "LABEL_44": 44,
105
+ "LABEL_45": 45,
106
+ "LABEL_46": 46,
107
+ "LABEL_47": 47,
108
+ "LABEL_48": 48,
109
+ "LABEL_5": 5,
110
+ "LABEL_6": 6,
111
+ "LABEL_7": 7,
112
+ "LABEL_8": 8,
113
+ "LABEL_9": 9
114
+ },
115
+ "layer_norm_eps": 1e-12,
116
+ "max_position_embeddings": 512,
117
+ "model_type": "bert",
118
+ "num_attention_heads": 12,
119
+ "num_hidden_layers": 12,
120
+ "pad_token_id": 0,
121
+ "position_embedding_type": "absolute",
122
+ "transformers_version": "4.2.2",
123
+ "type_vocab_size": 2,
124
+ "use_cache": true,
125
+ "vocab_size": 31090
126
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba44ef13a40bb66a043ead135fee59d126cffa4144bfb62c2b0fbbc4872c1aaa
3
+ size 936680237
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b146d2877b5c1932dc9533dc4f7b2019a24cdd0bc8b1c2f0f57389e43174937e
3
+ size 468366489
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac19287f148ee50fa230edcbcd8ea771ce6d66f03c6666b8e91bfc082c328a2d
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, "special_tokens_map_file": null, "name_or_path": "allenai/scibert_scivocab_uncased", "do_basic_tokenize": true, "never_split": null}
trainer_state.json ADDED
@@ -0,0 +1,3442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8633093520177468,
3
+ "best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/bio/ner-seq/run-42/checkpoints/checkpoint-9936",
4
+ "epoch": 207.0,
5
+ "global_step": 9936,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "eval_loss": 1.1098062992095947,
13
+ "eval_micro_f1": 0.003890104334087921,
14
+ "eval_runtime": 6.0388,
15
+ "eval_samples_per_second": 166.093,
16
+ "step": 24
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.5973769426345825,
21
+ "eval_micro_f1": 0.42558139486896246,
22
+ "eval_runtime": 6.0634,
23
+ "eval_samples_per_second": 165.418,
24
+ "step": 48
25
+ },
26
+ {
27
+ "epoch": 1.5,
28
+ "eval_loss": 0.40060245990753174,
29
+ "eval_micro_f1": 0.6111590446544916,
30
+ "eval_runtime": 5.8615,
31
+ "eval_samples_per_second": 171.115,
32
+ "step": 72
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.3138572573661804,
37
+ "eval_micro_f1": 0.7027103727086026,
38
+ "eval_runtime": 6.3832,
39
+ "eval_samples_per_second": 157.132,
40
+ "step": 96
41
+ },
42
+ {
43
+ "epoch": 2.5,
44
+ "eval_loss": 0.27617648243904114,
45
+ "eval_micro_f1": 0.7279544502705333,
46
+ "eval_runtime": 6.2183,
47
+ "eval_samples_per_second": 161.298,
48
+ "step": 120
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.24901142716407776,
53
+ "eval_micro_f1": 0.747047513918934,
54
+ "eval_runtime": 6.1522,
55
+ "eval_samples_per_second": 163.032,
56
+ "step": 144
57
+ },
58
+ {
59
+ "epoch": 3.5,
60
+ "eval_loss": 0.23769469559192657,
61
+ "eval_micro_f1": 0.7653271151218225,
62
+ "eval_runtime": 6.7106,
63
+ "eval_samples_per_second": 149.466,
64
+ "step": 168
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_loss": 0.22372488677501678,
69
+ "eval_micro_f1": 0.7922799217436097,
70
+ "eval_runtime": 6.3584,
71
+ "eval_samples_per_second": 157.745,
72
+ "step": 192
73
+ },
74
+ {
75
+ "epoch": 4.5,
76
+ "eval_loss": 0.2169770449399948,
77
+ "eval_micro_f1": 0.7921279207790637,
78
+ "eval_runtime": 6.3182,
79
+ "eval_samples_per_second": 158.748,
80
+ "step": 216
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_loss": 0.2114868462085724,
85
+ "eval_micro_f1": 0.8005517236377132,
86
+ "eval_runtime": 6.262,
87
+ "eval_samples_per_second": 160.172,
88
+ "step": 240
89
+ },
90
+ {
91
+ "epoch": 5.5,
92
+ "eval_loss": 0.21184641122817993,
93
+ "eval_micro_f1": 0.8090292198293713,
94
+ "eval_runtime": 6.1684,
95
+ "eval_samples_per_second": 162.603,
96
+ "step": 264
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_loss": 0.21851345896720886,
101
+ "eval_micro_f1": 0.8180932493258202,
102
+ "eval_runtime": 6.2879,
103
+ "eval_samples_per_second": 159.514,
104
+ "step": 288
105
+ },
106
+ {
107
+ "epoch": 6.5,
108
+ "eval_loss": 0.21611660718917847,
109
+ "eval_micro_f1": 0.8163490743409797,
110
+ "eval_runtime": 6.2623,
111
+ "eval_samples_per_second": 160.165,
112
+ "step": 312
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_loss": 0.21607881784439087,
117
+ "eval_micro_f1": 0.8197811326207053,
118
+ "eval_runtime": 6.4184,
119
+ "eval_samples_per_second": 156.269,
120
+ "step": 336
121
+ },
122
+ {
123
+ "epoch": 7.5,
124
+ "eval_loss": 0.22012177109718323,
125
+ "eval_micro_f1": 0.8179942215385827,
126
+ "eval_runtime": 6.3666,
127
+ "eval_samples_per_second": 157.542,
128
+ "step": 360
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_loss": 0.22075983881950378,
133
+ "eval_micro_f1": 0.8221823694818424,
134
+ "eval_runtime": 5.8453,
135
+ "eval_samples_per_second": 171.591,
136
+ "step": 384
137
+ },
138
+ {
139
+ "epoch": 8.5,
140
+ "eval_loss": 0.22356319427490234,
141
+ "eval_micro_f1": 0.8212321227121105,
142
+ "eval_runtime": 6.0762,
143
+ "eval_samples_per_second": 165.07,
144
+ "step": 408
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_loss": 0.22051317989826202,
149
+ "eval_micro_f1": 0.8247197151137284,
150
+ "eval_runtime": 6.0755,
151
+ "eval_samples_per_second": 165.089,
152
+ "step": 432
153
+ },
154
+ {
155
+ "epoch": 9.5,
156
+ "eval_loss": 0.22701342403888702,
157
+ "eval_micro_f1": 0.8305528741723245,
158
+ "eval_runtime": 6.0451,
159
+ "eval_samples_per_second": 165.919,
160
+ "step": 456
161
+ },
162
+ {
163
+ "epoch": 10.0,
164
+ "eval_loss": 0.23073448240756989,
165
+ "eval_micro_f1": 0.8254530584997449,
166
+ "eval_runtime": 6.4299,
167
+ "eval_samples_per_second": 155.991,
168
+ "step": 480
169
+ },
170
+ {
171
+ "epoch": 10.42,
172
+ "learning_rate": 9.652777777777779e-06,
173
+ "loss": 0.2766,
174
+ "step": 500
175
+ },
176
+ {
177
+ "epoch": 10.5,
178
+ "eval_loss": 0.23178032040596008,
179
+ "eval_micro_f1": 0.829160934850542,
180
+ "eval_runtime": 6.1793,
181
+ "eval_samples_per_second": 162.315,
182
+ "step": 504
183
+ },
184
+ {
185
+ "epoch": 11.0,
186
+ "eval_loss": 0.23805859684944153,
187
+ "eval_micro_f1": 0.831497796856609,
188
+ "eval_runtime": 5.8217,
189
+ "eval_samples_per_second": 172.285,
190
+ "step": 528
191
+ },
192
+ {
193
+ "epoch": 11.5,
194
+ "eval_loss": 0.2399190366268158,
195
+ "eval_micro_f1": 0.8264078726545693,
196
+ "eval_runtime": 5.8392,
197
+ "eval_samples_per_second": 171.772,
198
+ "step": 552
199
+ },
200
+ {
201
+ "epoch": 12.0,
202
+ "eval_loss": 0.2405175417661667,
203
+ "eval_micro_f1": 0.8350260769085273,
204
+ "eval_runtime": 5.9074,
205
+ "eval_samples_per_second": 169.788,
206
+ "step": 576
207
+ },
208
+ {
209
+ "epoch": 12.5,
210
+ "eval_loss": 0.2381366789340973,
211
+ "eval_micro_f1": 0.834723171065113,
212
+ "eval_runtime": 6.5302,
213
+ "eval_samples_per_second": 153.593,
214
+ "step": 600
215
+ },
216
+ {
217
+ "epoch": 13.0,
218
+ "eval_loss": 0.24490594863891602,
219
+ "eval_micro_f1": 0.8348041914468227,
220
+ "eval_runtime": 6.0728,
221
+ "eval_samples_per_second": 165.164,
222
+ "step": 624
223
+ },
224
+ {
225
+ "epoch": 13.5,
226
+ "eval_loss": 0.24209046363830566,
227
+ "eval_micro_f1": 0.8395095738213074,
228
+ "eval_runtime": 6.0983,
229
+ "eval_samples_per_second": 164.471,
230
+ "step": 648
231
+ },
232
+ {
233
+ "epoch": 14.0,
234
+ "eval_loss": 0.24820514023303986,
235
+ "eval_micro_f1": 0.8326227474024123,
236
+ "eval_runtime": 6.4127,
237
+ "eval_samples_per_second": 156.407,
238
+ "step": 672
239
+ },
240
+ {
241
+ "epoch": 14.5,
242
+ "eval_loss": 0.25653138756752014,
243
+ "eval_micro_f1": 0.8367683424511504,
244
+ "eval_runtime": 6.0646,
245
+ "eval_samples_per_second": 165.387,
246
+ "step": 696
247
+ },
248
+ {
249
+ "epoch": 15.0,
250
+ "eval_loss": 0.2563244700431824,
251
+ "eval_micro_f1": 0.8394010161229527,
252
+ "eval_runtime": 6.36,
253
+ "eval_samples_per_second": 157.705,
254
+ "step": 720
255
+ },
256
+ {
257
+ "epoch": 15.5,
258
+ "eval_loss": 0.26074159145355225,
259
+ "eval_micro_f1": 0.8418304241253202,
260
+ "eval_runtime": 5.8817,
261
+ "eval_samples_per_second": 170.528,
262
+ "step": 744
263
+ },
264
+ {
265
+ "epoch": 16.0,
266
+ "eval_loss": 0.26279860734939575,
267
+ "eval_micro_f1": 0.8372411896821719,
268
+ "eval_runtime": 6.3173,
269
+ "eval_samples_per_second": 158.771,
270
+ "step": 768
271
+ },
272
+ {
273
+ "epoch": 16.5,
274
+ "eval_loss": 0.2652227580547333,
275
+ "eval_micro_f1": 0.8411522628742865,
276
+ "eval_runtime": 5.8698,
277
+ "eval_samples_per_second": 170.875,
278
+ "step": 792
279
+ },
280
+ {
281
+ "epoch": 17.0,
282
+ "eval_loss": 0.2626892030239105,
283
+ "eval_micro_f1": 0.8468793337577448,
284
+ "eval_runtime": 6.0919,
285
+ "eval_samples_per_second": 164.644,
286
+ "step": 816
287
+ },
288
+ {
289
+ "epoch": 17.5,
290
+ "eval_loss": 0.2680288255214691,
291
+ "eval_micro_f1": 0.8349993148496747,
292
+ "eval_runtime": 6.3897,
293
+ "eval_samples_per_second": 156.972,
294
+ "step": 840
295
+ },
296
+ {
297
+ "epoch": 18.0,
298
+ "eval_loss": 0.26079022884368896,
299
+ "eval_micro_f1": 0.8468493145683045,
300
+ "eval_runtime": 6.5686,
301
+ "eval_samples_per_second": 152.695,
302
+ "step": 864
303
+ },
304
+ {
305
+ "epoch": 18.5,
306
+ "eval_loss": 0.26652792096138,
307
+ "eval_micro_f1": 0.846419207447885,
308
+ "eval_runtime": 5.9486,
309
+ "eval_samples_per_second": 168.612,
310
+ "step": 888
311
+ },
312
+ {
313
+ "epoch": 19.0,
314
+ "eval_loss": 0.2698013484477997,
315
+ "eval_micro_f1": 0.8414969725322518,
316
+ "eval_runtime": 6.031,
317
+ "eval_samples_per_second": 166.309,
318
+ "step": 912
319
+ },
320
+ {
321
+ "epoch": 19.5,
322
+ "eval_loss": 0.26716122031211853,
323
+ "eval_micro_f1": 0.8425414359638563,
324
+ "eval_runtime": 6.27,
325
+ "eval_samples_per_second": 159.967,
326
+ "step": 936
327
+ },
328
+ {
329
+ "epoch": 20.0,
330
+ "eval_loss": 0.27200189232826233,
331
+ "eval_micro_f1": 0.8454770410175185,
332
+ "eval_runtime": 6.1163,
333
+ "eval_samples_per_second": 163.987,
334
+ "step": 960
335
+ },
336
+ {
337
+ "epoch": 20.5,
338
+ "eval_loss": 0.27574917674064636,
339
+ "eval_micro_f1": 0.8431183825604193,
340
+ "eval_runtime": 8.494,
341
+ "eval_samples_per_second": 118.084,
342
+ "step": 984
343
+ },
344
+ {
345
+ "epoch": 20.83,
346
+ "learning_rate": 9.305555555555557e-06,
347
+ "loss": 0.0254,
348
+ "step": 1000
349
+ },
350
+ {
351
+ "epoch": 21.0,
352
+ "eval_loss": 0.2804272472858429,
353
+ "eval_micro_f1": 0.8444873735855977,
354
+ "eval_runtime": 6.2176,
355
+ "eval_samples_per_second": 161.317,
356
+ "step": 1008
357
+ },
358
+ {
359
+ "epoch": 21.5,
360
+ "eval_loss": 0.2772634029388428,
361
+ "eval_micro_f1": 0.8412938742416919,
362
+ "eval_runtime": 6.1722,
363
+ "eval_samples_per_second": 162.503,
364
+ "step": 1032
365
+ },
366
+ {
367
+ "epoch": 22.0,
368
+ "eval_loss": 0.2732590436935425,
369
+ "eval_micro_f1": 0.8384982930152101,
370
+ "eval_runtime": 9.0717,
371
+ "eval_samples_per_second": 110.564,
372
+ "step": 1056
373
+ },
374
+ {
375
+ "epoch": 22.5,
376
+ "eval_loss": 0.2768493592739105,
377
+ "eval_micro_f1": 0.8461115686121808,
378
+ "eval_runtime": 6.0219,
379
+ "eval_samples_per_second": 166.559,
380
+ "step": 1080
381
+ },
382
+ {
383
+ "epoch": 23.0,
384
+ "eval_loss": 0.2818585932254791,
385
+ "eval_micro_f1": 0.8440919032197414,
386
+ "eval_runtime": 6.1012,
387
+ "eval_samples_per_second": 164.395,
388
+ "step": 1104
389
+ },
390
+ {
391
+ "epoch": 23.5,
392
+ "eval_loss": 0.28745830059051514,
393
+ "eval_micro_f1": 0.841771278296846,
394
+ "eval_runtime": 9.9264,
395
+ "eval_samples_per_second": 101.044,
396
+ "step": 1128
397
+ },
398
+ {
399
+ "epoch": 24.0,
400
+ "eval_loss": 0.29081103205680847,
401
+ "eval_micro_f1": 0.8411651547622235,
402
+ "eval_runtime": 6.3347,
403
+ "eval_samples_per_second": 158.334,
404
+ "step": 1152
405
+ },
406
+ {
407
+ "epoch": 24.5,
408
+ "eval_loss": 0.2879377007484436,
409
+ "eval_micro_f1": 0.8457629441502503,
410
+ "eval_runtime": 6.2616,
411
+ "eval_samples_per_second": 160.183,
412
+ "step": 1176
413
+ },
414
+ {
415
+ "epoch": 25.0,
416
+ "eval_loss": 0.2839908003807068,
417
+ "eval_micro_f1": 0.8430777711489715,
418
+ "eval_runtime": 6.0974,
419
+ "eval_samples_per_second": 164.495,
420
+ "step": 1200
421
+ },
422
+ {
423
+ "epoch": 25.5,
424
+ "eval_loss": 0.2796134948730469,
425
+ "eval_micro_f1": 0.8425099541887948,
426
+ "eval_runtime": 6.3706,
427
+ "eval_samples_per_second": 157.443,
428
+ "step": 1224
429
+ },
430
+ {
431
+ "epoch": 26.0,
432
+ "eval_loss": 0.2904074192047119,
433
+ "eval_micro_f1": 0.8425696162629374,
434
+ "eval_runtime": 6.0586,
435
+ "eval_samples_per_second": 165.551,
436
+ "step": 1248
437
+ },
438
+ {
439
+ "epoch": 26.5,
440
+ "eval_loss": 0.2851482033729553,
441
+ "eval_micro_f1": 0.8490044242785261,
442
+ "eval_runtime": 6.3763,
443
+ "eval_samples_per_second": 157.302,
444
+ "step": 1272
445
+ },
446
+ {
447
+ "epoch": 27.0,
448
+ "eval_loss": 0.2814634442329407,
449
+ "eval_micro_f1": 0.845024021462732,
450
+ "eval_runtime": 6.3013,
451
+ "eval_samples_per_second": 159.173,
452
+ "step": 1296
453
+ },
454
+ {
455
+ "epoch": 27.5,
456
+ "eval_loss": 0.2927158772945404,
457
+ "eval_micro_f1": 0.8454432643556927,
458
+ "eval_runtime": 6.4777,
459
+ "eval_samples_per_second": 154.838,
460
+ "step": 1320
461
+ },
462
+ {
463
+ "epoch": 28.0,
464
+ "eval_loss": 0.2913835048675537,
465
+ "eval_micro_f1": 0.8525179851112751,
466
+ "eval_runtime": 6.0062,
467
+ "eval_samples_per_second": 166.995,
468
+ "step": 1344
469
+ },
470
+ {
471
+ "epoch": 28.5,
472
+ "eval_loss": 0.289249449968338,
473
+ "eval_micro_f1": 0.8486017352760508,
474
+ "eval_runtime": 6.3904,
475
+ "eval_samples_per_second": 156.955,
476
+ "step": 1368
477
+ },
478
+ {
479
+ "epoch": 29.0,
480
+ "eval_loss": 0.2902076840400696,
481
+ "eval_micro_f1": 0.8464501921249857,
482
+ "eval_runtime": 6.7322,
483
+ "eval_samples_per_second": 148.985,
484
+ "step": 1392
485
+ },
486
+ {
487
+ "epoch": 29.5,
488
+ "eval_loss": 0.29000627994537354,
489
+ "eval_micro_f1": 0.8463227217830025,
490
+ "eval_runtime": 6.226,
491
+ "eval_samples_per_second": 161.099,
492
+ "step": 1416
493
+ },
494
+ {
495
+ "epoch": 30.0,
496
+ "eval_loss": 0.2924293577671051,
497
+ "eval_micro_f1": 0.8505652049036853,
498
+ "eval_runtime": 6.0131,
499
+ "eval_samples_per_second": 166.801,
500
+ "step": 1440
501
+ },
502
+ {
503
+ "epoch": 30.5,
504
+ "eval_loss": 0.29464036226272583,
505
+ "eval_micro_f1": 0.8510638292870268,
506
+ "eval_runtime": 6.2792,
507
+ "eval_samples_per_second": 159.735,
508
+ "step": 1464
509
+ },
510
+ {
511
+ "epoch": 31.0,
512
+ "eval_loss": 0.2963722348213196,
513
+ "eval_micro_f1": 0.8486257344923084,
514
+ "eval_runtime": 6.2548,
515
+ "eval_samples_per_second": 160.356,
516
+ "step": 1488
517
+ },
518
+ {
519
+ "epoch": 31.25,
520
+ "learning_rate": 8.958333333333334e-06,
521
+ "loss": 0.008,
522
+ "step": 1500
523
+ },
524
+ {
525
+ "epoch": 31.5,
526
+ "eval_loss": 0.2964193820953369,
527
+ "eval_micro_f1": 0.8495672477481732,
528
+ "eval_runtime": 5.907,
529
+ "eval_samples_per_second": 169.799,
530
+ "step": 1512
531
+ },
532
+ {
533
+ "epoch": 32.0,
534
+ "eval_loss": 0.2991025149822235,
535
+ "eval_micro_f1": 0.8481618144513184,
536
+ "eval_runtime": 5.988,
537
+ "eval_samples_per_second": 167.5,
538
+ "step": 1536
539
+ },
540
+ {
541
+ "epoch": 32.5,
542
+ "eval_loss": 0.30083808302879333,
543
+ "eval_micro_f1": 0.8532084820114783,
544
+ "eval_runtime": 6.059,
545
+ "eval_samples_per_second": 165.539,
546
+ "step": 1560
547
+ },
548
+ {
549
+ "epoch": 33.0,
550
+ "eval_loss": 0.29919904470443726,
551
+ "eval_micro_f1": 0.8511749342256337,
552
+ "eval_runtime": 6.0406,
553
+ "eval_samples_per_second": 166.044,
554
+ "step": 1584
555
+ },
556
+ {
557
+ "epoch": 33.5,
558
+ "eval_loss": 0.30297034978866577,
559
+ "eval_micro_f1": 0.8507298259938528,
560
+ "eval_runtime": 5.7666,
561
+ "eval_samples_per_second": 173.934,
562
+ "step": 1608
563
+ },
564
+ {
565
+ "epoch": 34.0,
566
+ "eval_loss": 0.31402286887168884,
567
+ "eval_micro_f1": 0.8461964033725182,
568
+ "eval_runtime": 5.8909,
569
+ "eval_samples_per_second": 170.263,
570
+ "step": 1632
571
+ },
572
+ {
573
+ "epoch": 34.5,
574
+ "eval_loss": 0.30535468459129333,
575
+ "eval_micro_f1": 0.8467897487419885,
576
+ "eval_runtime": 9.2324,
577
+ "eval_samples_per_second": 108.639,
578
+ "step": 1656
579
+ },
580
+ {
581
+ "epoch": 35.0,
582
+ "eval_loss": 0.3078806698322296,
583
+ "eval_micro_f1": 0.8474436498571246,
584
+ "eval_runtime": 6.0346,
585
+ "eval_samples_per_second": 166.209,
586
+ "step": 1680
587
+ },
588
+ {
589
+ "epoch": 35.5,
590
+ "eval_loss": 0.30856069922447205,
591
+ "eval_micro_f1": 0.848934707403564,
592
+ "eval_runtime": 6.221,
593
+ "eval_samples_per_second": 161.228,
594
+ "step": 1704
595
+ },
596
+ {
597
+ "epoch": 36.0,
598
+ "eval_loss": 0.310249000787735,
599
+ "eval_micro_f1": 0.8474343095836978,
600
+ "eval_runtime": 8.9601,
601
+ "eval_samples_per_second": 111.941,
602
+ "step": 1728
603
+ },
604
+ {
605
+ "epoch": 36.5,
606
+ "eval_loss": 0.3153418302536011,
607
+ "eval_micro_f1": 0.8441700955217479,
608
+ "eval_runtime": 6.2978,
609
+ "eval_samples_per_second": 159.262,
610
+ "step": 1752
611
+ },
612
+ {
613
+ "epoch": 37.0,
614
+ "eval_loss": 0.30738189816474915,
615
+ "eval_micro_f1": 0.8492096214929111,
616
+ "eval_runtime": 5.8592,
617
+ "eval_samples_per_second": 171.183,
618
+ "step": 1776
619
+ },
620
+ {
621
+ "epoch": 37.5,
622
+ "eval_loss": 0.31066763401031494,
623
+ "eval_micro_f1": 0.8501100105008814,
624
+ "eval_runtime": 8.982,
625
+ "eval_samples_per_second": 111.668,
626
+ "step": 1800
627
+ },
628
+ {
629
+ "epoch": 38.0,
630
+ "eval_loss": 0.3155709207057953,
631
+ "eval_micro_f1": 0.849417636770983,
632
+ "eval_runtime": 5.9468,
633
+ "eval_samples_per_second": 168.661,
634
+ "step": 1824
635
+ },
636
+ {
637
+ "epoch": 38.5,
638
+ "eval_loss": 0.30841168761253357,
639
+ "eval_micro_f1": 0.8464070208931094,
640
+ "eval_runtime": 6.2933,
641
+ "eval_samples_per_second": 159.375,
642
+ "step": 1848
643
+ },
644
+ {
645
+ "epoch": 39.0,
646
+ "eval_loss": 0.31119850277900696,
647
+ "eval_micro_f1": 0.8525174916111974,
648
+ "eval_runtime": 5.9779,
649
+ "eval_samples_per_second": 167.785,
650
+ "step": 1872
651
+ },
652
+ {
653
+ "epoch": 39.5,
654
+ "eval_loss": 0.32061535120010376,
655
+ "eval_micro_f1": 0.8513047074936912,
656
+ "eval_runtime": 5.8262,
657
+ "eval_samples_per_second": 172.153,
658
+ "step": 1896
659
+ },
660
+ {
661
+ "epoch": 40.0,
662
+ "eval_loss": 0.3138852119445801,
663
+ "eval_micro_f1": 0.8493752569486447,
664
+ "eval_runtime": 6.1285,
665
+ "eval_samples_per_second": 163.662,
666
+ "step": 1920
667
+ },
668
+ {
669
+ "epoch": 40.5,
670
+ "eval_loss": 0.31410863995552063,
671
+ "eval_micro_f1": 0.8491497526539425,
672
+ "eval_runtime": 6.1391,
673
+ "eval_samples_per_second": 163.38,
674
+ "step": 1944
675
+ },
676
+ {
677
+ "epoch": 41.0,
678
+ "eval_loss": 0.3184076249599457,
679
+ "eval_micro_f1": 0.8503391937403856,
680
+ "eval_runtime": 5.8782,
681
+ "eval_samples_per_second": 170.629,
682
+ "step": 1968
683
+ },
684
+ {
685
+ "epoch": 41.5,
686
+ "eval_loss": 0.3144913911819458,
687
+ "eval_micro_f1": 0.8504302685887637,
688
+ "eval_runtime": 6.3221,
689
+ "eval_samples_per_second": 158.65,
690
+ "step": 1992
691
+ },
692
+ {
693
+ "epoch": 41.67,
694
+ "learning_rate": 8.611111111111112e-06,
695
+ "loss": 0.0036,
696
+ "step": 2000
697
+ },
698
+ {
699
+ "epoch": 42.0,
700
+ "eval_loss": 0.3145175576210022,
701
+ "eval_micro_f1": 0.849594054818341,
702
+ "eval_runtime": 6.7679,
703
+ "eval_samples_per_second": 148.199,
704
+ "step": 2016
705
+ },
706
+ {
707
+ "epoch": 42.5,
708
+ "eval_loss": 0.3162612318992615,
709
+ "eval_micro_f1": 0.8481861733533427,
710
+ "eval_runtime": 5.8201,
711
+ "eval_samples_per_second": 172.332,
712
+ "step": 2040
713
+ },
714
+ {
715
+ "epoch": 43.0,
716
+ "eval_loss": 0.3216666579246521,
717
+ "eval_micro_f1": 0.8520204104775647,
718
+ "eval_runtime": 5.6573,
719
+ "eval_samples_per_second": 177.294,
720
+ "step": 2064
721
+ },
722
+ {
723
+ "epoch": 43.5,
724
+ "eval_loss": 0.32895880937576294,
725
+ "eval_micro_f1": 0.8503674936059948,
726
+ "eval_runtime": 5.8628,
727
+ "eval_samples_per_second": 171.078,
728
+ "step": 2088
729
+ },
730
+ {
731
+ "epoch": 44.0,
732
+ "eval_loss": 0.3290811777114868,
733
+ "eval_micro_f1": 0.8527345359372976,
734
+ "eval_runtime": 6.1149,
735
+ "eval_samples_per_second": 164.027,
736
+ "step": 2112
737
+ },
738
+ {
739
+ "epoch": 44.5,
740
+ "eval_loss": 0.3273111581802368,
741
+ "eval_micro_f1": 0.8544277642704653,
742
+ "eval_runtime": 5.8979,
743
+ "eval_samples_per_second": 170.06,
744
+ "step": 2136
745
+ },
746
+ {
747
+ "epoch": 45.0,
748
+ "eval_loss": 0.3250843286514282,
749
+ "eval_micro_f1": 0.8488516017553166,
750
+ "eval_runtime": 5.9627,
751
+ "eval_samples_per_second": 168.213,
752
+ "step": 2160
753
+ },
754
+ {
755
+ "epoch": 45.5,
756
+ "eval_loss": 0.32967016100883484,
757
+ "eval_micro_f1": 0.8456449829617348,
758
+ "eval_runtime": 8.9687,
759
+ "eval_samples_per_second": 111.834,
760
+ "step": 2184
761
+ },
762
+ {
763
+ "epoch": 46.0,
764
+ "eval_loss": 0.3291603624820709,
765
+ "eval_micro_f1": 0.8507236383695155,
766
+ "eval_runtime": 6.0794,
767
+ "eval_samples_per_second": 164.983,
768
+ "step": 2208
769
+ },
770
+ {
771
+ "epoch": 46.5,
772
+ "eval_loss": 0.3306710124015808,
773
+ "eval_micro_f1": 0.8527153039430255,
774
+ "eval_runtime": 5.8369,
775
+ "eval_samples_per_second": 171.838,
776
+ "step": 2232
777
+ },
778
+ {
779
+ "epoch": 47.0,
780
+ "eval_loss": 0.3293270766735077,
781
+ "eval_micro_f1": 0.8468148951484756,
782
+ "eval_runtime": 6.1375,
783
+ "eval_samples_per_second": 163.42,
784
+ "step": 2256
785
+ },
786
+ {
787
+ "epoch": 47.5,
788
+ "eval_loss": 0.34013232588768005,
789
+ "eval_micro_f1": 0.8484257448327537,
790
+ "eval_runtime": 6.2118,
791
+ "eval_samples_per_second": 161.467,
792
+ "step": 2280
793
+ },
794
+ {
795
+ "epoch": 48.0,
796
+ "eval_loss": 0.33161190152168274,
797
+ "eval_micro_f1": 0.8463024277558394,
798
+ "eval_runtime": 6.0255,
799
+ "eval_samples_per_second": 166.458,
800
+ "step": 2304
801
+ },
802
+ {
803
+ "epoch": 48.5,
804
+ "eval_loss": 0.32816997170448303,
805
+ "eval_micro_f1": 0.8515506542206523,
806
+ "eval_runtime": 5.8808,
807
+ "eval_samples_per_second": 170.554,
808
+ "step": 2328
809
+ },
810
+ {
811
+ "epoch": 49.0,
812
+ "eval_loss": 0.3282072842121124,
813
+ "eval_micro_f1": 0.8534732766714263,
814
+ "eval_runtime": 5.9773,
815
+ "eval_samples_per_second": 167.802,
816
+ "step": 2352
817
+ },
818
+ {
819
+ "epoch": 49.5,
820
+ "eval_loss": 0.33128488063812256,
821
+ "eval_micro_f1": 0.853270639798478,
822
+ "eval_runtime": 6.3934,
823
+ "eval_samples_per_second": 156.88,
824
+ "step": 2376
825
+ },
826
+ {
827
+ "epoch": 50.0,
828
+ "eval_loss": 0.3289351165294647,
829
+ "eval_micro_f1": 0.848958332833139,
830
+ "eval_runtime": 6.0749,
831
+ "eval_samples_per_second": 165.106,
832
+ "step": 2400
833
+ },
834
+ {
835
+ "epoch": 50.5,
836
+ "eval_loss": 0.3343229591846466,
837
+ "eval_micro_f1": 0.8525764668461479,
838
+ "eval_runtime": 6.0397,
839
+ "eval_samples_per_second": 166.068,
840
+ "step": 2424
841
+ },
842
+ {
843
+ "epoch": 51.0,
844
+ "eval_loss": 0.33142992854118347,
845
+ "eval_micro_f1": 0.8509291116814691,
846
+ "eval_runtime": 6.1654,
847
+ "eval_samples_per_second": 162.682,
848
+ "step": 2448
849
+ },
850
+ {
851
+ "epoch": 51.5,
852
+ "eval_loss": 0.3288741707801819,
853
+ "eval_micro_f1": 0.8547854780476348,
854
+ "eval_runtime": 6.0434,
855
+ "eval_samples_per_second": 165.966,
856
+ "step": 2472
857
+ },
858
+ {
859
+ "epoch": 52.0,
860
+ "eval_loss": 0.3286861181259155,
861
+ "eval_micro_f1": 0.8542437949200667,
862
+ "eval_runtime": 5.9527,
863
+ "eval_samples_per_second": 168.496,
864
+ "step": 2496
865
+ },
866
+ {
867
+ "epoch": 52.08,
868
+ "learning_rate": 8.263888888888888e-06,
869
+ "loss": 0.002,
870
+ "step": 2500
871
+ },
872
+ {
873
+ "epoch": 52.5,
874
+ "eval_loss": 0.32903286814689636,
875
+ "eval_micro_f1": 0.8551324498308923,
876
+ "eval_runtime": 5.7535,
877
+ "eval_samples_per_second": 174.329,
878
+ "step": 2520
879
+ },
880
+ {
881
+ "epoch": 53.0,
882
+ "eval_loss": 0.33099424839019775,
883
+ "eval_micro_f1": 0.850929977617989,
884
+ "eval_runtime": 6.7595,
885
+ "eval_samples_per_second": 148.384,
886
+ "step": 2544
887
+ },
888
+ {
889
+ "epoch": 53.5,
890
+ "eval_loss": 0.33220967650413513,
891
+ "eval_micro_f1": 0.8531970717273579,
892
+ "eval_runtime": 6.1864,
893
+ "eval_samples_per_second": 162.129,
894
+ "step": 2568
895
+ },
896
+ {
897
+ "epoch": 54.0,
898
+ "eval_loss": 0.33008280396461487,
899
+ "eval_micro_f1": 0.8516641550949353,
900
+ "eval_runtime": 5.9901,
901
+ "eval_samples_per_second": 167.443,
902
+ "step": 2592
903
+ },
904
+ {
905
+ "epoch": 54.5,
906
+ "eval_loss": 0.3372100591659546,
907
+ "eval_micro_f1": 0.8543769874682328,
908
+ "eval_runtime": 5.7489,
909
+ "eval_samples_per_second": 174.469,
910
+ "step": 2616
911
+ },
912
+ {
913
+ "epoch": 55.0,
914
+ "eval_loss": 0.3379433751106262,
915
+ "eval_micro_f1": 0.8535645467059416,
916
+ "eval_runtime": 6.0943,
917
+ "eval_samples_per_second": 164.58,
918
+ "step": 2640
919
+ },
920
+ {
921
+ "epoch": 55.5,
922
+ "eval_loss": 0.33973467350006104,
923
+ "eval_micro_f1": 0.8511986768213481,
924
+ "eval_runtime": 6.2932,
925
+ "eval_samples_per_second": 159.378,
926
+ "step": 2664
927
+ },
928
+ {
929
+ "epoch": 56.0,
930
+ "eval_loss": 0.33183470368385315,
931
+ "eval_micro_f1": 0.8446562282269136,
932
+ "eval_runtime": 6.1639,
933
+ "eval_samples_per_second": 162.72,
934
+ "step": 2688
935
+ },
936
+ {
937
+ "epoch": 56.5,
938
+ "eval_loss": 0.32909512519836426,
939
+ "eval_micro_f1": 0.8533663770297203,
940
+ "eval_runtime": 6.0981,
941
+ "eval_samples_per_second": 164.478,
942
+ "step": 2712
943
+ },
944
+ {
945
+ "epoch": 57.0,
946
+ "eval_loss": 0.333426833152771,
947
+ "eval_micro_f1": 0.8543956038953913,
948
+ "eval_runtime": 6.0494,
949
+ "eval_samples_per_second": 165.802,
950
+ "step": 2736
951
+ },
952
+ {
953
+ "epoch": 57.5,
954
+ "eval_loss": 0.33772042393684387,
955
+ "eval_micro_f1": 0.8485263874367477,
956
+ "eval_runtime": 5.8869,
957
+ "eval_samples_per_second": 170.378,
958
+ "step": 2760
959
+ },
960
+ {
961
+ "epoch": 58.0,
962
+ "eval_loss": 0.3450329303741455,
963
+ "eval_micro_f1": 0.8483764441888267,
964
+ "eval_runtime": 6.2394,
965
+ "eval_samples_per_second": 160.753,
966
+ "step": 2784
967
+ },
968
+ {
969
+ "epoch": 58.5,
970
+ "eval_loss": 0.340576708316803,
971
+ "eval_micro_f1": 0.8493563402283809,
972
+ "eval_runtime": 6.2854,
973
+ "eval_samples_per_second": 159.576,
974
+ "step": 2808
975
+ },
976
+ {
977
+ "epoch": 59.0,
978
+ "eval_loss": 0.34551429748535156,
979
+ "eval_micro_f1": 0.8554881407021946,
980
+ "eval_runtime": 5.9139,
981
+ "eval_samples_per_second": 169.601,
982
+ "step": 2832
983
+ },
984
+ {
985
+ "epoch": 59.5,
986
+ "eval_loss": 0.3404690623283386,
987
+ "eval_micro_f1": 0.8519637457233545,
988
+ "eval_runtime": 6.1053,
989
+ "eval_samples_per_second": 164.283,
990
+ "step": 2856
991
+ },
992
+ {
993
+ "epoch": 60.0,
994
+ "eval_loss": 0.3353828191757202,
995
+ "eval_micro_f1": 0.8525983815099478,
996
+ "eval_runtime": 6.0235,
997
+ "eval_samples_per_second": 166.515,
998
+ "step": 2880
999
+ },
1000
+ {
1001
+ "epoch": 60.5,
1002
+ "eval_loss": 0.33774691820144653,
1003
+ "eval_micro_f1": 0.8539171136399364,
1004
+ "eval_runtime": 6.759,
1005
+ "eval_samples_per_second": 148.394,
1006
+ "step": 2904
1007
+ },
1008
+ {
1009
+ "epoch": 61.0,
1010
+ "eval_loss": 0.33614590764045715,
1011
+ "eval_micro_f1": 0.8552613522230775,
1012
+ "eval_runtime": 5.8257,
1013
+ "eval_samples_per_second": 172.168,
1014
+ "step": 2928
1015
+ },
1016
+ {
1017
+ "epoch": 61.5,
1018
+ "eval_loss": 0.34379926323890686,
1019
+ "eval_micro_f1": 0.8556001656357184,
1020
+ "eval_runtime": 5.7605,
1021
+ "eval_samples_per_second": 174.118,
1022
+ "step": 2952
1023
+ },
1024
+ {
1025
+ "epoch": 62.0,
1026
+ "eval_loss": 0.33785271644592285,
1027
+ "eval_micro_f1": 0.8527430216364513,
1028
+ "eval_runtime": 6.3493,
1029
+ "eval_samples_per_second": 157.971,
1030
+ "step": 2976
1031
+ },
1032
+ {
1033
+ "epoch": 62.5,
1034
+ "learning_rate": 7.916666666666667e-06,
1035
+ "loss": 0.0015,
1036
+ "step": 3000
1037
+ },
1038
+ {
1039
+ "epoch": 62.5,
1040
+ "eval_loss": 0.3425731062889099,
1041
+ "eval_micro_f1": 0.853171872349646,
1042
+ "eval_runtime": 8.598,
1043
+ "eval_samples_per_second": 116.655,
1044
+ "step": 3000
1045
+ },
1046
+ {
1047
+ "epoch": 63.0,
1048
+ "eval_loss": 0.3453591763973236,
1049
+ "eval_micro_f1": 0.8541609442951749,
1050
+ "eval_runtime": 6.4746,
1051
+ "eval_samples_per_second": 154.913,
1052
+ "step": 3024
1053
+ },
1054
+ {
1055
+ "epoch": 63.5,
1056
+ "eval_loss": 0.3501335084438324,
1057
+ "eval_micro_f1": 0.8550504347629945,
1058
+ "eval_runtime": 5.9983,
1059
+ "eval_samples_per_second": 167.214,
1060
+ "step": 3048
1061
+ },
1062
+ {
1063
+ "epoch": 64.0,
1064
+ "eval_loss": 0.3514552116394043,
1065
+ "eval_micro_f1": 0.8477366250142022,
1066
+ "eval_runtime": 6.3077,
1067
+ "eval_samples_per_second": 159.012,
1068
+ "step": 3072
1069
+ },
1070
+ {
1071
+ "epoch": 64.5,
1072
+ "eval_loss": 0.3520335555076599,
1073
+ "eval_micro_f1": 0.8502681144454716,
1074
+ "eval_runtime": 6.2592,
1075
+ "eval_samples_per_second": 160.244,
1076
+ "step": 3096
1077
+ },
1078
+ {
1079
+ "epoch": 65.0,
1080
+ "eval_loss": 0.3587789535522461,
1081
+ "eval_micro_f1": 0.8504155119651399,
1082
+ "eval_runtime": 5.9962,
1083
+ "eval_samples_per_second": 167.273,
1084
+ "step": 3120
1085
+ },
1086
+ {
1087
+ "epoch": 65.5,
1088
+ "eval_loss": 0.34796902537345886,
1089
+ "eval_micro_f1": 0.8516574580633011,
1090
+ "eval_runtime": 6.318,
1091
+ "eval_samples_per_second": 158.754,
1092
+ "step": 3144
1093
+ },
1094
+ {
1095
+ "epoch": 66.0,
1096
+ "eval_loss": 0.34063753485679626,
1097
+ "eval_micro_f1": 0.8540689650170088,
1098
+ "eval_runtime": 5.9339,
1099
+ "eval_samples_per_second": 169.029,
1100
+ "step": 3168
1101
+ },
1102
+ {
1103
+ "epoch": 66.5,
1104
+ "eval_loss": 0.341467022895813,
1105
+ "eval_micro_f1": 0.8573788541253242,
1106
+ "eval_runtime": 6.16,
1107
+ "eval_samples_per_second": 162.826,
1108
+ "step": 3192
1109
+ },
1110
+ {
1111
+ "epoch": 67.0,
1112
+ "eval_loss": 0.3511905074119568,
1113
+ "eval_micro_f1": 0.8540885737049632,
1114
+ "eval_runtime": 6.1041,
1115
+ "eval_samples_per_second": 164.317,
1116
+ "step": 3216
1117
+ },
1118
+ {
1119
+ "epoch": 67.5,
1120
+ "eval_loss": 0.3426903188228607,
1121
+ "eval_micro_f1": 0.8565127493274739,
1122
+ "eval_runtime": 6.6022,
1123
+ "eval_samples_per_second": 151.919,
1124
+ "step": 3240
1125
+ },
1126
+ {
1127
+ "epoch": 68.0,
1128
+ "eval_loss": 0.34657588601112366,
1129
+ "eval_micro_f1": 0.8525720585261094,
1130
+ "eval_runtime": 6.5244,
1131
+ "eval_samples_per_second": 153.731,
1132
+ "step": 3264
1133
+ },
1134
+ {
1135
+ "epoch": 68.5,
1136
+ "eval_loss": 0.34785816073417664,
1137
+ "eval_micro_f1": 0.8562725001920929,
1138
+ "eval_runtime": 6.2324,
1139
+ "eval_samples_per_second": 160.932,
1140
+ "step": 3288
1141
+ },
1142
+ {
1143
+ "epoch": 69.0,
1144
+ "eval_loss": 0.3417331576347351,
1145
+ "eval_micro_f1": 0.853373642484531,
1146
+ "eval_runtime": 6.2335,
1147
+ "eval_samples_per_second": 160.904,
1148
+ "step": 3312
1149
+ },
1150
+ {
1151
+ "epoch": 69.5,
1152
+ "eval_loss": 0.34264498949050903,
1153
+ "eval_micro_f1": 0.8529048202661667,
1154
+ "eval_runtime": 6.3502,
1155
+ "eval_samples_per_second": 157.947,
1156
+ "step": 3336
1157
+ },
1158
+ {
1159
+ "epoch": 70.0,
1160
+ "eval_loss": 0.3420845866203308,
1161
+ "eval_micro_f1": 0.8584853505224274,
1162
+ "eval_runtime": 5.7697,
1163
+ "eval_samples_per_second": 173.839,
1164
+ "step": 3360
1165
+ },
1166
+ {
1167
+ "epoch": 70.5,
1168
+ "eval_loss": 0.34508171677589417,
1169
+ "eval_micro_f1": 0.852513501784767,
1170
+ "eval_runtime": 8.8802,
1171
+ "eval_samples_per_second": 112.948,
1172
+ "step": 3384
1173
+ },
1174
+ {
1175
+ "epoch": 71.0,
1176
+ "eval_loss": 0.3419511914253235,
1177
+ "eval_micro_f1": 0.8503699638736089,
1178
+ "eval_runtime": 5.9241,
1179
+ "eval_samples_per_second": 169.308,
1180
+ "step": 3408
1181
+ },
1182
+ {
1183
+ "epoch": 71.5,
1184
+ "eval_loss": 0.34192588925361633,
1185
+ "eval_micro_f1": 0.8539171136399364,
1186
+ "eval_runtime": 5.924,
1187
+ "eval_samples_per_second": 169.311,
1188
+ "step": 3432
1189
+ },
1190
+ {
1191
+ "epoch": 72.0,
1192
+ "eval_loss": 0.3473137617111206,
1193
+ "eval_micro_f1": 0.8556016592508007,
1194
+ "eval_runtime": 5.9289,
1195
+ "eval_samples_per_second": 169.172,
1196
+ "step": 3456
1197
+ },
1198
+ {
1199
+ "epoch": 72.5,
1200
+ "eval_loss": 0.34460851550102234,
1201
+ "eval_micro_f1": 0.8527472522470402,
1202
+ "eval_runtime": 5.7178,
1203
+ "eval_samples_per_second": 175.418,
1204
+ "step": 3480
1205
+ },
1206
+ {
1207
+ "epoch": 72.92,
1208
+ "learning_rate": 7.569444444444445e-06,
1209
+ "loss": 0.0011,
1210
+ "step": 3500
1211
+ },
1212
+ {
1213
+ "epoch": 73.0,
1214
+ "eval_loss": 0.34844404458999634,
1215
+ "eval_micro_f1": 0.8531642074137356,
1216
+ "eval_runtime": 5.6024,
1217
+ "eval_samples_per_second": 179.03,
1218
+ "step": 3504
1219
+ },
1220
+ {
1221
+ "epoch": 73.5,
1222
+ "eval_loss": 0.3471376597881317,
1223
+ "eval_micro_f1": 0.8531756937532877,
1224
+ "eval_runtime": 5.5814,
1225
+ "eval_samples_per_second": 179.705,
1226
+ "step": 3528
1227
+ },
1228
+ {
1229
+ "epoch": 74.0,
1230
+ "eval_loss": 0.34734970331192017,
1231
+ "eval_micro_f1": 0.8544303792466125,
1232
+ "eval_runtime": 6.0314,
1233
+ "eval_samples_per_second": 166.296,
1234
+ "step": 3552
1235
+ },
1236
+ {
1237
+ "epoch": 74.5,
1238
+ "eval_loss": 0.3543611764907837,
1239
+ "eval_micro_f1": 0.853628195767905,
1240
+ "eval_runtime": 5.7411,
1241
+ "eval_samples_per_second": 174.706,
1242
+ "step": 3576
1243
+ },
1244
+ {
1245
+ "epoch": 75.0,
1246
+ "eval_loss": 0.35149452090263367,
1247
+ "eval_micro_f1": 0.8507112272307422,
1248
+ "eval_runtime": 8.9533,
1249
+ "eval_samples_per_second": 112.025,
1250
+ "step": 3600
1251
+ },
1252
+ {
1253
+ "epoch": 75.5,
1254
+ "eval_loss": 0.35118862986564636,
1255
+ "eval_micro_f1": 0.8526619887692789,
1256
+ "eval_runtime": 5.6822,
1257
+ "eval_samples_per_second": 176.515,
1258
+ "step": 3624
1259
+ },
1260
+ {
1261
+ "epoch": 76.0,
1262
+ "eval_loss": 0.3524828553199768,
1263
+ "eval_micro_f1": 0.8578505568136601,
1264
+ "eval_runtime": 5.6765,
1265
+ "eval_samples_per_second": 176.693,
1266
+ "step": 3648
1267
+ },
1268
+ {
1269
+ "epoch": 76.5,
1270
+ "eval_loss": 0.3460742235183716,
1271
+ "eval_micro_f1": 0.8519934457041062,
1272
+ "eval_runtime": 5.7029,
1273
+ "eval_samples_per_second": 175.876,
1274
+ "step": 3672
1275
+ },
1276
+ {
1277
+ "epoch": 77.0,
1278
+ "eval_loss": 0.34593841433525085,
1279
+ "eval_micro_f1": 0.8539823003847196,
1280
+ "eval_runtime": 5.5593,
1281
+ "eval_samples_per_second": 180.419,
1282
+ "step": 3696
1283
+ },
1284
+ {
1285
+ "epoch": 77.5,
1286
+ "eval_loss": 0.3435734808444977,
1287
+ "eval_micro_f1": 0.8543502197640915,
1288
+ "eval_runtime": 5.5691,
1289
+ "eval_samples_per_second": 180.099,
1290
+ "step": 3720
1291
+ },
1292
+ {
1293
+ "epoch": 78.0,
1294
+ "eval_loss": 0.34400710463523865,
1295
+ "eval_micro_f1": 0.854465269621049,
1296
+ "eval_runtime": 5.8316,
1297
+ "eval_samples_per_second": 171.993,
1298
+ "step": 3744
1299
+ },
1300
+ {
1301
+ "epoch": 78.5,
1302
+ "eval_loss": 0.33947327733039856,
1303
+ "eval_micro_f1": 0.8509874321748107,
1304
+ "eval_runtime": 6.2684,
1305
+ "eval_samples_per_second": 160.009,
1306
+ "step": 3768
1307
+ },
1308
+ {
1309
+ "epoch": 79.0,
1310
+ "eval_loss": 0.3416493535041809,
1311
+ "eval_micro_f1": 0.8496479354379136,
1312
+ "eval_runtime": 5.6672,
1313
+ "eval_samples_per_second": 176.983,
1314
+ "step": 3792
1315
+ },
1316
+ {
1317
+ "epoch": 79.5,
1318
+ "eval_loss": 0.348812460899353,
1319
+ "eval_micro_f1": 0.8516984253489787,
1320
+ "eval_runtime": 5.7239,
1321
+ "eval_samples_per_second": 175.231,
1322
+ "step": 3816
1323
+ },
1324
+ {
1325
+ "epoch": 80.0,
1326
+ "eval_loss": 0.34709683060646057,
1327
+ "eval_micro_f1": 0.8521571855399067,
1328
+ "eval_runtime": 5.8615,
1329
+ "eval_samples_per_second": 171.116,
1330
+ "step": 3840
1331
+ },
1332
+ {
1333
+ "epoch": 80.5,
1334
+ "eval_loss": 0.34579169750213623,
1335
+ "eval_micro_f1": 0.8540807909260013,
1336
+ "eval_runtime": 6.1261,
1337
+ "eval_samples_per_second": 163.725,
1338
+ "step": 3864
1339
+ },
1340
+ {
1341
+ "epoch": 81.0,
1342
+ "eval_loss": 0.3537646532058716,
1343
+ "eval_micro_f1": 0.8519587623863811,
1344
+ "eval_runtime": 5.8368,
1345
+ "eval_samples_per_second": 171.84,
1346
+ "step": 3888
1347
+ },
1348
+ {
1349
+ "epoch": 81.5,
1350
+ "eval_loss": 0.353626012802124,
1351
+ "eval_micro_f1": 0.8530831833872001,
1352
+ "eval_runtime": 5.872,
1353
+ "eval_samples_per_second": 170.811,
1354
+ "step": 3912
1355
+ },
1356
+ {
1357
+ "epoch": 82.0,
1358
+ "eval_loss": 0.3480609059333801,
1359
+ "eval_micro_f1": 0.848767122787482,
1360
+ "eval_runtime": 5.7421,
1361
+ "eval_samples_per_second": 174.676,
1362
+ "step": 3936
1363
+ },
1364
+ {
1365
+ "epoch": 82.5,
1366
+ "eval_loss": 0.3502531945705414,
1367
+ "eval_micro_f1": 0.8530140374849123,
1368
+ "eval_runtime": 5.8972,
1369
+ "eval_samples_per_second": 170.081,
1370
+ "step": 3960
1371
+ },
1372
+ {
1373
+ "epoch": 83.0,
1374
+ "eval_loss": 0.3507061004638672,
1375
+ "eval_micro_f1": 0.8517089300400132,
1376
+ "eval_runtime": 5.6921,
1377
+ "eval_samples_per_second": 176.208,
1378
+ "step": 3984
1379
+ },
1380
+ {
1381
+ "epoch": 83.33,
1382
+ "learning_rate": 7.222222222222223e-06,
1383
+ "loss": 0.0008,
1384
+ "step": 4000
1385
+ },
1386
+ {
1387
+ "epoch": 83.5,
1388
+ "eval_loss": 0.34787294268608093,
1389
+ "eval_micro_f1": 0.8554865419428296,
1390
+ "eval_runtime": 5.4924,
1391
+ "eval_samples_per_second": 182.617,
1392
+ "step": 4008
1393
+ },
1394
+ {
1395
+ "epoch": 84.0,
1396
+ "eval_loss": 0.3475159704685211,
1397
+ "eval_micro_f1": 0.8558434394115667,
1398
+ "eval_runtime": 5.9916,
1399
+ "eval_samples_per_second": 167.4,
1400
+ "step": 4032
1401
+ },
1402
+ {
1403
+ "epoch": 84.5,
1404
+ "eval_loss": 0.35441136360168457,
1405
+ "eval_micro_f1": 0.8564692825395669,
1406
+ "eval_runtime": 5.6875,
1407
+ "eval_samples_per_second": 176.352,
1408
+ "step": 4056
1409
+ },
1410
+ {
1411
+ "epoch": 85.0,
1412
+ "eval_loss": 0.34438231587409973,
1413
+ "eval_micro_f1": 0.8563954283859084,
1414
+ "eval_runtime": 5.6085,
1415
+ "eval_samples_per_second": 178.837,
1416
+ "step": 4080
1417
+ },
1418
+ {
1419
+ "epoch": 85.5,
1420
+ "eval_loss": 0.34063827991485596,
1421
+ "eval_micro_f1": 0.8483769341662961,
1422
+ "eval_runtime": 5.5764,
1423
+ "eval_samples_per_second": 179.865,
1424
+ "step": 4104
1425
+ },
1426
+ {
1427
+ "epoch": 86.0,
1428
+ "eval_loss": 0.3490903675556183,
1429
+ "eval_micro_f1": 0.851181428268592,
1430
+ "eval_runtime": 5.7933,
1431
+ "eval_samples_per_second": 173.131,
1432
+ "step": 4128
1433
+ },
1434
+ {
1435
+ "epoch": 86.5,
1436
+ "eval_loss": 0.3459572196006775,
1437
+ "eval_micro_f1": 0.8517350152726698,
1438
+ "eval_runtime": 5.9026,
1439
+ "eval_samples_per_second": 169.924,
1440
+ "step": 4152
1441
+ },
1442
+ {
1443
+ "epoch": 87.0,
1444
+ "eval_loss": 0.34485316276550293,
1445
+ "eval_micro_f1": 0.8522696006001917,
1446
+ "eval_runtime": 5.5017,
1447
+ "eval_samples_per_second": 182.306,
1448
+ "step": 4176
1449
+ },
1450
+ {
1451
+ "epoch": 87.5,
1452
+ "eval_loss": 0.3643297255039215,
1453
+ "eval_micro_f1": 0.8547509413164622,
1454
+ "eval_runtime": 5.6704,
1455
+ "eval_samples_per_second": 176.884,
1456
+ "step": 4200
1457
+ },
1458
+ {
1459
+ "epoch": 88.0,
1460
+ "eval_loss": 0.3472428321838379,
1461
+ "eval_micro_f1": 0.8618357482920342,
1462
+ "eval_runtime": 5.7938,
1463
+ "eval_samples_per_second": 173.116,
1464
+ "step": 4224
1465
+ },
1466
+ {
1467
+ "epoch": 88.5,
1468
+ "eval_loss": 0.3448476195335388,
1469
+ "eval_micro_f1": 0.8558843766504973,
1470
+ "eval_runtime": 5.435,
1471
+ "eval_samples_per_second": 184.546,
1472
+ "step": 4248
1473
+ },
1474
+ {
1475
+ "epoch": 89.0,
1476
+ "eval_loss": 0.36234745383262634,
1477
+ "eval_micro_f1": 0.8582162232370842,
1478
+ "eval_runtime": 5.7096,
1479
+ "eval_samples_per_second": 175.67,
1480
+ "step": 4272
1481
+ },
1482
+ {
1483
+ "epoch": 89.5,
1484
+ "eval_loss": 0.3701987862586975,
1485
+ "eval_micro_f1": 0.8531042123600764,
1486
+ "eval_runtime": 6.1332,
1487
+ "eval_samples_per_second": 163.537,
1488
+ "step": 4296
1489
+ },
1490
+ {
1491
+ "epoch": 90.0,
1492
+ "eval_loss": 0.3521389365196228,
1493
+ "eval_micro_f1": 0.8508820281657026,
1494
+ "eval_runtime": 5.5021,
1495
+ "eval_samples_per_second": 182.294,
1496
+ "step": 4320
1497
+ },
1498
+ {
1499
+ "epoch": 90.5,
1500
+ "eval_loss": 0.35653793811798096,
1501
+ "eval_micro_f1": 0.860658003370373,
1502
+ "eval_runtime": 5.5114,
1503
+ "eval_samples_per_second": 181.985,
1504
+ "step": 4344
1505
+ },
1506
+ {
1507
+ "epoch": 91.0,
1508
+ "eval_loss": 0.3529963195323944,
1509
+ "eval_micro_f1": 0.8529210557318647,
1510
+ "eval_runtime": 5.641,
1511
+ "eval_samples_per_second": 177.806,
1512
+ "step": 4368
1513
+ },
1514
+ {
1515
+ "epoch": 91.5,
1516
+ "eval_loss": 0.3580401837825775,
1517
+ "eval_micro_f1": 0.8532526470035618,
1518
+ "eval_runtime": 6.4058,
1519
+ "eval_samples_per_second": 156.577,
1520
+ "step": 4392
1521
+ },
1522
+ {
1523
+ "epoch": 92.0,
1524
+ "eval_loss": 0.3582540452480316,
1525
+ "eval_micro_f1": 0.8562733429774225,
1526
+ "eval_runtime": 6.0419,
1527
+ "eval_samples_per_second": 166.009,
1528
+ "step": 4416
1529
+ },
1530
+ {
1531
+ "epoch": 92.5,
1532
+ "eval_loss": 0.3542097210884094,
1533
+ "eval_micro_f1": 0.8561170942249785,
1534
+ "eval_runtime": 5.5594,
1535
+ "eval_samples_per_second": 180.414,
1536
+ "step": 4440
1537
+ },
1538
+ {
1539
+ "epoch": 93.0,
1540
+ "eval_loss": 0.3571048974990845,
1541
+ "eval_micro_f1": 0.8574183766867111,
1542
+ "eval_runtime": 5.3927,
1543
+ "eval_samples_per_second": 185.993,
1544
+ "step": 4464
1545
+ },
1546
+ {
1547
+ "epoch": 93.5,
1548
+ "eval_loss": 0.36213651299476624,
1549
+ "eval_micro_f1": 0.8523323207804733,
1550
+ "eval_runtime": 5.6708,
1551
+ "eval_samples_per_second": 176.87,
1552
+ "step": 4488
1553
+ },
1554
+ {
1555
+ "epoch": 93.75,
1556
+ "learning_rate": 6.875e-06,
1557
+ "loss": 0.0007,
1558
+ "step": 4500
1559
+ },
1560
+ {
1561
+ "epoch": 94.0,
1562
+ "eval_loss": 0.3665699064731598,
1563
+ "eval_micro_f1": 0.8544574977720514,
1564
+ "eval_runtime": 5.8227,
1565
+ "eval_samples_per_second": 172.256,
1566
+ "step": 4512
1567
+ },
1568
+ {
1569
+ "epoch": 94.5,
1570
+ "eval_loss": 0.36207252740859985,
1571
+ "eval_micro_f1": 0.8555617039823312,
1572
+ "eval_runtime": 5.6242,
1573
+ "eval_samples_per_second": 178.335,
1574
+ "step": 4536
1575
+ },
1576
+ {
1577
+ "epoch": 95.0,
1578
+ "eval_loss": 0.36637625098228455,
1579
+ "eval_micro_f1": 0.8587975725830543,
1580
+ "eval_runtime": 6.0728,
1581
+ "eval_samples_per_second": 165.162,
1582
+ "step": 4560
1583
+ },
1584
+ {
1585
+ "epoch": 95.5,
1586
+ "eval_loss": 0.3622714579105377,
1587
+ "eval_micro_f1": 0.85792724726918,
1588
+ "eval_runtime": 5.5578,
1589
+ "eval_samples_per_second": 180.466,
1590
+ "step": 4584
1591
+ },
1592
+ {
1593
+ "epoch": 96.0,
1594
+ "eval_loss": 0.3659743368625641,
1595
+ "eval_micro_f1": 0.8548653101100087,
1596
+ "eval_runtime": 5.6934,
1597
+ "eval_samples_per_second": 176.168,
1598
+ "step": 4608
1599
+ },
1600
+ {
1601
+ "epoch": 96.5,
1602
+ "eval_loss": 0.36642375588417053,
1603
+ "eval_micro_f1": 0.8587927947699571,
1604
+ "eval_runtime": 5.683,
1605
+ "eval_samples_per_second": 176.491,
1606
+ "step": 4632
1607
+ },
1608
+ {
1609
+ "epoch": 97.0,
1610
+ "eval_loss": 0.35858702659606934,
1611
+ "eval_micro_f1": 0.8538493202079045,
1612
+ "eval_runtime": 8.872,
1613
+ "eval_samples_per_second": 113.052,
1614
+ "step": 4656
1615
+ },
1616
+ {
1617
+ "epoch": 97.5,
1618
+ "eval_loss": 0.3688984811306,
1619
+ "eval_micro_f1": 0.855199222045932,
1620
+ "eval_runtime": 6.0184,
1621
+ "eval_samples_per_second": 166.656,
1622
+ "step": 4680
1623
+ },
1624
+ {
1625
+ "epoch": 98.0,
1626
+ "eval_loss": 0.3623090088367462,
1627
+ "eval_micro_f1": 0.8535679907001111,
1628
+ "eval_runtime": 5.6719,
1629
+ "eval_samples_per_second": 176.837,
1630
+ "step": 4704
1631
+ },
1632
+ {
1633
+ "epoch": 98.5,
1634
+ "eval_loss": 0.38087159395217896,
1635
+ "eval_micro_f1": 0.8560732108142424,
1636
+ "eval_runtime": 5.6312,
1637
+ "eval_samples_per_second": 178.116,
1638
+ "step": 4728
1639
+ },
1640
+ {
1641
+ "epoch": 99.0,
1642
+ "eval_loss": 0.3709181845188141,
1643
+ "eval_micro_f1": 0.8554466376331349,
1644
+ "eval_runtime": 5.5415,
1645
+ "eval_samples_per_second": 180.999,
1646
+ "step": 4752
1647
+ },
1648
+ {
1649
+ "epoch": 99.5,
1650
+ "eval_loss": 0.3728066384792328,
1651
+ "eval_micro_f1": 0.8544251442474945,
1652
+ "eval_runtime": 6.2188,
1653
+ "eval_samples_per_second": 161.286,
1654
+ "step": 4776
1655
+ },
1656
+ {
1657
+ "epoch": 100.0,
1658
+ "eval_loss": 0.37541478872299194,
1659
+ "eval_micro_f1": 0.8525313831388901,
1660
+ "eval_runtime": 5.861,
1661
+ "eval_samples_per_second": 171.131,
1662
+ "step": 4800
1663
+ },
1664
+ {
1665
+ "epoch": 100.5,
1666
+ "eval_loss": 0.3905048072338104,
1667
+ "eval_micro_f1": 0.8469514719178496,
1668
+ "eval_runtime": 5.8398,
1669
+ "eval_samples_per_second": 171.751,
1670
+ "step": 4824
1671
+ },
1672
+ {
1673
+ "epoch": 101.0,
1674
+ "eval_loss": 0.3774263262748718,
1675
+ "eval_micro_f1": 0.8538429803879977,
1676
+ "eval_runtime": 5.6702,
1677
+ "eval_samples_per_second": 176.889,
1678
+ "step": 4848
1679
+ },
1680
+ {
1681
+ "epoch": 101.5,
1682
+ "eval_loss": 0.3738786578178406,
1683
+ "eval_micro_f1": 0.8543073737244422,
1684
+ "eval_runtime": 5.5758,
1685
+ "eval_samples_per_second": 179.884,
1686
+ "step": 4872
1687
+ },
1688
+ {
1689
+ "epoch": 102.0,
1690
+ "eval_loss": 0.3875065743923187,
1691
+ "eval_micro_f1": 0.8495648565242165,
1692
+ "eval_runtime": 5.7307,
1693
+ "eval_samples_per_second": 175.023,
1694
+ "step": 4896
1695
+ },
1696
+ {
1697
+ "epoch": 102.5,
1698
+ "eval_loss": 0.39181411266326904,
1699
+ "eval_micro_f1": 0.8462498262015571,
1700
+ "eval_runtime": 6.1952,
1701
+ "eval_samples_per_second": 161.899,
1702
+ "step": 4920
1703
+ },
1704
+ {
1705
+ "epoch": 103.0,
1706
+ "eval_loss": 0.3727124333381653,
1707
+ "eval_micro_f1": 0.8535242285746646,
1708
+ "eval_runtime": 5.7922,
1709
+ "eval_samples_per_second": 173.164,
1710
+ "step": 4944
1711
+ },
1712
+ {
1713
+ "epoch": 103.5,
1714
+ "eval_loss": 0.36870327591896057,
1715
+ "eval_micro_f1": 0.8481186482226688,
1716
+ "eval_runtime": 5.9526,
1717
+ "eval_samples_per_second": 168.499,
1718
+ "step": 4968
1719
+ },
1720
+ {
1721
+ "epoch": 104.0,
1722
+ "eval_loss": 0.36689645051956177,
1723
+ "eval_micro_f1": 0.8511871888978889,
1724
+ "eval_runtime": 6.0549,
1725
+ "eval_samples_per_second": 165.652,
1726
+ "step": 4992
1727
+ },
1728
+ {
1729
+ "epoch": 104.17,
1730
+ "learning_rate": 6.5277777777777784e-06,
1731
+ "loss": 0.0007,
1732
+ "step": 5000
1733
+ },
1734
+ {
1735
+ "epoch": 104.5,
1736
+ "eval_loss": 0.3692272901535034,
1737
+ "eval_micro_f1": 0.8514988253044343,
1738
+ "eval_runtime": 6.1692,
1739
+ "eval_samples_per_second": 162.583,
1740
+ "step": 5016
1741
+ },
1742
+ {
1743
+ "epoch": 105.0,
1744
+ "eval_loss": 0.3660043478012085,
1745
+ "eval_micro_f1": 0.8517099858199334,
1746
+ "eval_runtime": 5.7015,
1747
+ "eval_samples_per_second": 175.918,
1748
+ "step": 5040
1749
+ },
1750
+ {
1751
+ "epoch": 105.5,
1752
+ "eval_loss": 0.372674822807312,
1753
+ "eval_micro_f1": 0.8507647783340004,
1754
+ "eval_runtime": 5.4465,
1755
+ "eval_samples_per_second": 184.155,
1756
+ "step": 5064
1757
+ },
1758
+ {
1759
+ "epoch": 106.0,
1760
+ "eval_loss": 0.380240797996521,
1761
+ "eval_micro_f1": 0.8532818527816217,
1762
+ "eval_runtime": 6.1483,
1763
+ "eval_samples_per_second": 163.134,
1764
+ "step": 5088
1765
+ },
1766
+ {
1767
+ "epoch": 106.5,
1768
+ "eval_loss": 0.3633327782154083,
1769
+ "eval_micro_f1": 0.8493449776657929,
1770
+ "eval_runtime": 5.9509,
1771
+ "eval_samples_per_second": 168.547,
1772
+ "step": 5112
1773
+ },
1774
+ {
1775
+ "epoch": 107.0,
1776
+ "eval_loss": 0.36895424127578735,
1777
+ "eval_micro_f1": 0.851627136841192,
1778
+ "eval_runtime": 5.7861,
1779
+ "eval_samples_per_second": 173.347,
1780
+ "step": 5136
1781
+ },
1782
+ {
1783
+ "epoch": 107.5,
1784
+ "eval_loss": 0.37197694182395935,
1785
+ "eval_micro_f1": 0.8514332960819097,
1786
+ "eval_runtime": 5.5635,
1787
+ "eval_samples_per_second": 180.283,
1788
+ "step": 5160
1789
+ },
1790
+ {
1791
+ "epoch": 108.0,
1792
+ "eval_loss": 0.3767761290073395,
1793
+ "eval_micro_f1": 0.8492809729510925,
1794
+ "eval_runtime": 6.0983,
1795
+ "eval_samples_per_second": 164.471,
1796
+ "step": 5184
1797
+ },
1798
+ {
1799
+ "epoch": 108.5,
1800
+ "eval_loss": 0.3700298070907593,
1801
+ "eval_micro_f1": 0.8512101205118823,
1802
+ "eval_runtime": 5.6367,
1803
+ "eval_samples_per_second": 177.942,
1804
+ "step": 5208
1805
+ },
1806
+ {
1807
+ "epoch": 109.0,
1808
+ "eval_loss": 0.36682432889938354,
1809
+ "eval_micro_f1": 0.8519687194888215,
1810
+ "eval_runtime": 5.6234,
1811
+ "eval_samples_per_second": 178.363,
1812
+ "step": 5232
1813
+ },
1814
+ {
1815
+ "epoch": 109.5,
1816
+ "eval_loss": 0.3719537854194641,
1817
+ "eval_micro_f1": 0.8510403743102992,
1818
+ "eval_runtime": 5.7217,
1819
+ "eval_samples_per_second": 175.296,
1820
+ "step": 5256
1821
+ },
1822
+ {
1823
+ "epoch": 110.0,
1824
+ "eval_loss": 0.3728875517845154,
1825
+ "eval_micro_f1": 0.8538705666309933,
1826
+ "eval_runtime": 5.4587,
1827
+ "eval_samples_per_second": 183.742,
1828
+ "step": 5280
1829
+ },
1830
+ {
1831
+ "epoch": 110.5,
1832
+ "eval_loss": 0.3713199198246002,
1833
+ "eval_micro_f1": 0.8528198069275643,
1834
+ "eval_runtime": 5.9244,
1835
+ "eval_samples_per_second": 169.301,
1836
+ "step": 5304
1837
+ },
1838
+ {
1839
+ "epoch": 111.0,
1840
+ "eval_loss": 0.37196192145347595,
1841
+ "eval_micro_f1": 0.8544225191630753,
1842
+ "eval_runtime": 5.9278,
1843
+ "eval_samples_per_second": 169.201,
1844
+ "step": 5328
1845
+ },
1846
+ {
1847
+ "epoch": 111.5,
1848
+ "eval_loss": 0.3665309548377991,
1849
+ "eval_micro_f1": 0.8517350152726698,
1850
+ "eval_runtime": 5.9205,
1851
+ "eval_samples_per_second": 169.411,
1852
+ "step": 5352
1853
+ },
1854
+ {
1855
+ "epoch": 112.0,
1856
+ "eval_loss": 0.36780908703804016,
1857
+ "eval_micro_f1": 0.8532967027964905,
1858
+ "eval_runtime": 5.8132,
1859
+ "eval_samples_per_second": 172.539,
1860
+ "step": 5376
1861
+ },
1862
+ {
1863
+ "epoch": 112.5,
1864
+ "eval_loss": 0.36912158131599426,
1865
+ "eval_micro_f1": 0.8522649038092883,
1866
+ "eval_runtime": 6.2147,
1867
+ "eval_samples_per_second": 161.392,
1868
+ "step": 5400
1869
+ },
1870
+ {
1871
+ "epoch": 113.0,
1872
+ "eval_loss": 0.36149299144744873,
1873
+ "eval_micro_f1": 0.8558855880586357,
1874
+ "eval_runtime": 5.7636,
1875
+ "eval_samples_per_second": 174.023,
1876
+ "step": 5424
1877
+ },
1878
+ {
1879
+ "epoch": 113.5,
1880
+ "eval_loss": 0.3701845109462738,
1881
+ "eval_micro_f1": 0.8520513878130679,
1882
+ "eval_runtime": 6.1708,
1883
+ "eval_samples_per_second": 162.539,
1884
+ "step": 5448
1885
+ },
1886
+ {
1887
+ "epoch": 114.0,
1888
+ "eval_loss": 0.3650461435317993,
1889
+ "eval_micro_f1": 0.8499727218130091,
1890
+ "eval_runtime": 5.6282,
1891
+ "eval_samples_per_second": 178.21,
1892
+ "step": 5472
1893
+ },
1894
+ {
1895
+ "epoch": 114.5,
1896
+ "eval_loss": 0.3701334297657013,
1897
+ "eval_micro_f1": 0.856552862935897,
1898
+ "eval_runtime": 5.8273,
1899
+ "eval_samples_per_second": 172.12,
1900
+ "step": 5496
1901
+ },
1902
+ {
1903
+ "epoch": 114.58,
1904
+ "learning_rate": 6.180555555555557e-06,
1905
+ "loss": 0.0005,
1906
+ "step": 5500
1907
+ },
1908
+ {
1909
+ "epoch": 115.0,
1910
+ "eval_loss": 0.372747540473938,
1911
+ "eval_micro_f1": 0.8559591211680423,
1912
+ "eval_runtime": 6.142,
1913
+ "eval_samples_per_second": 163.303,
1914
+ "step": 5520
1915
+ },
1916
+ {
1917
+ "epoch": 115.5,
1918
+ "eval_loss": 0.36282673478126526,
1919
+ "eval_micro_f1": 0.8573004269091156,
1920
+ "eval_runtime": 5.9641,
1921
+ "eval_samples_per_second": 168.172,
1922
+ "step": 5544
1923
+ },
1924
+ {
1925
+ "epoch": 116.0,
1926
+ "eval_loss": 0.3660167455673218,
1927
+ "eval_micro_f1": 0.8576168090104072,
1928
+ "eval_runtime": 5.7047,
1929
+ "eval_samples_per_second": 175.82,
1930
+ "step": 5568
1931
+ },
1932
+ {
1933
+ "epoch": 116.5,
1934
+ "eval_loss": 0.3644525408744812,
1935
+ "eval_micro_f1": 0.8549555702448751,
1936
+ "eval_runtime": 5.8433,
1937
+ "eval_samples_per_second": 171.65,
1938
+ "step": 5592
1939
+ },
1940
+ {
1941
+ "epoch": 117.0,
1942
+ "eval_loss": 0.39221301674842834,
1943
+ "eval_micro_f1": 0.8509212725316333,
1944
+ "eval_runtime": 6.2098,
1945
+ "eval_samples_per_second": 161.519,
1946
+ "step": 5616
1947
+ },
1948
+ {
1949
+ "epoch": 117.5,
1950
+ "eval_loss": 0.37303581833839417,
1951
+ "eval_micro_f1": 0.8548987179784805,
1952
+ "eval_runtime": 5.8319,
1953
+ "eval_samples_per_second": 171.984,
1954
+ "step": 5640
1955
+ },
1956
+ {
1957
+ "epoch": 118.0,
1958
+ "eval_loss": 0.37046360969543457,
1959
+ "eval_micro_f1": 0.8536251704984554,
1960
+ "eval_runtime": 5.7636,
1961
+ "eval_samples_per_second": 174.022,
1962
+ "step": 5664
1963
+ },
1964
+ {
1965
+ "epoch": 118.5,
1966
+ "eval_loss": 0.36990973353385925,
1967
+ "eval_micro_f1": 0.8569069890429795,
1968
+ "eval_runtime": 5.7379,
1969
+ "eval_samples_per_second": 174.804,
1970
+ "step": 5688
1971
+ },
1972
+ {
1973
+ "epoch": 119.0,
1974
+ "eval_loss": 0.3653363585472107,
1975
+ "eval_micro_f1": 0.8573013446668724,
1976
+ "eval_runtime": 5.8924,
1977
+ "eval_samples_per_second": 170.22,
1978
+ "step": 5712
1979
+ },
1980
+ {
1981
+ "epoch": 119.5,
1982
+ "eval_loss": 0.3810867667198181,
1983
+ "eval_micro_f1": 0.8565477012078675,
1984
+ "eval_runtime": 5.9608,
1985
+ "eval_samples_per_second": 168.265,
1986
+ "step": 5736
1987
+ },
1988
+ {
1989
+ "epoch": 120.0,
1990
+ "eval_loss": 0.3663919270038605,
1991
+ "eval_micro_f1": 0.8575349981272968,
1992
+ "eval_runtime": 5.4571,
1993
+ "eval_samples_per_second": 183.797,
1994
+ "step": 5760
1995
+ },
1996
+ {
1997
+ "epoch": 120.5,
1998
+ "eval_loss": 0.37352585792541504,
1999
+ "eval_micro_f1": 0.855140186415671,
2000
+ "eval_runtime": 5.6351,
2001
+ "eval_samples_per_second": 177.99,
2002
+ "step": 5784
2003
+ },
2004
+ {
2005
+ "epoch": 121.0,
2006
+ "eval_loss": 0.3712100386619568,
2007
+ "eval_micro_f1": 0.858478888235853,
2008
+ "eval_runtime": 5.6798,
2009
+ "eval_samples_per_second": 176.592,
2010
+ "step": 5808
2011
+ },
2012
+ {
2013
+ "epoch": 121.5,
2014
+ "eval_loss": 0.3769887685775757,
2015
+ "eval_micro_f1": 0.8552957354007412,
2016
+ "eval_runtime": 5.8072,
2017
+ "eval_samples_per_second": 172.718,
2018
+ "step": 5832
2019
+ },
2020
+ {
2021
+ "epoch": 122.0,
2022
+ "eval_loss": 0.37318331003189087,
2023
+ "eval_micro_f1": 0.8567884212778529,
2024
+ "eval_runtime": 5.6716,
2025
+ "eval_samples_per_second": 176.845,
2026
+ "step": 5856
2027
+ },
2028
+ {
2029
+ "epoch": 122.5,
2030
+ "eval_loss": 0.37376827001571655,
2031
+ "eval_micro_f1": 0.8558011044721399,
2032
+ "eval_runtime": 6.2446,
2033
+ "eval_samples_per_second": 160.619,
2034
+ "step": 5880
2035
+ },
2036
+ {
2037
+ "epoch": 123.0,
2038
+ "eval_loss": 0.37398213148117065,
2039
+ "eval_micro_f1": 0.8557612595163431,
2040
+ "eval_runtime": 5.6401,
2041
+ "eval_samples_per_second": 177.835,
2042
+ "step": 5904
2043
+ },
2044
+ {
2045
+ "epoch": 123.5,
2046
+ "eval_loss": 0.3746246099472046,
2047
+ "eval_micro_f1": 0.8532743846890433,
2048
+ "eval_runtime": 5.636,
2049
+ "eval_samples_per_second": 177.963,
2050
+ "step": 5928
2051
+ },
2052
+ {
2053
+ "epoch": 124.0,
2054
+ "eval_loss": 0.3776625692844391,
2055
+ "eval_micro_f1": 0.8565907517426913,
2056
+ "eval_runtime": 5.7377,
2057
+ "eval_samples_per_second": 174.809,
2058
+ "step": 5952
2059
+ },
2060
+ {
2061
+ "epoch": 124.5,
2062
+ "eval_loss": 0.3907985985279083,
2063
+ "eval_micro_f1": 0.8550020808096065,
2064
+ "eval_runtime": 5.936,
2065
+ "eval_samples_per_second": 168.969,
2066
+ "step": 5976
2067
+ },
2068
+ {
2069
+ "epoch": 125.0,
2070
+ "learning_rate": 5.833333333333334e-06,
2071
+ "loss": 0.0005,
2072
+ "step": 6000
2073
+ },
2074
+ {
2075
+ "epoch": 125.0,
2076
+ "eval_loss": 0.37965744733810425,
2077
+ "eval_micro_f1": 0.8533479387028808,
2078
+ "eval_runtime": 5.6237,
2079
+ "eval_samples_per_second": 178.352,
2080
+ "step": 6000
2081
+ },
2082
+ {
2083
+ "epoch": 125.5,
2084
+ "eval_loss": 0.37962594628334045,
2085
+ "eval_micro_f1": 0.8523195163814845,
2086
+ "eval_runtime": 5.6029,
2087
+ "eval_samples_per_second": 179.015,
2088
+ "step": 6024
2089
+ },
2090
+ {
2091
+ "epoch": 126.0,
2092
+ "eval_loss": 0.39396020770072937,
2093
+ "eval_micro_f1": 0.8528428088643412,
2094
+ "eval_runtime": 5.5906,
2095
+ "eval_samples_per_second": 179.408,
2096
+ "step": 6048
2097
+ },
2098
+ {
2099
+ "epoch": 126.5,
2100
+ "eval_loss": 0.3795776963233948,
2101
+ "eval_micro_f1": 0.8543209871541182,
2102
+ "eval_runtime": 5.8837,
2103
+ "eval_samples_per_second": 170.47,
2104
+ "step": 6072
2105
+ },
2106
+ {
2107
+ "epoch": 127.0,
2108
+ "eval_loss": 0.3853691816329956,
2109
+ "eval_micro_f1": 0.8537560298236841,
2110
+ "eval_runtime": 6.0649,
2111
+ "eval_samples_per_second": 165.378,
2112
+ "step": 6096
2113
+ },
2114
+ {
2115
+ "epoch": 127.5,
2116
+ "eval_loss": 0.39363810420036316,
2117
+ "eval_micro_f1": 0.8536585360851318,
2118
+ "eval_runtime": 5.8293,
2119
+ "eval_samples_per_second": 172.062,
2120
+ "step": 6120
2121
+ },
2122
+ {
2123
+ "epoch": 128.0,
2124
+ "eval_loss": 0.38859593868255615,
2125
+ "eval_micro_f1": 0.855090481610553,
2126
+ "eval_runtime": 6.0043,
2127
+ "eval_samples_per_second": 167.047,
2128
+ "step": 6144
2129
+ },
2130
+ {
2131
+ "epoch": 128.5,
2132
+ "eval_loss": 0.38463208079338074,
2133
+ "eval_micro_f1": 0.8484597315069492,
2134
+ "eval_runtime": 5.7281,
2135
+ "eval_samples_per_second": 175.101,
2136
+ "step": 6168
2137
+ },
2138
+ {
2139
+ "epoch": 129.0,
2140
+ "eval_loss": 0.38469961285591125,
2141
+ "eval_micro_f1": 0.8541237815774666,
2142
+ "eval_runtime": 5.7777,
2143
+ "eval_samples_per_second": 173.597,
2144
+ "step": 6192
2145
+ },
2146
+ {
2147
+ "epoch": 129.5,
2148
+ "eval_loss": 0.37942320108413696,
2149
+ "eval_micro_f1": 0.8577710590023256,
2150
+ "eval_runtime": 5.702,
2151
+ "eval_samples_per_second": 175.904,
2152
+ "step": 6216
2153
+ },
2154
+ {
2155
+ "epoch": 130.0,
2156
+ "eval_loss": 0.3804577887058258,
2157
+ "eval_micro_f1": 0.8547455290733686,
2158
+ "eval_runtime": 5.9726,
2159
+ "eval_samples_per_second": 167.934,
2160
+ "step": 6240
2161
+ },
2162
+ {
2163
+ "epoch": 130.5,
2164
+ "eval_loss": 0.3916989266872406,
2165
+ "eval_micro_f1": 0.8516666661664399,
2166
+ "eval_runtime": 5.9032,
2167
+ "eval_samples_per_second": 169.907,
2168
+ "step": 6264
2169
+ },
2170
+ {
2171
+ "epoch": 131.0,
2172
+ "eval_loss": 0.38645055890083313,
2173
+ "eval_micro_f1": 0.851181428268592,
2174
+ "eval_runtime": 5.5458,
2175
+ "eval_samples_per_second": 180.858,
2176
+ "step": 6288
2177
+ },
2178
+ {
2179
+ "epoch": 131.5,
2180
+ "eval_loss": 0.37874165177345276,
2181
+ "eval_micro_f1": 0.8535842784922911,
2182
+ "eval_runtime": 6.3049,
2183
+ "eval_samples_per_second": 159.082,
2184
+ "step": 6312
2185
+ },
2186
+ {
2187
+ "epoch": 132.0,
2188
+ "eval_loss": 0.38064897060394287,
2189
+ "eval_micro_f1": 0.854500275590323,
2190
+ "eval_runtime": 5.6982,
2191
+ "eval_samples_per_second": 176.02,
2192
+ "step": 6336
2193
+ },
2194
+ {
2195
+ "epoch": 132.5,
2196
+ "eval_loss": 0.3811017572879791,
2197
+ "eval_micro_f1": 0.8520253508362279,
2198
+ "eval_runtime": 5.8722,
2199
+ "eval_samples_per_second": 170.805,
2200
+ "step": 6360
2201
+ },
2202
+ {
2203
+ "epoch": 133.0,
2204
+ "eval_loss": 0.38710901141166687,
2205
+ "eval_micro_f1": 0.8537494816154948,
2206
+ "eval_runtime": 5.8989,
2207
+ "eval_samples_per_second": 170.031,
2208
+ "step": 6384
2209
+ },
2210
+ {
2211
+ "epoch": 133.5,
2212
+ "eval_loss": 0.39245015382766724,
2213
+ "eval_micro_f1": 0.8535541747930717,
2214
+ "eval_runtime": 5.6235,
2215
+ "eval_samples_per_second": 178.358,
2216
+ "step": 6408
2217
+ },
2218
+ {
2219
+ "epoch": 134.0,
2220
+ "eval_loss": 0.3756490647792816,
2221
+ "eval_micro_f1": 0.8525085905650751,
2222
+ "eval_runtime": 5.659,
2223
+ "eval_samples_per_second": 177.238,
2224
+ "step": 6432
2225
+ },
2226
+ {
2227
+ "epoch": 134.5,
2228
+ "eval_loss": 0.3782115578651428,
2229
+ "eval_micro_f1": 0.8535102261443193,
2230
+ "eval_runtime": 8.3175,
2231
+ "eval_samples_per_second": 120.589,
2232
+ "step": 6456
2233
+ },
2234
+ {
2235
+ "epoch": 135.0,
2236
+ "eval_loss": 0.3912818431854248,
2237
+ "eval_micro_f1": 0.8539853565932857,
2238
+ "eval_runtime": 6.2509,
2239
+ "eval_samples_per_second": 160.457,
2240
+ "step": 6480
2241
+ },
2242
+ {
2243
+ "epoch": 135.42,
2244
+ "learning_rate": 5.486111111111112e-06,
2245
+ "loss": 0.0004,
2246
+ "step": 6500
2247
+ },
2248
+ {
2249
+ "epoch": 135.5,
2250
+ "eval_loss": 0.38531988859176636,
2251
+ "eval_micro_f1": 0.8534292030395869,
2252
+ "eval_runtime": 5.908,
2253
+ "eval_samples_per_second": 169.769,
2254
+ "step": 6504
2255
+ },
2256
+ {
2257
+ "epoch": 136.0,
2258
+ "eval_loss": 0.3855549991130829,
2259
+ "eval_micro_f1": 0.8551647738005119,
2260
+ "eval_runtime": 5.6047,
2261
+ "eval_samples_per_second": 178.957,
2262
+ "step": 6528
2263
+ },
2264
+ {
2265
+ "epoch": 136.5,
2266
+ "eval_loss": 0.38542604446411133,
2267
+ "eval_micro_f1": 0.8533517617665229,
2268
+ "eval_runtime": 5.7414,
2269
+ "eval_samples_per_second": 174.696,
2270
+ "step": 6552
2271
+ },
2272
+ {
2273
+ "epoch": 137.0,
2274
+ "eval_loss": 0.38722705841064453,
2275
+ "eval_micro_f1": 0.8554801158916177,
2276
+ "eval_runtime": 5.5862,
2277
+ "eval_samples_per_second": 179.55,
2278
+ "step": 6576
2279
+ },
2280
+ {
2281
+ "epoch": 137.5,
2282
+ "eval_loss": 0.3835110366344452,
2283
+ "eval_micro_f1": 0.8500068610340341,
2284
+ "eval_runtime": 8.5511,
2285
+ "eval_samples_per_second": 117.295,
2286
+ "step": 6600
2287
+ },
2288
+ {
2289
+ "epoch": 138.0,
2290
+ "eval_loss": 0.3856574296951294,
2291
+ "eval_micro_f1": 0.849800741563823,
2292
+ "eval_runtime": 5.6908,
2293
+ "eval_samples_per_second": 176.249,
2294
+ "step": 6624
2295
+ },
2296
+ {
2297
+ "epoch": 138.5,
2298
+ "eval_loss": 0.3717750012874603,
2299
+ "eval_micro_f1": 0.8491237672982827,
2300
+ "eval_runtime": 6.1099,
2301
+ "eval_samples_per_second": 164.161,
2302
+ "step": 6648
2303
+ },
2304
+ {
2305
+ "epoch": 139.0,
2306
+ "eval_loss": 0.38148289918899536,
2307
+ "eval_micro_f1": 0.8531932535777292,
2308
+ "eval_runtime": 5.7548,
2309
+ "eval_samples_per_second": 174.288,
2310
+ "step": 6672
2311
+ },
2312
+ {
2313
+ "epoch": 139.5,
2314
+ "eval_loss": 0.38594627380371094,
2315
+ "eval_micro_f1": 0.8534256050360963,
2316
+ "eval_runtime": 5.572,
2317
+ "eval_samples_per_second": 180.008,
2318
+ "step": 6696
2319
+ },
2320
+ {
2321
+ "epoch": 140.0,
2322
+ "eval_loss": 0.3809627294540405,
2323
+ "eval_micro_f1": 0.855609084152218,
2324
+ "eval_runtime": 6.0836,
2325
+ "eval_samples_per_second": 164.87,
2326
+ "step": 6720
2327
+ },
2328
+ {
2329
+ "epoch": 140.5,
2330
+ "eval_loss": 0.38293471932411194,
2331
+ "eval_micro_f1": 0.8566298337539076,
2332
+ "eval_runtime": 6.2031,
2333
+ "eval_samples_per_second": 161.694,
2334
+ "step": 6744
2335
+ },
2336
+ {
2337
+ "epoch": 141.0,
2338
+ "eval_loss": 0.37818583846092224,
2339
+ "eval_micro_f1": 0.8535084114817699,
2340
+ "eval_runtime": 5.8175,
2341
+ "eval_samples_per_second": 172.41,
2342
+ "step": 6768
2343
+ },
2344
+ {
2345
+ "epoch": 141.5,
2346
+ "eval_loss": 0.38753288984298706,
2347
+ "eval_micro_f1": 0.8528644039509473,
2348
+ "eval_runtime": 5.9812,
2349
+ "eval_samples_per_second": 167.693,
2350
+ "step": 6792
2351
+ },
2352
+ {
2353
+ "epoch": 142.0,
2354
+ "eval_loss": 0.3880375623703003,
2355
+ "eval_micro_f1": 0.8550865046900751,
2356
+ "eval_runtime": 5.7101,
2357
+ "eval_samples_per_second": 175.653,
2358
+ "step": 6816
2359
+ },
2360
+ {
2361
+ "epoch": 142.5,
2362
+ "eval_loss": 0.38564714789390564,
2363
+ "eval_micro_f1": 0.8569847851152539,
2364
+ "eval_runtime": 5.6349,
2365
+ "eval_samples_per_second": 177.999,
2366
+ "step": 6840
2367
+ },
2368
+ {
2369
+ "epoch": 143.0,
2370
+ "eval_loss": 0.3862641155719757,
2371
+ "eval_micro_f1": 0.8545028266960164,
2372
+ "eval_runtime": 5.443,
2373
+ "eval_samples_per_second": 184.272,
2374
+ "step": 6864
2375
+ },
2376
+ {
2377
+ "epoch": 143.5,
2378
+ "eval_loss": 0.3768296539783478,
2379
+ "eval_micro_f1": 0.8520401149002539,
2380
+ "eval_runtime": 5.4694,
2381
+ "eval_samples_per_second": 183.385,
2382
+ "step": 6888
2383
+ },
2384
+ {
2385
+ "epoch": 144.0,
2386
+ "eval_loss": 0.3925332725048065,
2387
+ "eval_micro_f1": 0.8559888574385065,
2388
+ "eval_runtime": 5.6488,
2389
+ "eval_samples_per_second": 177.561,
2390
+ "step": 6912
2391
+ },
2392
+ {
2393
+ "epoch": 144.5,
2394
+ "eval_loss": 0.383102148771286,
2395
+ "eval_micro_f1": 0.8543101069082006,
2396
+ "eval_runtime": 6.1279,
2397
+ "eval_samples_per_second": 163.678,
2398
+ "step": 6936
2399
+ },
2400
+ {
2401
+ "epoch": 145.0,
2402
+ "eval_loss": 0.38753485679626465,
2403
+ "eval_micro_f1": 0.8541781954045783,
2404
+ "eval_runtime": 6.0038,
2405
+ "eval_samples_per_second": 167.06,
2406
+ "step": 6960
2407
+ },
2408
+ {
2409
+ "epoch": 145.5,
2410
+ "eval_loss": 0.38225728273391724,
2411
+ "eval_micro_f1": 0.8515259824527658,
2412
+ "eval_runtime": 5.9668,
2413
+ "eval_samples_per_second": 168.096,
2414
+ "step": 6984
2415
+ },
2416
+ {
2417
+ "epoch": 145.83,
2418
+ "learning_rate": 5.138888888888889e-06,
2419
+ "loss": 0.0003,
2420
+ "step": 7000
2421
+ },
2422
+ {
2423
+ "epoch": 146.0,
2424
+ "eval_loss": 0.38822275400161743,
2425
+ "eval_micro_f1": 0.8542671992791703,
2426
+ "eval_runtime": 6.0265,
2427
+ "eval_samples_per_second": 166.432,
2428
+ "step": 7008
2429
+ },
2430
+ {
2431
+ "epoch": 146.5,
2432
+ "eval_loss": 0.3835729658603668,
2433
+ "eval_micro_f1": 0.8543956038953913,
2434
+ "eval_runtime": 5.8949,
2435
+ "eval_samples_per_second": 170.147,
2436
+ "step": 7032
2437
+ },
2438
+ {
2439
+ "epoch": 147.0,
2440
+ "eval_loss": 0.3849795162677765,
2441
+ "eval_micro_f1": 0.8587633139277608,
2442
+ "eval_runtime": 5.8164,
2443
+ "eval_samples_per_second": 172.444,
2444
+ "step": 7056
2445
+ },
2446
+ {
2447
+ "epoch": 147.5,
2448
+ "eval_loss": 0.3917798697948456,
2449
+ "eval_micro_f1": 0.8590808411387438,
2450
+ "eval_runtime": 5.7209,
2451
+ "eval_samples_per_second": 175.321,
2452
+ "step": 7080
2453
+ },
2454
+ {
2455
+ "epoch": 148.0,
2456
+ "eval_loss": 0.39219409227371216,
2457
+ "eval_micro_f1": 0.8584474880842375,
2458
+ "eval_runtime": 5.5661,
2459
+ "eval_samples_per_second": 180.199,
2460
+ "step": 7104
2461
+ },
2462
+ {
2463
+ "epoch": 148.5,
2464
+ "eval_loss": 0.3943347632884979,
2465
+ "eval_micro_f1": 0.8584474880842375,
2466
+ "eval_runtime": 5.6779,
2467
+ "eval_samples_per_second": 176.649,
2468
+ "step": 7128
2469
+ },
2470
+ {
2471
+ "epoch": 149.0,
2472
+ "eval_loss": 0.3948417603969574,
2473
+ "eval_micro_f1": 0.8584070791457803,
2474
+ "eval_runtime": 5.7195,
2475
+ "eval_samples_per_second": 175.364,
2476
+ "step": 7152
2477
+ },
2478
+ {
2479
+ "epoch": 149.5,
2480
+ "eval_loss": 0.3897669315338135,
2481
+ "eval_micro_f1": 0.8535450309807922,
2482
+ "eval_runtime": 5.9135,
2483
+ "eval_samples_per_second": 169.611,
2484
+ "step": 7176
2485
+ },
2486
+ {
2487
+ "epoch": 150.0,
2488
+ "eval_loss": 0.39478468894958496,
2489
+ "eval_micro_f1": 0.8583679109797072,
2490
+ "eval_runtime": 8.3714,
2491
+ "eval_samples_per_second": 119.813,
2492
+ "step": 7200
2493
+ },
2494
+ {
2495
+ "epoch": 150.5,
2496
+ "eval_loss": 0.38256460428237915,
2497
+ "eval_micro_f1": 0.8574173180122125,
2498
+ "eval_runtime": 5.5847,
2499
+ "eval_samples_per_second": 179.597,
2500
+ "step": 7224
2501
+ },
2502
+ {
2503
+ "epoch": 151.0,
2504
+ "eval_loss": 0.38082531094551086,
2505
+ "eval_micro_f1": 0.8563982987728741,
2506
+ "eval_runtime": 5.6053,
2507
+ "eval_samples_per_second": 178.937,
2508
+ "step": 7248
2509
+ },
2510
+ {
2511
+ "epoch": 151.5,
2512
+ "eval_loss": 0.39371758699417114,
2513
+ "eval_micro_f1": 0.8581727431570508,
2514
+ "eval_runtime": 6.3519,
2515
+ "eval_samples_per_second": 157.905,
2516
+ "step": 7272
2517
+ },
2518
+ {
2519
+ "epoch": 152.0,
2520
+ "eval_loss": 0.3845665752887726,
2521
+ "eval_micro_f1": 0.8565121407801193,
2522
+ "eval_runtime": 5.8139,
2523
+ "eval_samples_per_second": 172.518,
2524
+ "step": 7296
2525
+ },
2526
+ {
2527
+ "epoch": 152.5,
2528
+ "eval_loss": 0.3823990821838379,
2529
+ "eval_micro_f1": 0.8587927947699571,
2530
+ "eval_runtime": 5.667,
2531
+ "eval_samples_per_second": 176.99,
2532
+ "step": 7320
2533
+ },
2534
+ {
2535
+ "epoch": 153.0,
2536
+ "eval_loss": 0.3907621502876282,
2537
+ "eval_micro_f1": 0.8582861868876499,
2538
+ "eval_runtime": 5.7157,
2539
+ "eval_samples_per_second": 175.483,
2540
+ "step": 7344
2541
+ },
2542
+ {
2543
+ "epoch": 153.5,
2544
+ "eval_loss": 0.38899049162864685,
2545
+ "eval_micro_f1": 0.8571034857888699,
2546
+ "eval_runtime": 6.1259,
2547
+ "eval_samples_per_second": 163.73,
2548
+ "step": 7368
2549
+ },
2550
+ {
2551
+ "epoch": 154.0,
2552
+ "eval_loss": 0.402112752199173,
2553
+ "eval_micro_f1": 0.8543769874682328,
2554
+ "eval_runtime": 5.6522,
2555
+ "eval_samples_per_second": 177.452,
2556
+ "step": 7392
2557
+ },
2558
+ {
2559
+ "epoch": 154.5,
2560
+ "eval_loss": 0.3932728171348572,
2561
+ "eval_micro_f1": 0.8557958952291065,
2562
+ "eval_runtime": 5.7058,
2563
+ "eval_samples_per_second": 175.785,
2564
+ "step": 7416
2565
+ },
2566
+ {
2567
+ "epoch": 155.0,
2568
+ "eval_loss": 0.38310226798057556,
2569
+ "eval_micro_f1": 0.8550645067740174,
2570
+ "eval_runtime": 5.8421,
2571
+ "eval_samples_per_second": 171.684,
2572
+ "step": 7440
2573
+ },
2574
+ {
2575
+ "epoch": 155.5,
2576
+ "eval_loss": 0.3877960741519928,
2577
+ "eval_micro_f1": 0.8586851206070292,
2578
+ "eval_runtime": 5.9703,
2579
+ "eval_samples_per_second": 167.999,
2580
+ "step": 7464
2581
+ },
2582
+ {
2583
+ "epoch": 156.0,
2584
+ "eval_loss": 0.39034387469291687,
2585
+ "eval_micro_f1": 0.8552903843804399,
2586
+ "eval_runtime": 5.6986,
2587
+ "eval_samples_per_second": 176.008,
2588
+ "step": 7488
2589
+ },
2590
+ {
2591
+ "epoch": 156.25,
2592
+ "learning_rate": 4.791666666666668e-06,
2593
+ "loss": 0.0003,
2594
+ "step": 7500
2595
+ },
2596
+ {
2597
+ "epoch": 156.5,
2598
+ "eval_loss": 0.39123356342315674,
2599
+ "eval_micro_f1": 0.8557227663090982,
2600
+ "eval_runtime": 5.8192,
2601
+ "eval_samples_per_second": 172.361,
2602
+ "step": 7512
2603
+ },
2604
+ {
2605
+ "epoch": 157.0,
2606
+ "eval_loss": 0.3877943754196167,
2607
+ "eval_micro_f1": 0.8563528268189945,
2608
+ "eval_runtime": 6.0841,
2609
+ "eval_samples_per_second": 164.855,
2610
+ "step": 7536
2611
+ },
2612
+ {
2613
+ "epoch": 157.5,
2614
+ "eval_loss": 0.39917612075805664,
2615
+ "eval_micro_f1": 0.8549280172184792,
2616
+ "eval_runtime": 5.6549,
2617
+ "eval_samples_per_second": 177.368,
2618
+ "step": 7560
2619
+ },
2620
+ {
2621
+ "epoch": 158.0,
2622
+ "eval_loss": 0.3977440297603607,
2623
+ "eval_micro_f1": 0.8555232955041876,
2624
+ "eval_runtime": 5.4972,
2625
+ "eval_samples_per_second": 182.456,
2626
+ "step": 7584
2627
+ },
2628
+ {
2629
+ "epoch": 158.5,
2630
+ "eval_loss": 0.40202879905700684,
2631
+ "eval_micro_f1": 0.854304635261356,
2632
+ "eval_runtime": 5.8271,
2633
+ "eval_samples_per_second": 172.126,
2634
+ "step": 7608
2635
+ },
2636
+ {
2637
+ "epoch": 159.0,
2638
+ "eval_loss": 0.39499518275260925,
2639
+ "eval_micro_f1": 0.857379767327292,
2640
+ "eval_runtime": 6.0158,
2641
+ "eval_samples_per_second": 166.728,
2642
+ "step": 7632
2643
+ },
2644
+ {
2645
+ "epoch": 159.5,
2646
+ "eval_loss": 0.39411211013793945,
2647
+ "eval_micro_f1": 0.8547478351463419,
2648
+ "eval_runtime": 6.0658,
2649
+ "eval_samples_per_second": 165.353,
2650
+ "step": 7656
2651
+ },
2652
+ {
2653
+ "epoch": 160.0,
2654
+ "eval_loss": 0.3973565399646759,
2655
+ "eval_micro_f1": 0.8534697257922715,
2656
+ "eval_runtime": 5.6179,
2657
+ "eval_samples_per_second": 178.537,
2658
+ "step": 7680
2659
+ },
2660
+ {
2661
+ "epoch": 160.5,
2662
+ "eval_loss": 0.38958290219306946,
2663
+ "eval_micro_f1": 0.8566313175000474,
2664
+ "eval_runtime": 6.1011,
2665
+ "eval_samples_per_second": 164.396,
2666
+ "step": 7704
2667
+ },
2668
+ {
2669
+ "epoch": 161.0,
2670
+ "eval_loss": 0.3927232623100281,
2671
+ "eval_micro_f1": 0.855640137908068,
2672
+ "eval_runtime": 8.4923,
2673
+ "eval_samples_per_second": 118.107,
2674
+ "step": 7728
2675
+ },
2676
+ {
2677
+ "epoch": 161.5,
2678
+ "eval_loss": 0.40015000104904175,
2679
+ "eval_micro_f1": 0.8534803578733052,
2680
+ "eval_runtime": 5.6185,
2681
+ "eval_samples_per_second": 178.517,
2682
+ "step": 7752
2683
+ },
2684
+ {
2685
+ "epoch": 162.0,
2686
+ "eval_loss": 0.4028796851634979,
2687
+ "eval_micro_f1": 0.8533075001917099,
2688
+ "eval_runtime": 6.2091,
2689
+ "eval_samples_per_second": 161.536,
2690
+ "step": 7776
2691
+ },
2692
+ {
2693
+ "epoch": 162.5,
2694
+ "eval_loss": 0.39666134119033813,
2695
+ "eval_micro_f1": 0.8550423077255965,
2696
+ "eval_runtime": 5.8041,
2697
+ "eval_samples_per_second": 172.807,
2698
+ "step": 7800
2699
+ },
2700
+ {
2701
+ "epoch": 163.0,
2702
+ "eval_loss": 0.38879114389419556,
2703
+ "eval_micro_f1": 0.8524137926032161,
2704
+ "eval_runtime": 6.0472,
2705
+ "eval_samples_per_second": 165.861,
2706
+ "step": 7824
2707
+ },
2708
+ {
2709
+ "epoch": 163.5,
2710
+ "eval_loss": 0.38980597257614136,
2711
+ "eval_micro_f1": 0.853002069893141,
2712
+ "eval_runtime": 5.9512,
2713
+ "eval_samples_per_second": 168.537,
2714
+ "step": 7848
2715
+ },
2716
+ {
2717
+ "epoch": 164.0,
2718
+ "eval_loss": 0.3938656449317932,
2719
+ "eval_micro_f1": 0.8561974350436811,
2720
+ "eval_runtime": 6.074,
2721
+ "eval_samples_per_second": 165.13,
2722
+ "step": 7872
2723
+ },
2724
+ {
2725
+ "epoch": 164.5,
2726
+ "eval_loss": 0.3952140212059021,
2727
+ "eval_micro_f1": 0.8568673365985447,
2728
+ "eval_runtime": 6.3602,
2729
+ "eval_samples_per_second": 157.7,
2730
+ "step": 7896
2731
+ },
2732
+ {
2733
+ "epoch": 165.0,
2734
+ "eval_loss": 0.40358638763427734,
2735
+ "eval_micro_f1": 0.8536247919734773,
2736
+ "eval_runtime": 5.5093,
2737
+ "eval_samples_per_second": 182.057,
2738
+ "step": 7920
2739
+ },
2740
+ {
2741
+ "epoch": 165.5,
2742
+ "eval_loss": 0.3869708478450775,
2743
+ "eval_micro_f1": 0.8544225191630753,
2744
+ "eval_runtime": 5.7983,
2745
+ "eval_samples_per_second": 172.982,
2746
+ "step": 7944
2747
+ },
2748
+ {
2749
+ "epoch": 166.0,
2750
+ "eval_loss": 0.3874531686306,
2751
+ "eval_micro_f1": 0.8550524567057288,
2752
+ "eval_runtime": 5.5447,
2753
+ "eval_samples_per_second": 180.892,
2754
+ "step": 7968
2755
+ },
2756
+ {
2757
+ "epoch": 166.5,
2758
+ "eval_loss": 0.3891386091709137,
2759
+ "eval_micro_f1": 0.8550124270059786,
2760
+ "eval_runtime": 5.8403,
2761
+ "eval_samples_per_second": 171.739,
2762
+ "step": 7992
2763
+ },
2764
+ {
2765
+ "epoch": 166.67,
2766
+ "learning_rate": 4.444444444444444e-06,
2767
+ "loss": 0.0003,
2768
+ "step": 8000
2769
+ },
2770
+ {
2771
+ "epoch": 167.0,
2772
+ "eval_loss": 0.3918393850326538,
2773
+ "eval_micro_f1": 0.8555632337775797,
2774
+ "eval_runtime": 5.7383,
2775
+ "eval_samples_per_second": 174.791,
2776
+ "step": 8016
2777
+ },
2778
+ {
2779
+ "epoch": 167.5,
2780
+ "eval_loss": 0.3910408318042755,
2781
+ "eval_micro_f1": 0.8536652830405661,
2782
+ "eval_runtime": 5.9314,
2783
+ "eval_samples_per_second": 169.1,
2784
+ "step": 8040
2785
+ },
2786
+ {
2787
+ "epoch": 168.0,
2788
+ "eval_loss": 0.39062175154685974,
2789
+ "eval_micro_f1": 0.8530910087246123,
2790
+ "eval_runtime": 6.1458,
2791
+ "eval_samples_per_second": 163.2,
2792
+ "step": 8064
2793
+ },
2794
+ {
2795
+ "epoch": 168.5,
2796
+ "eval_loss": 0.39219942688941956,
2797
+ "eval_micro_f1": 0.8552067482205489,
2798
+ "eval_runtime": 5.6698,
2799
+ "eval_samples_per_second": 176.902,
2800
+ "step": 8088
2801
+ },
2802
+ {
2803
+ "epoch": 169.0,
2804
+ "eval_loss": 0.3994564414024353,
2805
+ "eval_micro_f1": 0.855354658748736,
2806
+ "eval_runtime": 5.7264,
2807
+ "eval_samples_per_second": 175.153,
2808
+ "step": 8112
2809
+ },
2810
+ {
2811
+ "epoch": 169.5,
2812
+ "eval_loss": 0.39145705103874207,
2813
+ "eval_micro_f1": 0.8595614760470895,
2814
+ "eval_runtime": 5.716,
2815
+ "eval_samples_per_second": 175.471,
2816
+ "step": 8136
2817
+ },
2818
+ {
2819
+ "epoch": 170.0,
2820
+ "eval_loss": 0.39426934719085693,
2821
+ "eval_micro_f1": 0.8576581571024312,
2822
+ "eval_runtime": 5.8686,
2823
+ "eval_samples_per_second": 170.91,
2824
+ "step": 8160
2825
+ },
2826
+ {
2827
+ "epoch": 170.5,
2828
+ "eval_loss": 0.39562082290649414,
2829
+ "eval_micro_f1": 0.857895466018551,
2830
+ "eval_runtime": 8.614,
2831
+ "eval_samples_per_second": 116.439,
2832
+ "step": 8184
2833
+ },
2834
+ {
2835
+ "epoch": 171.0,
2836
+ "eval_loss": 0.3995242714881897,
2837
+ "eval_micro_f1": 0.8583298707087372,
2838
+ "eval_runtime": 5.8989,
2839
+ "eval_samples_per_second": 170.032,
2840
+ "step": 8208
2841
+ },
2842
+ {
2843
+ "epoch": 171.5,
2844
+ "eval_loss": 0.39817550778388977,
2845
+ "eval_micro_f1": 0.8549660612811749,
2846
+ "eval_runtime": 5.7135,
2847
+ "eval_samples_per_second": 175.55,
2848
+ "step": 8232
2849
+ },
2850
+ {
2851
+ "epoch": 172.0,
2852
+ "eval_loss": 0.3983123004436493,
2853
+ "eval_micro_f1": 0.8547339317734334,
2854
+ "eval_runtime": 5.921,
2855
+ "eval_samples_per_second": 169.397,
2856
+ "step": 8256
2857
+ },
2858
+ {
2859
+ "epoch": 172.5,
2860
+ "eval_loss": 0.3970920443534851,
2861
+ "eval_micro_f1": 0.8546206891549398,
2862
+ "eval_runtime": 5.7379,
2863
+ "eval_samples_per_second": 174.803,
2864
+ "step": 8280
2865
+ },
2866
+ {
2867
+ "epoch": 173.0,
2868
+ "eval_loss": 0.39891427755355835,
2869
+ "eval_micro_f1": 0.8570247928882011,
2870
+ "eval_runtime": 5.7045,
2871
+ "eval_samples_per_second": 175.827,
2872
+ "step": 8304
2873
+ },
2874
+ {
2875
+ "epoch": 173.5,
2876
+ "eval_loss": 0.39694347977638245,
2877
+ "eval_micro_f1": 0.8556473824198819,
2878
+ "eval_runtime": 6.1692,
2879
+ "eval_samples_per_second": 162.581,
2880
+ "step": 8328
2881
+ },
2882
+ {
2883
+ "epoch": 174.0,
2884
+ "eval_loss": 0.3953845202922821,
2885
+ "eval_micro_f1": 0.8554768841311742,
2886
+ "eval_runtime": 5.7391,
2887
+ "eval_samples_per_second": 174.765,
2888
+ "step": 8352
2889
+ },
2890
+ {
2891
+ "epoch": 174.5,
2892
+ "eval_loss": 0.39521798491477966,
2893
+ "eval_micro_f1": 0.855674398721887,
2894
+ "eval_runtime": 5.6073,
2895
+ "eval_samples_per_second": 178.873,
2896
+ "step": 8376
2897
+ },
2898
+ {
2899
+ "epoch": 175.0,
2900
+ "eval_loss": 0.39752158522605896,
2901
+ "eval_micro_f1": 0.8563896207013778,
2902
+ "eval_runtime": 5.731,
2903
+ "eval_samples_per_second": 175.013,
2904
+ "step": 8400
2905
+ },
2906
+ {
2907
+ "epoch": 175.5,
2908
+ "eval_loss": 0.39693886041641235,
2909
+ "eval_micro_f1": 0.854374307362444,
2910
+ "eval_runtime": 5.9297,
2911
+ "eval_samples_per_second": 169.147,
2912
+ "step": 8424
2913
+ },
2914
+ {
2915
+ "epoch": 176.0,
2916
+ "eval_loss": 0.39973294734954834,
2917
+ "eval_micro_f1": 0.8566273416232946,
2918
+ "eval_runtime": 5.7092,
2919
+ "eval_samples_per_second": 175.682,
2920
+ "step": 8448
2921
+ },
2922
+ {
2923
+ "epoch": 176.5,
2924
+ "eval_loss": 0.3962303400039673,
2925
+ "eval_micro_f1": 0.8539480944749174,
2926
+ "eval_runtime": 5.6499,
2927
+ "eval_samples_per_second": 177.525,
2928
+ "step": 8472
2929
+ },
2930
+ {
2931
+ "epoch": 177.0,
2932
+ "eval_loss": 0.39966246485710144,
2933
+ "eval_micro_f1": 0.8558807283788374,
2934
+ "eval_runtime": 5.6861,
2935
+ "eval_samples_per_second": 176.396,
2936
+ "step": 8496
2937
+ },
2938
+ {
2939
+ "epoch": 177.08,
2940
+ "learning_rate": 4.097222222222222e-06,
2941
+ "loss": 0.0002,
2942
+ "step": 8500
2943
+ },
2944
+ {
2945
+ "epoch": 177.5,
2946
+ "eval_loss": 0.4028112590312958,
2947
+ "eval_micro_f1": 0.8552850022667805,
2948
+ "eval_runtime": 5.6586,
2949
+ "eval_samples_per_second": 177.252,
2950
+ "step": 8520
2951
+ },
2952
+ {
2953
+ "epoch": 178.0,
2954
+ "eval_loss": 0.4031909108161926,
2955
+ "eval_micro_f1": 0.8557599220554263,
2956
+ "eval_runtime": 5.6041,
2957
+ "eval_samples_per_second": 178.976,
2958
+ "step": 8544
2959
+ },
2960
+ {
2961
+ "epoch": 178.5,
2962
+ "eval_loss": 0.40641722083091736,
2963
+ "eval_micro_f1": 0.8574591747004272,
2964
+ "eval_runtime": 5.7003,
2965
+ "eval_samples_per_second": 175.957,
2966
+ "step": 8568
2967
+ },
2968
+ {
2969
+ "epoch": 179.0,
2970
+ "eval_loss": 0.4027506709098816,
2971
+ "eval_micro_f1": 0.8565923474216028,
2972
+ "eval_runtime": 6.1105,
2973
+ "eval_samples_per_second": 164.144,
2974
+ "step": 8592
2975
+ },
2976
+ {
2977
+ "epoch": 179.5,
2978
+ "eval_loss": 0.4038204550743103,
2979
+ "eval_micro_f1": 0.8558396677789618,
2980
+ "eval_runtime": 5.7716,
2981
+ "eval_samples_per_second": 173.783,
2982
+ "step": 8616
2983
+ },
2984
+ {
2985
+ "epoch": 180.0,
2986
+ "eval_loss": 0.4131969213485718,
2987
+ "eval_micro_f1": 0.8523816131645413,
2988
+ "eval_runtime": 5.6353,
2989
+ "eval_samples_per_second": 177.984,
2990
+ "step": 8640
2991
+ },
2992
+ {
2993
+ "epoch": 180.5,
2994
+ "eval_loss": 0.40509098768234253,
2995
+ "eval_micro_f1": 0.8555647606154785,
2996
+ "eval_runtime": 5.6804,
2997
+ "eval_samples_per_second": 176.572,
2998
+ "step": 8664
2999
+ },
3000
+ {
3001
+ "epoch": 181.0,
3002
+ "eval_loss": 0.4057497978210449,
3003
+ "eval_micro_f1": 0.8567474043440538,
3004
+ "eval_runtime": 5.5763,
3005
+ "eval_samples_per_second": 179.868,
3006
+ "step": 8688
3007
+ },
3008
+ {
3009
+ "epoch": 181.5,
3010
+ "eval_loss": 0.40371522307395935,
3011
+ "eval_micro_f1": 0.8576154371289898,
3012
+ "eval_runtime": 5.7443,
3013
+ "eval_samples_per_second": 174.607,
3014
+ "step": 8712
3015
+ },
3016
+ {
3017
+ "epoch": 182.0,
3018
+ "eval_loss": 0.4053860902786255,
3019
+ "eval_micro_f1": 0.8572610669387409,
3020
+ "eval_runtime": 5.7325,
3021
+ "eval_samples_per_second": 174.968,
3022
+ "step": 8736
3023
+ },
3024
+ {
3025
+ "epoch": 182.5,
3026
+ "eval_loss": 0.40778404474258423,
3027
+ "eval_micro_f1": 0.859156875795547,
3028
+ "eval_runtime": 5.9697,
3029
+ "eval_samples_per_second": 168.014,
3030
+ "step": 8760
3031
+ },
3032
+ {
3033
+ "epoch": 183.0,
3034
+ "eval_loss": 0.40705546736717224,
3035
+ "eval_micro_f1": 0.8597485140776264,
3036
+ "eval_runtime": 5.6568,
3037
+ "eval_samples_per_second": 177.309,
3038
+ "step": 8784
3039
+ },
3040
+ {
3041
+ "epoch": 183.5,
3042
+ "eval_loss": 0.39787569642066956,
3043
+ "eval_micro_f1": 0.8560804291926519,
3044
+ "eval_runtime": 6.5717,
3045
+ "eval_samples_per_second": 152.625,
3046
+ "step": 8808
3047
+ },
3048
+ {
3049
+ "epoch": 184.0,
3050
+ "eval_loss": 0.40880951285362244,
3051
+ "eval_micro_f1": 0.8575778541710434,
3052
+ "eval_runtime": 5.7729,
3053
+ "eval_samples_per_second": 173.744,
3054
+ "step": 8832
3055
+ },
3056
+ {
3057
+ "epoch": 184.5,
3058
+ "eval_loss": 0.40336480736732483,
3059
+ "eval_micro_f1": 0.8547409035791523,
3060
+ "eval_runtime": 8.64,
3061
+ "eval_samples_per_second": 116.088,
3062
+ "step": 8856
3063
+ },
3064
+ {
3065
+ "epoch": 185.0,
3066
+ "eval_loss": 0.39812880754470825,
3067
+ "eval_micro_f1": 0.8532160522760345,
3068
+ "eval_runtime": 5.6351,
3069
+ "eval_samples_per_second": 177.991,
3070
+ "step": 8880
3071
+ },
3072
+ {
3073
+ "epoch": 185.5,
3074
+ "eval_loss": 0.3996230363845825,
3075
+ "eval_micro_f1": 0.8536383677467382,
3076
+ "eval_runtime": 5.5888,
3077
+ "eval_samples_per_second": 179.465,
3078
+ "step": 8904
3079
+ },
3080
+ {
3081
+ "epoch": 186.0,
3082
+ "eval_loss": 0.40416982769966125,
3083
+ "eval_micro_f1": 0.856826056325822,
3084
+ "eval_runtime": 5.5375,
3085
+ "eval_samples_per_second": 181.129,
3086
+ "step": 8928
3087
+ },
3088
+ {
3089
+ "epoch": 186.5,
3090
+ "eval_loss": 0.3977098762989044,
3091
+ "eval_micro_f1": 0.8583252857461446,
3092
+ "eval_runtime": 6.0174,
3093
+ "eval_samples_per_second": 166.683,
3094
+ "step": 8952
3095
+ },
3096
+ {
3097
+ "epoch": 187.0,
3098
+ "eval_loss": 0.4049621522426605,
3099
+ "eval_micro_f1": 0.8563528268189945,
3100
+ "eval_runtime": 5.7731,
3101
+ "eval_samples_per_second": 173.737,
3102
+ "step": 8976
3103
+ },
3104
+ {
3105
+ "epoch": 187.5,
3106
+ "learning_rate": 3.7500000000000005e-06,
3107
+ "loss": 0.0002,
3108
+ "step": 9000
3109
+ },
3110
+ {
3111
+ "epoch": 187.5,
3112
+ "eval_loss": 0.39555349946022034,
3113
+ "eval_micro_f1": 0.8561577708416512,
3114
+ "eval_runtime": 5.8513,
3115
+ "eval_samples_per_second": 171.415,
3116
+ "step": 9000
3117
+ },
3118
+ {
3119
+ "epoch": 188.0,
3120
+ "eval_loss": 0.3971739709377289,
3121
+ "eval_micro_f1": 0.8559977883333734,
3122
+ "eval_runtime": 5.7265,
3123
+ "eval_samples_per_second": 175.152,
3124
+ "step": 9024
3125
+ },
3126
+ {
3127
+ "epoch": 188.5,
3128
+ "eval_loss": 0.4019377827644348,
3129
+ "eval_micro_f1": 0.8543339790068261,
3130
+ "eval_runtime": 5.5606,
3131
+ "eval_samples_per_second": 180.375,
3132
+ "step": 9048
3133
+ },
3134
+ {
3135
+ "epoch": 189.0,
3136
+ "eval_loss": 0.4021461009979248,
3137
+ "eval_micro_f1": 0.8545328714720821,
3138
+ "eval_runtime": 5.899,
3139
+ "eval_samples_per_second": 170.03,
3140
+ "step": 9072
3141
+ },
3142
+ {
3143
+ "epoch": 189.5,
3144
+ "eval_loss": 0.40178442001342773,
3145
+ "eval_micro_f1": 0.8555601712211325,
3146
+ "eval_runtime": 5.4149,
3147
+ "eval_samples_per_second": 185.23,
3148
+ "step": 9096
3149
+ },
3150
+ {
3151
+ "epoch": 190.0,
3152
+ "eval_loss": 0.402057945728302,
3153
+ "eval_micro_f1": 0.8560742480106384,
3154
+ "eval_runtime": 5.91,
3155
+ "eval_samples_per_second": 169.714,
3156
+ "step": 9120
3157
+ },
3158
+ {
3159
+ "epoch": 190.5,
3160
+ "eval_loss": 0.40114665031433105,
3161
+ "eval_micro_f1": 0.8559579757231529,
3162
+ "eval_runtime": 5.7715,
3163
+ "eval_samples_per_second": 173.785,
3164
+ "step": 9144
3165
+ },
3166
+ {
3167
+ "epoch": 191.0,
3168
+ "eval_loss": 0.40176090598106384,
3169
+ "eval_micro_f1": 0.8563543530253626,
3170
+ "eval_runtime": 5.8027,
3171
+ "eval_samples_per_second": 172.851,
3172
+ "step": 9168
3173
+ },
3174
+ {
3175
+ "epoch": 191.5,
3176
+ "eval_loss": 0.40274718403816223,
3177
+ "eval_micro_f1": 0.8564725360716672,
3178
+ "eval_runtime": 5.802,
3179
+ "eval_samples_per_second": 172.872,
3180
+ "step": 9192
3181
+ },
3182
+ {
3183
+ "epoch": 192.0,
3184
+ "eval_loss": 0.40702563524246216,
3185
+ "eval_micro_f1": 0.8559193253735035,
3186
+ "eval_runtime": 5.6942,
3187
+ "eval_samples_per_second": 176.145,
3188
+ "step": 9216
3189
+ },
3190
+ {
3191
+ "epoch": 192.5,
3192
+ "eval_loss": 0.40590065717697144,
3193
+ "eval_micro_f1": 0.8568670706525529,
3194
+ "eval_runtime": 6.0125,
3195
+ "eval_samples_per_second": 166.82,
3196
+ "step": 9240
3197
+ },
3198
+ {
3199
+ "epoch": 193.0,
3200
+ "eval_loss": 0.4045752286911011,
3201
+ "eval_micro_f1": 0.8570640932282318,
3202
+ "eval_runtime": 5.4373,
3203
+ "eval_samples_per_second": 184.466,
3204
+ "step": 9264
3205
+ },
3206
+ {
3207
+ "epoch": 193.5,
3208
+ "eval_loss": 0.4057496190071106,
3209
+ "eval_micro_f1": 0.8565912846624812,
3210
+ "eval_runtime": 6.2198,
3211
+ "eval_samples_per_second": 161.258,
3212
+ "step": 9288
3213
+ },
3214
+ {
3215
+ "epoch": 194.0,
3216
+ "eval_loss": 0.40410348773002625,
3217
+ "eval_micro_f1": 0.8571428566426279,
3218
+ "eval_runtime": 5.6852,
3219
+ "eval_samples_per_second": 176.424,
3220
+ "step": 9312
3221
+ },
3222
+ {
3223
+ "epoch": 194.5,
3224
+ "eval_loss": 0.4102969765663147,
3225
+ "eval_micro_f1": 0.8573806876240739,
3226
+ "eval_runtime": 5.5912,
3227
+ "eval_samples_per_second": 179.388,
3228
+ "step": 9336
3229
+ },
3230
+ {
3231
+ "epoch": 195.0,
3232
+ "eval_loss": 0.3981609046459198,
3233
+ "eval_micro_f1": 0.8586373016332908,
3234
+ "eval_runtime": 5.6659,
3235
+ "eval_samples_per_second": 177.023,
3236
+ "step": 9360
3237
+ },
3238
+ {
3239
+ "epoch": 195.5,
3240
+ "eval_loss": 0.40271085500717163,
3241
+ "eval_micro_f1": 0.8603522391336583,
3242
+ "eval_runtime": 5.9572,
3243
+ "eval_samples_per_second": 168.369,
3244
+ "step": 9384
3245
+ },
3246
+ {
3247
+ "epoch": 196.0,
3248
+ "eval_loss": 0.4059590995311737,
3249
+ "eval_micro_f1": 0.8580520194222863,
3250
+ "eval_runtime": 5.756,
3251
+ "eval_samples_per_second": 174.253,
3252
+ "step": 9408
3253
+ },
3254
+ {
3255
+ "epoch": 196.5,
3256
+ "eval_loss": 0.40151461958885193,
3257
+ "eval_micro_f1": 0.8567489309763983,
3258
+ "eval_runtime": 5.6257,
3259
+ "eval_samples_per_second": 178.288,
3260
+ "step": 9432
3261
+ },
3262
+ {
3263
+ "epoch": 197.0,
3264
+ "eval_loss": 0.4040184020996094,
3265
+ "eval_micro_f1": 0.8561568189365402,
3266
+ "eval_runtime": 5.5723,
3267
+ "eval_samples_per_second": 179.997,
3268
+ "step": 9456
3269
+ },
3270
+ {
3271
+ "epoch": 197.5,
3272
+ "eval_loss": 0.3993892967700958,
3273
+ "eval_micro_f1": 0.8594766712428058,
3274
+ "eval_runtime": 5.6807,
3275
+ "eval_samples_per_second": 176.561,
3276
+ "step": 9480
3277
+ },
3278
+ {
3279
+ "epoch": 197.92,
3280
+ "learning_rate": 3.4027777777777783e-06,
3281
+ "loss": 0.0001,
3282
+ "step": 9500
3283
+ },
3284
+ {
3285
+ "epoch": 198.0,
3286
+ "eval_loss": 0.4072522819042206,
3287
+ "eval_micro_f1": 0.8595497854409317,
3288
+ "eval_runtime": 5.6766,
3289
+ "eval_samples_per_second": 176.691,
3290
+ "step": 9504
3291
+ },
3292
+ {
3293
+ "epoch": 198.5,
3294
+ "eval_loss": 0.4100194275379181,
3295
+ "eval_micro_f1": 0.8594721564708834,
3296
+ "eval_runtime": 8.317,
3297
+ "eval_samples_per_second": 120.597,
3298
+ "step": 9528
3299
+ },
3300
+ {
3301
+ "epoch": 199.0,
3302
+ "eval_loss": 0.4050011932849884,
3303
+ "eval_micro_f1": 0.857656163126076,
3304
+ "eval_runtime": 5.4136,
3305
+ "eval_samples_per_second": 185.273,
3306
+ "step": 9552
3307
+ },
3308
+ {
3309
+ "epoch": 199.5,
3310
+ "eval_loss": 0.40566879510879517,
3311
+ "eval_micro_f1": 0.858130530473214,
3312
+ "eval_runtime": 5.4929,
3313
+ "eval_samples_per_second": 182.599,
3314
+ "step": 9576
3315
+ },
3316
+ {
3317
+ "epoch": 200.0,
3318
+ "eval_loss": 0.40994182229042053,
3319
+ "eval_micro_f1": 0.8548900257827903,
3320
+ "eval_runtime": 5.4167,
3321
+ "eval_samples_per_second": 185.168,
3322
+ "step": 9600
3323
+ },
3324
+ {
3325
+ "epoch": 200.5,
3326
+ "eval_loss": 0.3946707844734192,
3327
+ "eval_micro_f1": 0.8590677844578437,
3328
+ "eval_runtime": 5.4529,
3329
+ "eval_samples_per_second": 183.938,
3330
+ "step": 9624
3331
+ },
3332
+ {
3333
+ "epoch": 201.0,
3334
+ "eval_loss": 0.394417941570282,
3335
+ "eval_micro_f1": 0.8593792909032482,
3336
+ "eval_runtime": 6.1316,
3337
+ "eval_samples_per_second": 163.578,
3338
+ "step": 9648
3339
+ },
3340
+ {
3341
+ "epoch": 201.5,
3342
+ "eval_loss": 0.3943053185939789,
3343
+ "eval_micro_f1": 0.861602209444514,
3344
+ "eval_runtime": 5.7586,
3345
+ "eval_samples_per_second": 174.173,
3346
+ "step": 9672
3347
+ },
3348
+ {
3349
+ "epoch": 202.0,
3350
+ "eval_loss": 0.3954358994960785,
3351
+ "eval_micro_f1": 0.8612148881119107,
3352
+ "eval_runtime": 5.6373,
3353
+ "eval_samples_per_second": 177.921,
3354
+ "step": 9696
3355
+ },
3356
+ {
3357
+ "epoch": 202.5,
3358
+ "eval_loss": 0.40347030758857727,
3359
+ "eval_micro_f1": 0.8599221784881004,
3360
+ "eval_runtime": 5.8309,
3361
+ "eval_samples_per_second": 172.015,
3362
+ "step": 9720
3363
+ },
3364
+ {
3365
+ "epoch": 203.0,
3366
+ "eval_loss": 0.40211471915245056,
3367
+ "eval_micro_f1": 0.8600635441882556,
3368
+ "eval_runtime": 5.7031,
3369
+ "eval_samples_per_second": 175.869,
3370
+ "step": 9744
3371
+ },
3372
+ {
3373
+ "epoch": 203.5,
3374
+ "eval_loss": 0.4008079469203949,
3375
+ "eval_micro_f1": 0.8608467792542825,
3376
+ "eval_runtime": 5.589,
3377
+ "eval_samples_per_second": 179.459,
3378
+ "step": 9768
3379
+ },
3380
+ {
3381
+ "epoch": 204.0,
3382
+ "eval_loss": 0.40170103311538696,
3383
+ "eval_micro_f1": 0.8611686692055229,
3384
+ "eval_runtime": 5.9822,
3385
+ "eval_samples_per_second": 167.663,
3386
+ "step": 9792
3387
+ },
3388
+ {
3389
+ "epoch": 204.5,
3390
+ "eval_loss": 0.40431681275367737,
3391
+ "eval_micro_f1": 0.8593944416399532,
3392
+ "eval_runtime": 5.5512,
3393
+ "eval_samples_per_second": 180.682,
3394
+ "step": 9816
3395
+ },
3396
+ {
3397
+ "epoch": 205.0,
3398
+ "eval_loss": 0.4069841802120209,
3399
+ "eval_micro_f1": 0.8587633139277608,
3400
+ "eval_runtime": 5.6951,
3401
+ "eval_samples_per_second": 176.117,
3402
+ "step": 9840
3403
+ },
3404
+ {
3405
+ "epoch": 205.5,
3406
+ "eval_loss": 0.40759971737861633,
3407
+ "eval_micro_f1": 0.8589601764909128,
3408
+ "eval_runtime": 5.7064,
3409
+ "eval_samples_per_second": 175.769,
3410
+ "step": 9864
3411
+ },
3412
+ {
3413
+ "epoch": 206.0,
3414
+ "eval_loss": 0.40662652254104614,
3415
+ "eval_micro_f1": 0.858444965664658,
3416
+ "eval_runtime": 5.8179,
3417
+ "eval_samples_per_second": 172.4,
3418
+ "step": 9888
3419
+ },
3420
+ {
3421
+ "epoch": 206.5,
3422
+ "eval_loss": 0.4064077138900757,
3423
+ "eval_micro_f1": 0.8586791667409089,
3424
+ "eval_runtime": 6.1843,
3425
+ "eval_samples_per_second": 162.184,
3426
+ "step": 9912
3427
+ },
3428
+ {
3429
+ "epoch": 207.0,
3430
+ "eval_loss": 0.41001489758491516,
3431
+ "eval_micro_f1": 0.8633093520177468,
3432
+ "eval_runtime": 5.8209,
3433
+ "eval_samples_per_second": 172.311,
3434
+ "step": 9936
3435
+ }
3436
+ ],
3437
+ "max_steps": 14400,
3438
+ "num_train_epochs": 300,
3439
+ "total_flos": 37620331380469854,
3440
+ "trial_name": null,
3441
+ "trial_params": null
3442
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555f998c870ce7dc895aa884e777982fd244a4f97db4250ca916ea155aac0ad0
3
+ size 2095
vocab.txt ADDED
The diff for this file is too large to render. See raw diff