Upload 9 files
Browse files- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +939 -0
- trainer_state.json +2343 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,939 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": true,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"model_max_length": 512,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"tokenizer_class": "T5Tokenizer",
|
| 938 |
+
"unk_token": "<unk>"
|
| 939 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 100000,
|
| 3 |
+
"best_metric": 0.0042214160785079,
|
| 4 |
+
"best_model_checkpoint": "./models/t5-small-separated-100k\\checkpoint-100000",
|
| 5 |
+
"epoch": 1.9557989438685703,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 100000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009778994719342852,
|
| 14 |
+
"grad_norm": 0.6658946871757507,
|
| 15 |
+
"learning_rate": 3.493e-05,
|
| 16 |
+
"loss": 4.7982,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019557989438685704,
|
| 21 |
+
"grad_norm": 0.3144054412841797,
|
| 22 |
+
"learning_rate": 6.993e-05,
|
| 23 |
+
"loss": 0.1216,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.019557989438685704,
|
| 28 |
+
"eval_accuracy": 0.9892674761904762,
|
| 29 |
+
"eval_loss": 0.08768512308597565,
|
| 30 |
+
"eval_runtime": 53.527,
|
| 31 |
+
"eval_samples_per_second": 560.465,
|
| 32 |
+
"eval_steps_per_second": 35.029,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.029336984158028555,
|
| 37 |
+
"grad_norm": 0.23313283920288086,
|
| 38 |
+
"learning_rate": 0.00010493,
|
| 39 |
+
"loss": 0.0921,
|
| 40 |
+
"step": 1500
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.03911597887737141,
|
| 44 |
+
"grad_norm": 0.20106713473796844,
|
| 45 |
+
"learning_rate": 0.00013993,
|
| 46 |
+
"loss": 0.0777,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.03911597887737141,
|
| 51 |
+
"eval_accuracy": 0.9915514285714285,
|
| 52 |
+
"eval_loss": 0.06547641009092331,
|
| 53 |
+
"eval_runtime": 53.2664,
|
| 54 |
+
"eval_samples_per_second": 563.207,
|
| 55 |
+
"eval_steps_per_second": 35.2,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.048894973596714256,
|
| 60 |
+
"grad_norm": 0.23620536923408508,
|
| 61 |
+
"learning_rate": 0.00017493,
|
| 62 |
+
"loss": 0.0697,
|
| 63 |
+
"step": 2500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05867396831605711,
|
| 67 |
+
"grad_norm": 0.2420068085193634,
|
| 68 |
+
"learning_rate": 0.00020993,
|
| 69 |
+
"loss": 0.065,
|
| 70 |
+
"step": 3000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.05867396831605711,
|
| 74 |
+
"eval_accuracy": 0.9928663333333333,
|
| 75 |
+
"eval_loss": 0.05075705423951149,
|
| 76 |
+
"eval_runtime": 53.7766,
|
| 77 |
+
"eval_samples_per_second": 557.863,
|
| 78 |
+
"eval_steps_per_second": 34.866,
|
| 79 |
+
"step": 3000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06845296303539997,
|
| 83 |
+
"grad_norm": 0.11961843073368073,
|
| 84 |
+
"learning_rate": 0.00024493,
|
| 85 |
+
"loss": 0.0569,
|
| 86 |
+
"step": 3500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07823195775474281,
|
| 90 |
+
"grad_norm": 0.14315247535705566,
|
| 91 |
+
"learning_rate": 0.00027992999999999996,
|
| 92 |
+
"loss": 0.0543,
|
| 93 |
+
"step": 4000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07823195775474281,
|
| 97 |
+
"eval_accuracy": 0.9939067619047619,
|
| 98 |
+
"eval_loss": 0.041266366839408875,
|
| 99 |
+
"eval_runtime": 53.7245,
|
| 100 |
+
"eval_samples_per_second": 558.404,
|
| 101 |
+
"eval_steps_per_second": 34.9,
|
| 102 |
+
"step": 4000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.08801095247408566,
|
| 106 |
+
"grad_norm": 0.10638320446014404,
|
| 107 |
+
"learning_rate": 0.00031493,
|
| 108 |
+
"loss": 0.0516,
|
| 109 |
+
"step": 4500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.09778994719342851,
|
| 113 |
+
"grad_norm": 0.13181553781032562,
|
| 114 |
+
"learning_rate": 0.00034993,
|
| 115 |
+
"loss": 0.047,
|
| 116 |
+
"step": 5000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.09778994719342851,
|
| 120 |
+
"eval_accuracy": 0.9946067142857142,
|
| 121 |
+
"eval_loss": 0.03676154091954231,
|
| 122 |
+
"eval_runtime": 53.8638,
|
| 123 |
+
"eval_samples_per_second": 556.96,
|
| 124 |
+
"eval_steps_per_second": 34.81,
|
| 125 |
+
"step": 5000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.10756894191277137,
|
| 129 |
+
"grad_norm": 0.09576228260993958,
|
| 130 |
+
"learning_rate": 0.00038493,
|
| 131 |
+
"loss": 0.0447,
|
| 132 |
+
"step": 5500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.11734793663211422,
|
| 136 |
+
"grad_norm": 0.10529287159442902,
|
| 137 |
+
"learning_rate": 0.00041993,
|
| 138 |
+
"loss": 0.043,
|
| 139 |
+
"step": 6000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.11734793663211422,
|
| 143 |
+
"eval_accuracy": 0.994841619047619,
|
| 144 |
+
"eval_loss": 0.03489045798778534,
|
| 145 |
+
"eval_runtime": 52.9135,
|
| 146 |
+
"eval_samples_per_second": 566.964,
|
| 147 |
+
"eval_steps_per_second": 35.435,
|
| 148 |
+
"step": 6000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.12712693135145706,
|
| 152 |
+
"grad_norm": 0.12828822433948517,
|
| 153 |
+
"learning_rate": 0.00045493000000000004,
|
| 154 |
+
"loss": 0.04,
|
| 155 |
+
"step": 6500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.13690592607079993,
|
| 159 |
+
"grad_norm": 0.11473549902439117,
|
| 160 |
+
"learning_rate": 0.00048993,
|
| 161 |
+
"loss": 0.0385,
|
| 162 |
+
"step": 7000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.13690592607079993,
|
| 166 |
+
"eval_accuracy": 0.9954386190476191,
|
| 167 |
+
"eval_loss": 0.031031519174575806,
|
| 168 |
+
"eval_runtime": 53.7491,
|
| 169 |
+
"eval_samples_per_second": 558.149,
|
| 170 |
+
"eval_steps_per_second": 34.884,
|
| 171 |
+
"step": 7000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14668492079014278,
|
| 175 |
+
"grad_norm": 0.1124059334397316,
|
| 176 |
+
"learning_rate": 0.00052493,
|
| 177 |
+
"loss": 0.038,
|
| 178 |
+
"step": 7500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.15646391550948563,
|
| 182 |
+
"grad_norm": 0.10570541769266129,
|
| 183 |
+
"learning_rate": 0.00055993,
|
| 184 |
+
"loss": 0.036,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15646391550948563,
|
| 189 |
+
"eval_accuracy": 0.9959220952380953,
|
| 190 |
+
"eval_loss": 0.02701031044125557,
|
| 191 |
+
"eval_runtime": 53.2087,
|
| 192 |
+
"eval_samples_per_second": 563.818,
|
| 193 |
+
"eval_steps_per_second": 35.239,
|
| 194 |
+
"step": 8000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.16624291022882848,
|
| 198 |
+
"grad_norm": 0.08027876168489456,
|
| 199 |
+
"learning_rate": 0.00059493,
|
| 200 |
+
"loss": 0.0346,
|
| 201 |
+
"step": 8500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.17602190494817133,
|
| 205 |
+
"grad_norm": 0.15847843885421753,
|
| 206 |
+
"learning_rate": 0.00062993,
|
| 207 |
+
"loss": 0.0335,
|
| 208 |
+
"step": 9000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.17602190494817133,
|
| 212 |
+
"eval_accuracy": 0.9961202857142857,
|
| 213 |
+
"eval_loss": 0.02567765861749649,
|
| 214 |
+
"eval_runtime": 53.6856,
|
| 215 |
+
"eval_samples_per_second": 558.809,
|
| 216 |
+
"eval_steps_per_second": 34.926,
|
| 217 |
+
"step": 9000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.18580089966751417,
|
| 221 |
+
"grad_norm": 0.12231533229351044,
|
| 222 |
+
"learning_rate": 0.00066493,
|
| 223 |
+
"loss": 0.0327,
|
| 224 |
+
"step": 9500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.19557989438685702,
|
| 228 |
+
"grad_norm": 0.09047775715589523,
|
| 229 |
+
"learning_rate": 0.00069993,
|
| 230 |
+
"loss": 0.0319,
|
| 231 |
+
"step": 10000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.19557989438685702,
|
| 235 |
+
"eval_accuracy": 0.9961952380952381,
|
| 236 |
+
"eval_loss": 0.025217700749635696,
|
| 237 |
+
"eval_runtime": 54.2394,
|
| 238 |
+
"eval_samples_per_second": 553.104,
|
| 239 |
+
"eval_steps_per_second": 34.569,
|
| 240 |
+
"step": 10000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.20535888910619987,
|
| 244 |
+
"grad_norm": 0.13553255796432495,
|
| 245 |
+
"learning_rate": 0.0006961188888888888,
|
| 246 |
+
"loss": 0.0302,
|
| 247 |
+
"step": 10500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.21513788382554275,
|
| 251 |
+
"grad_norm": 0.10632240027189255,
|
| 252 |
+
"learning_rate": 0.00069223,
|
| 253 |
+
"loss": 0.0294,
|
| 254 |
+
"step": 11000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.21513788382554275,
|
| 258 |
+
"eval_accuracy": 0.9967280952380952,
|
| 259 |
+
"eval_loss": 0.021495230495929718,
|
| 260 |
+
"eval_runtime": 53.6938,
|
| 261 |
+
"eval_samples_per_second": 558.724,
|
| 262 |
+
"eval_steps_per_second": 34.92,
|
| 263 |
+
"step": 11000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.2249168785448856,
|
| 267 |
+
"grad_norm": 0.06258939951658249,
|
| 268 |
+
"learning_rate": 0.0006883411111111112,
|
| 269 |
+
"loss": 0.0282,
|
| 270 |
+
"step": 11500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.23469587326422844,
|
| 274 |
+
"grad_norm": 0.10836105048656464,
|
| 275 |
+
"learning_rate": 0.0006844522222222223,
|
| 276 |
+
"loss": 0.0273,
|
| 277 |
+
"step": 12000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.23469587326422844,
|
| 281 |
+
"eval_accuracy": 0.9968712857142857,
|
| 282 |
+
"eval_loss": 0.020473388954997063,
|
| 283 |
+
"eval_runtime": 53.0251,
|
| 284 |
+
"eval_samples_per_second": 565.77,
|
| 285 |
+
"eval_steps_per_second": 35.361,
|
| 286 |
+
"step": 12000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.2444748679835713,
|
| 290 |
+
"grad_norm": 0.115768201649189,
|
| 291 |
+
"learning_rate": 0.0006805633333333333,
|
| 292 |
+
"loss": 0.0272,
|
| 293 |
+
"step": 12500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.2542538627029141,
|
| 297 |
+
"grad_norm": 0.06682537496089935,
|
| 298 |
+
"learning_rate": 0.0006766744444444444,
|
| 299 |
+
"loss": 0.0258,
|
| 300 |
+
"step": 13000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.2542538627029141,
|
| 304 |
+
"eval_accuracy": 0.9970798095238095,
|
| 305 |
+
"eval_loss": 0.018996767699718475,
|
| 306 |
+
"eval_runtime": 53.1775,
|
| 307 |
+
"eval_samples_per_second": 564.149,
|
| 308 |
+
"eval_steps_per_second": 35.259,
|
| 309 |
+
"step": 13000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.264032857422257,
|
| 313 |
+
"grad_norm": 0.09202491492033005,
|
| 314 |
+
"learning_rate": 0.0006727855555555555,
|
| 315 |
+
"loss": 0.0249,
|
| 316 |
+
"step": 13500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.27381185214159987,
|
| 320 |
+
"grad_norm": 0.08306081593036652,
|
| 321 |
+
"learning_rate": 0.0006688966666666666,
|
| 322 |
+
"loss": 0.0249,
|
| 323 |
+
"step": 14000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.27381185214159987,
|
| 327 |
+
"eval_accuracy": 0.9973076666666667,
|
| 328 |
+
"eval_loss": 0.01746002584695816,
|
| 329 |
+
"eval_runtime": 52.9753,
|
| 330 |
+
"eval_samples_per_second": 566.302,
|
| 331 |
+
"eval_steps_per_second": 35.394,
|
| 332 |
+
"step": 14000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2835908468609427,
|
| 336 |
+
"grad_norm": 0.09477762877941132,
|
| 337 |
+
"learning_rate": 0.0006650077777777777,
|
| 338 |
+
"loss": 0.0233,
|
| 339 |
+
"step": 14500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.29336984158028556,
|
| 343 |
+
"grad_norm": 0.08538249880075455,
|
| 344 |
+
"learning_rate": 0.000661118888888889,
|
| 345 |
+
"loss": 0.0231,
|
| 346 |
+
"step": 15000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.29336984158028556,
|
| 350 |
+
"eval_accuracy": 0.9973289047619047,
|
| 351 |
+
"eval_loss": 0.017424894496798515,
|
| 352 |
+
"eval_runtime": 53.685,
|
| 353 |
+
"eval_samples_per_second": 558.815,
|
| 354 |
+
"eval_steps_per_second": 34.926,
|
| 355 |
+
"step": 15000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.3031488362996284,
|
| 359 |
+
"grad_norm": 0.07964974641799927,
|
| 360 |
+
"learning_rate": 0.00065723,
|
| 361 |
+
"loss": 0.0225,
|
| 362 |
+
"step": 15500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.31292783101897126,
|
| 366 |
+
"grad_norm": 0.14638037979602814,
|
| 367 |
+
"learning_rate": 0.0006533411111111111,
|
| 368 |
+
"loss": 0.0222,
|
| 369 |
+
"step": 16000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.31292783101897126,
|
| 373 |
+
"eval_accuracy": 0.9975395238095238,
|
| 374 |
+
"eval_loss": 0.015860475599765778,
|
| 375 |
+
"eval_runtime": 52.8483,
|
| 376 |
+
"eval_samples_per_second": 567.663,
|
| 377 |
+
"eval_steps_per_second": 35.479,
|
| 378 |
+
"step": 16000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.3227068257383141,
|
| 382 |
+
"grad_norm": 0.08919312059879303,
|
| 383 |
+
"learning_rate": 0.0006494522222222222,
|
| 384 |
+
"loss": 0.0216,
|
| 385 |
+
"step": 16500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.33248582045765696,
|
| 389 |
+
"grad_norm": 0.15240578353405,
|
| 390 |
+
"learning_rate": 0.0006455633333333333,
|
| 391 |
+
"loss": 0.0209,
|
| 392 |
+
"step": 17000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.33248582045765696,
|
| 396 |
+
"eval_accuracy": 0.9974646666666667,
|
| 397 |
+
"eval_loss": 0.016827261075377464,
|
| 398 |
+
"eval_runtime": 53.37,
|
| 399 |
+
"eval_samples_per_second": 562.113,
|
| 400 |
+
"eval_steps_per_second": 35.132,
|
| 401 |
+
"step": 17000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3422648151769998,
|
| 405 |
+
"grad_norm": 0.1320294886827469,
|
| 406 |
+
"learning_rate": 0.0006416744444444444,
|
| 407 |
+
"loss": 0.0208,
|
| 408 |
+
"step": 17500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.35204380989634265,
|
| 412 |
+
"grad_norm": 0.0735507681965828,
|
| 413 |
+
"learning_rate": 0.0006377855555555555,
|
| 414 |
+
"loss": 0.0202,
|
| 415 |
+
"step": 18000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.35204380989634265,
|
| 419 |
+
"eval_accuracy": 0.997734380952381,
|
| 420 |
+
"eval_loss": 0.014700877480208874,
|
| 421 |
+
"eval_runtime": 53.0678,
|
| 422 |
+
"eval_samples_per_second": 565.315,
|
| 423 |
+
"eval_steps_per_second": 35.332,
|
| 424 |
+
"step": 18000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.3618228046156855,
|
| 428 |
+
"grad_norm": 0.08381917327642441,
|
| 429 |
+
"learning_rate": 0.0006338966666666666,
|
| 430 |
+
"loss": 0.02,
|
| 431 |
+
"step": 18500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.37160179933502835,
|
| 435 |
+
"grad_norm": 0.0752609446644783,
|
| 436 |
+
"learning_rate": 0.0006300077777777778,
|
| 437 |
+
"loss": 0.0193,
|
| 438 |
+
"step": 19000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.37160179933502835,
|
| 442 |
+
"eval_accuracy": 0.9978090952380952,
|
| 443 |
+
"eval_loss": 0.01433408260345459,
|
| 444 |
+
"eval_runtime": 53.5916,
|
| 445 |
+
"eval_samples_per_second": 559.789,
|
| 446 |
+
"eval_steps_per_second": 34.987,
|
| 447 |
+
"step": 19000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.3813807940543712,
|
| 451 |
+
"grad_norm": 0.07932694256305695,
|
| 452 |
+
"learning_rate": 0.0006261188888888889,
|
| 453 |
+
"loss": 0.0193,
|
| 454 |
+
"step": 19500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.39115978877371405,
|
| 458 |
+
"grad_norm": 0.10809051245450974,
|
| 459 |
+
"learning_rate": 0.00062223,
|
| 460 |
+
"loss": 0.0178,
|
| 461 |
+
"step": 20000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.39115978877371405,
|
| 465 |
+
"eval_accuracy": 0.997885,
|
| 466 |
+
"eval_loss": 0.013729237020015717,
|
| 467 |
+
"eval_runtime": 56.2141,
|
| 468 |
+
"eval_samples_per_second": 533.674,
|
| 469 |
+
"eval_steps_per_second": 33.355,
|
| 470 |
+
"step": 20000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.4009387834930569,
|
| 474 |
+
"grad_norm": 0.07173776626586914,
|
| 475 |
+
"learning_rate": 0.0006183411111111111,
|
| 476 |
+
"loss": 0.0178,
|
| 477 |
+
"step": 20500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.41071777821239974,
|
| 481 |
+
"grad_norm": 0.09770897030830383,
|
| 482 |
+
"learning_rate": 0.0006144522222222222,
|
| 483 |
+
"loss": 0.0179,
|
| 484 |
+
"step": 21000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.41071777821239974,
|
| 488 |
+
"eval_accuracy": 0.9979653333333334,
|
| 489 |
+
"eval_loss": 0.013427665457129478,
|
| 490 |
+
"eval_runtime": 53.5321,
|
| 491 |
+
"eval_samples_per_second": 560.412,
|
| 492 |
+
"eval_steps_per_second": 35.026,
|
| 493 |
+
"step": 21000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.4204967729317426,
|
| 497 |
+
"grad_norm": 0.07839228957891464,
|
| 498 |
+
"learning_rate": 0.0006105633333333333,
|
| 499 |
+
"loss": 0.0181,
|
| 500 |
+
"step": 21500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4302757676510855,
|
| 504 |
+
"grad_norm": 0.04327086731791496,
|
| 505 |
+
"learning_rate": 0.0006066744444444444,
|
| 506 |
+
"loss": 0.0173,
|
| 507 |
+
"step": 22000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4302757676510855,
|
| 511 |
+
"eval_accuracy": 0.9980109523809524,
|
| 512 |
+
"eval_loss": 0.012947156094014645,
|
| 513 |
+
"eval_runtime": 53.2499,
|
| 514 |
+
"eval_samples_per_second": 563.381,
|
| 515 |
+
"eval_steps_per_second": 35.211,
|
| 516 |
+
"step": 22000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.44005476237042834,
|
| 520 |
+
"grad_norm": 0.053673435002565384,
|
| 521 |
+
"learning_rate": 0.0006027855555555555,
|
| 522 |
+
"loss": 0.0173,
|
| 523 |
+
"step": 22500
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.4498337570897712,
|
| 527 |
+
"grad_norm": 0.06219884008169174,
|
| 528 |
+
"learning_rate": 0.0005988966666666667,
|
| 529 |
+
"loss": 0.0167,
|
| 530 |
+
"step": 23000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.4498337570897712,
|
| 534 |
+
"eval_accuracy": 0.9980908571428572,
|
| 535 |
+
"eval_loss": 0.012620575726032257,
|
| 536 |
+
"eval_runtime": 53.7271,
|
| 537 |
+
"eval_samples_per_second": 558.377,
|
| 538 |
+
"eval_steps_per_second": 34.899,
|
| 539 |
+
"step": 23000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.45961275180911404,
|
| 543 |
+
"grad_norm": 0.04141264408826828,
|
| 544 |
+
"learning_rate": 0.0005950077777777778,
|
| 545 |
+
"loss": 0.0161,
|
| 546 |
+
"step": 23500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.4693917465284569,
|
| 550 |
+
"grad_norm": 0.07115904241800308,
|
| 551 |
+
"learning_rate": 0.0005911188888888889,
|
| 552 |
+
"loss": 0.0168,
|
| 553 |
+
"step": 24000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.4693917465284569,
|
| 557 |
+
"eval_accuracy": 0.9981130476190476,
|
| 558 |
+
"eval_loss": 0.01251070573925972,
|
| 559 |
+
"eval_runtime": 52.7673,
|
| 560 |
+
"eval_samples_per_second": 568.534,
|
| 561 |
+
"eval_steps_per_second": 35.533,
|
| 562 |
+
"step": 24000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.47917074124779974,
|
| 566 |
+
"grad_norm": 0.08638204634189606,
|
| 567 |
+
"learning_rate": 0.00058723,
|
| 568 |
+
"loss": 0.0159,
|
| 569 |
+
"step": 24500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4889497359671426,
|
| 573 |
+
"grad_norm": 0.10276144742965698,
|
| 574 |
+
"learning_rate": 0.0005833411111111111,
|
| 575 |
+
"loss": 0.0161,
|
| 576 |
+
"step": 25000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.4889497359671426,
|
| 580 |
+
"eval_accuracy": 0.9982332857142857,
|
| 581 |
+
"eval_loss": 0.011564305052161217,
|
| 582 |
+
"eval_runtime": 53.2533,
|
| 583 |
+
"eval_samples_per_second": 563.345,
|
| 584 |
+
"eval_steps_per_second": 35.209,
|
| 585 |
+
"step": 25000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.49872873068648543,
|
| 589 |
+
"grad_norm": 0.06187009438872337,
|
| 590 |
+
"learning_rate": 0.0005794522222222222,
|
| 591 |
+
"loss": 0.0153,
|
| 592 |
+
"step": 25500
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5085077254058282,
|
| 596 |
+
"grad_norm": 0.09968678653240204,
|
| 597 |
+
"learning_rate": 0.0005755633333333333,
|
| 598 |
+
"loss": 0.0153,
|
| 599 |
+
"step": 26000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.5085077254058282,
|
| 603 |
+
"eval_accuracy": 0.9983106666666667,
|
| 604 |
+
"eval_loss": 0.011036869138479233,
|
| 605 |
+
"eval_runtime": 52.8497,
|
| 606 |
+
"eval_samples_per_second": 567.648,
|
| 607 |
+
"eval_steps_per_second": 35.478,
|
| 608 |
+
"step": 26000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.5182867201251712,
|
| 612 |
+
"grad_norm": 0.06401211023330688,
|
| 613 |
+
"learning_rate": 0.0005716744444444445,
|
| 614 |
+
"loss": 0.0149,
|
| 615 |
+
"step": 26500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.528065714844514,
|
| 619 |
+
"grad_norm": 0.09270446747541428,
|
| 620 |
+
"learning_rate": 0.0005677855555555556,
|
| 621 |
+
"loss": 0.0149,
|
| 622 |
+
"step": 27000
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.528065714844514,
|
| 626 |
+
"eval_accuracy": 0.9982730952380953,
|
| 627 |
+
"eval_loss": 0.011211142875254154,
|
| 628 |
+
"eval_runtime": 53.6334,
|
| 629 |
+
"eval_samples_per_second": 559.353,
|
| 630 |
+
"eval_steps_per_second": 34.96,
|
| 631 |
+
"step": 27000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.5378447095638569,
|
| 635 |
+
"grad_norm": 0.09460537880659103,
|
| 636 |
+
"learning_rate": 0.0005638966666666667,
|
| 637 |
+
"loss": 0.015,
|
| 638 |
+
"step": 27500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.5476237042831997,
|
| 642 |
+
"grad_norm": 0.06823355704545975,
|
| 643 |
+
"learning_rate": 0.0005600077777777778,
|
| 644 |
+
"loss": 0.0146,
|
| 645 |
+
"step": 28000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.5476237042831997,
|
| 649 |
+
"eval_accuracy": 0.9983301428571428,
|
| 650 |
+
"eval_loss": 0.01109024602919817,
|
| 651 |
+
"eval_runtime": 52.7069,
|
| 652 |
+
"eval_samples_per_second": 569.185,
|
| 653 |
+
"eval_steps_per_second": 35.574,
|
| 654 |
+
"step": 28000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5574026990025426,
|
| 658 |
+
"grad_norm": 0.0623260997235775,
|
| 659 |
+
"learning_rate": 0.0005561188888888889,
|
| 660 |
+
"loss": 0.0142,
|
| 661 |
+
"step": 28500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5671816937218854,
|
| 665 |
+
"grad_norm": 0.055208127945661545,
|
| 666 |
+
"learning_rate": 0.00055223,
|
| 667 |
+
"loss": 0.0143,
|
| 668 |
+
"step": 29000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5671816937218854,
|
| 672 |
+
"eval_accuracy": 0.9984018095238095,
|
| 673 |
+
"eval_loss": 0.010609026066958904,
|
| 674 |
+
"eval_runtime": 53.929,
|
| 675 |
+
"eval_samples_per_second": 556.287,
|
| 676 |
+
"eval_steps_per_second": 34.768,
|
| 677 |
+
"step": 29000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.5769606884412283,
|
| 681 |
+
"grad_norm": 0.057654768228530884,
|
| 682 |
+
"learning_rate": 0.000548341111111111,
|
| 683 |
+
"loss": 0.0146,
|
| 684 |
+
"step": 29500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.5867396831605711,
|
| 688 |
+
"grad_norm": 0.10069073736667633,
|
| 689 |
+
"learning_rate": 0.0005444522222222222,
|
| 690 |
+
"loss": 0.0136,
|
| 691 |
+
"step": 30000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.5867396831605711,
|
| 695 |
+
"eval_accuracy": 0.9984032857142857,
|
| 696 |
+
"eval_loss": 0.01064229290932417,
|
| 697 |
+
"eval_runtime": 53.1545,
|
| 698 |
+
"eval_samples_per_second": 564.392,
|
| 699 |
+
"eval_steps_per_second": 35.275,
|
| 700 |
+
"step": 30000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.596518677879914,
|
| 704 |
+
"grad_norm": 0.022035960108041763,
|
| 705 |
+
"learning_rate": 0.0005405633333333334,
|
| 706 |
+
"loss": 0.0137,
|
| 707 |
+
"step": 30500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.6062976725992568,
|
| 711 |
+
"grad_norm": 0.05899837240576744,
|
| 712 |
+
"learning_rate": 0.0005366744444444445,
|
| 713 |
+
"loss": 0.0138,
|
| 714 |
+
"step": 31000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.6062976725992568,
|
| 718 |
+
"eval_accuracy": 0.9984709047619048,
|
| 719 |
+
"eval_loss": 0.009958229959011078,
|
| 720 |
+
"eval_runtime": 54.4759,
|
| 721 |
+
"eval_samples_per_second": 550.702,
|
| 722 |
+
"eval_steps_per_second": 34.419,
|
| 723 |
+
"step": 31000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6160766673185997,
|
| 727 |
+
"grad_norm": 0.10861151665449142,
|
| 728 |
+
"learning_rate": 0.0005327855555555556,
|
| 729 |
+
"loss": 0.0135,
|
| 730 |
+
"step": 31500
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6258556620379425,
|
| 734 |
+
"grad_norm": 0.05685458332300186,
|
| 735 |
+
"learning_rate": 0.0005288966666666667,
|
| 736 |
+
"loss": 0.013,
|
| 737 |
+
"step": 32000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.6258556620379425,
|
| 741 |
+
"eval_accuracy": 0.9985278095238095,
|
| 742 |
+
"eval_loss": 0.009605683386325836,
|
| 743 |
+
"eval_runtime": 53.4302,
|
| 744 |
+
"eval_samples_per_second": 561.48,
|
| 745 |
+
"eval_steps_per_second": 35.093,
|
| 746 |
+
"step": 32000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.6356346567572854,
|
| 750 |
+
"grad_norm": 0.0556936115026474,
|
| 751 |
+
"learning_rate": 0.0005250077777777777,
|
| 752 |
+
"loss": 0.0133,
|
| 753 |
+
"step": 32500
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.6454136514766282,
|
| 757 |
+
"grad_norm": 0.045375969260931015,
|
| 758 |
+
"learning_rate": 0.0005211188888888889,
|
| 759 |
+
"loss": 0.0128,
|
| 760 |
+
"step": 33000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.6454136514766282,
|
| 764 |
+
"eval_accuracy": 0.9985240952380953,
|
| 765 |
+
"eval_loss": 0.009833588264882565,
|
| 766 |
+
"eval_runtime": 53.6384,
|
| 767 |
+
"eval_samples_per_second": 559.301,
|
| 768 |
+
"eval_steps_per_second": 34.956,
|
| 769 |
+
"step": 33000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.6551926461959711,
|
| 773 |
+
"grad_norm": 0.07633641362190247,
|
| 774 |
+
"learning_rate": 0.00051723,
|
| 775 |
+
"loss": 0.0128,
|
| 776 |
+
"step": 33500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.6649716409153139,
|
| 780 |
+
"grad_norm": 0.042216092348098755,
|
| 781 |
+
"learning_rate": 0.0005133411111111111,
|
| 782 |
+
"loss": 0.0127,
|
| 783 |
+
"step": 34000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6649716409153139,
|
| 787 |
+
"eval_accuracy": 0.9985537142857143,
|
| 788 |
+
"eval_loss": 0.009525810368359089,
|
| 789 |
+
"eval_runtime": 53.4483,
|
| 790 |
+
"eval_samples_per_second": 561.291,
|
| 791 |
+
"eval_steps_per_second": 35.081,
|
| 792 |
+
"step": 34000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.6747506356346568,
|
| 796 |
+
"grad_norm": 0.06529881060123444,
|
| 797 |
+
"learning_rate": 0.0005094522222222223,
|
| 798 |
+
"loss": 0.0119,
|
| 799 |
+
"step": 34500
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.6845296303539996,
|
| 803 |
+
"grad_norm": 0.08874630928039551,
|
| 804 |
+
"learning_rate": 0.0005055633333333333,
|
| 805 |
+
"loss": 0.0126,
|
| 806 |
+
"step": 35000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.6845296303539996,
|
| 810 |
+
"eval_accuracy": 0.9986020476190476,
|
| 811 |
+
"eval_loss": 0.009064077399671078,
|
| 812 |
+
"eval_runtime": 52.7726,
|
| 813 |
+
"eval_samples_per_second": 568.477,
|
| 814 |
+
"eval_steps_per_second": 35.53,
|
| 815 |
+
"step": 35000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6943086250733425,
|
| 819 |
+
"grad_norm": 0.055686578154563904,
|
| 820 |
+
"learning_rate": 0.0005016744444444444,
|
| 821 |
+
"loss": 0.0122,
|
| 822 |
+
"step": 35500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7040876197926853,
|
| 826 |
+
"grad_norm": 0.06874644011259079,
|
| 827 |
+
"learning_rate": 0.0004977855555555555,
|
| 828 |
+
"loss": 0.0122,
|
| 829 |
+
"step": 36000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7040876197926853,
|
| 833 |
+
"eval_accuracy": 0.9986208571428571,
|
| 834 |
+
"eval_loss": 0.009121677838265896,
|
| 835 |
+
"eval_runtime": 53.0769,
|
| 836 |
+
"eval_samples_per_second": 565.218,
|
| 837 |
+
"eval_steps_per_second": 35.326,
|
| 838 |
+
"step": 36000
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.7138666145120282,
|
| 842 |
+
"grad_norm": 0.057503316551446915,
|
| 843 |
+
"learning_rate": 0.0004938966666666667,
|
| 844 |
+
"loss": 0.0122,
|
| 845 |
+
"step": 36500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.723645609231371,
|
| 849 |
+
"grad_norm": 0.06306219100952148,
|
| 850 |
+
"learning_rate": 0.0004900077777777778,
|
| 851 |
+
"loss": 0.0124,
|
| 852 |
+
"step": 37000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.723645609231371,
|
| 856 |
+
"eval_accuracy": 0.9986166666666667,
|
| 857 |
+
"eval_loss": 0.009038920514285564,
|
| 858 |
+
"eval_runtime": 53.2946,
|
| 859 |
+
"eval_samples_per_second": 562.908,
|
| 860 |
+
"eval_steps_per_second": 35.182,
|
| 861 |
+
"step": 37000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.7334246039507138,
|
| 865 |
+
"grad_norm": 0.09351666271686554,
|
| 866 |
+
"learning_rate": 0.00048611888888888894,
|
| 867 |
+
"loss": 0.012,
|
| 868 |
+
"step": 37500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.7432035986700567,
|
| 872 |
+
"grad_norm": 0.0897260531783104,
|
| 873 |
+
"learning_rate": 0.00048222999999999994,
|
| 874 |
+
"loss": 0.0118,
|
| 875 |
+
"step": 38000
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.7432035986700567,
|
| 879 |
+
"eval_accuracy": 0.9986792857142858,
|
| 880 |
+
"eval_loss": 0.008696652948856354,
|
| 881 |
+
"eval_runtime": 54.4099,
|
| 882 |
+
"eval_samples_per_second": 551.37,
|
| 883 |
+
"eval_steps_per_second": 34.461,
|
| 884 |
+
"step": 38000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.7529825933893995,
|
| 888 |
+
"grad_norm": 0.04299278184771538,
|
| 889 |
+
"learning_rate": 0.0004783411111111111,
|
| 890 |
+
"loss": 0.012,
|
| 891 |
+
"step": 38500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7627615881087424,
|
| 895 |
+
"grad_norm": 0.04438682273030281,
|
| 896 |
+
"learning_rate": 0.0004744522222222222,
|
| 897 |
+
"loss": 0.0116,
|
| 898 |
+
"step": 39000
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7627615881087424,
|
| 902 |
+
"eval_accuracy": 0.9986683333333334,
|
| 903 |
+
"eval_loss": 0.008706375025212765,
|
| 904 |
+
"eval_runtime": 53.9467,
|
| 905 |
+
"eval_samples_per_second": 556.105,
|
| 906 |
+
"eval_steps_per_second": 34.757,
|
| 907 |
+
"step": 39000
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.7725405828280852,
|
| 911 |
+
"grad_norm": 0.06099909543991089,
|
| 912 |
+
"learning_rate": 0.00047056333333333333,
|
| 913 |
+
"loss": 0.0115,
|
| 914 |
+
"step": 39500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.7823195775474281,
|
| 918 |
+
"grad_norm": 0.07929019629955292,
|
| 919 |
+
"learning_rate": 0.00046667444444444445,
|
| 920 |
+
"loss": 0.0115,
|
| 921 |
+
"step": 40000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.7823195775474281,
|
| 925 |
+
"eval_accuracy": 0.9987148571428571,
|
| 926 |
+
"eval_loss": 0.008460523560643196,
|
| 927 |
+
"eval_runtime": 53.1953,
|
| 928 |
+
"eval_samples_per_second": 563.959,
|
| 929 |
+
"eval_steps_per_second": 35.247,
|
| 930 |
+
"step": 40000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.7920985722667709,
|
| 934 |
+
"grad_norm": 0.063071608543396,
|
| 935 |
+
"learning_rate": 0.0004627855555555555,
|
| 936 |
+
"loss": 0.0113,
|
| 937 |
+
"step": 40500
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.8018775669861138,
|
| 941 |
+
"grad_norm": 0.08535472303628922,
|
| 942 |
+
"learning_rate": 0.0004588966666666666,
|
| 943 |
+
"loss": 0.011,
|
| 944 |
+
"step": 41000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.8018775669861138,
|
| 948 |
+
"eval_accuracy": 0.9987766666666666,
|
| 949 |
+
"eval_loss": 0.00813833624124527,
|
| 950 |
+
"eval_runtime": 52.7545,
|
| 951 |
+
"eval_samples_per_second": 568.672,
|
| 952 |
+
"eval_steps_per_second": 35.542,
|
| 953 |
+
"step": 41000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.8116565617054566,
|
| 957 |
+
"grad_norm": 0.06376124918460846,
|
| 958 |
+
"learning_rate": 0.0004550077777777778,
|
| 959 |
+
"loss": 0.0113,
|
| 960 |
+
"step": 41500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.8214355564247995,
|
| 964 |
+
"grad_norm": 0.057552047073841095,
|
| 965 |
+
"learning_rate": 0.0004511188888888889,
|
| 966 |
+
"loss": 0.011,
|
| 967 |
+
"step": 42000
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.8214355564247995,
|
| 971 |
+
"eval_accuracy": 0.9987588095238096,
|
| 972 |
+
"eval_loss": 0.00814767088741064,
|
| 973 |
+
"eval_runtime": 52.6286,
|
| 974 |
+
"eval_samples_per_second": 570.033,
|
| 975 |
+
"eval_steps_per_second": 35.627,
|
| 976 |
+
"step": 42000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8312145511441423,
|
| 980 |
+
"grad_norm": 0.11143315583467484,
|
| 981 |
+
"learning_rate": 0.00044723,
|
| 982 |
+
"loss": 0.0107,
|
| 983 |
+
"step": 42500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8409935458634852,
|
| 987 |
+
"grad_norm": 0.04874800890684128,
|
| 988 |
+
"learning_rate": 0.0004433411111111111,
|
| 989 |
+
"loss": 0.011,
|
| 990 |
+
"step": 43000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8409935458634852,
|
| 994 |
+
"eval_accuracy": 0.9987991428571429,
|
| 995 |
+
"eval_loss": 0.007788496091961861,
|
| 996 |
+
"eval_runtime": 54.0001,
|
| 997 |
+
"eval_samples_per_second": 555.554,
|
| 998 |
+
"eval_steps_per_second": 34.722,
|
| 999 |
+
"step": 43000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.8507725405828281,
|
| 1003 |
+
"grad_norm": 0.13771504163742065,
|
| 1004 |
+
"learning_rate": 0.0004394522222222222,
|
| 1005 |
+
"loss": 0.0104,
|
| 1006 |
+
"step": 43500
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.860551535302171,
|
| 1010 |
+
"grad_norm": 0.09559216350317001,
|
| 1011 |
+
"learning_rate": 0.0004355633333333333,
|
| 1012 |
+
"loss": 0.0105,
|
| 1013 |
+
"step": 44000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.860551535302171,
|
| 1017 |
+
"eval_accuracy": 0.9988242380952381,
|
| 1018 |
+
"eval_loss": 0.007781007327139378,
|
| 1019 |
+
"eval_runtime": 52.7492,
|
| 1020 |
+
"eval_samples_per_second": 568.729,
|
| 1021 |
+
"eval_steps_per_second": 35.546,
|
| 1022 |
+
"step": 44000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.8703305300215138,
|
| 1026 |
+
"grad_norm": 0.057924531400203705,
|
| 1027 |
+
"learning_rate": 0.0004316744444444444,
|
| 1028 |
+
"loss": 0.0107,
|
| 1029 |
+
"step": 44500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.8801095247408567,
|
| 1033 |
+
"grad_norm": 0.025040749460458755,
|
| 1034 |
+
"learning_rate": 0.0004277855555555556,
|
| 1035 |
+
"loss": 0.0103,
|
| 1036 |
+
"step": 45000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.8801095247408567,
|
| 1040 |
+
"eval_accuracy": 0.998757761904762,
|
| 1041 |
+
"eval_loss": 0.008185211569070816,
|
| 1042 |
+
"eval_runtime": 53.6018,
|
| 1043 |
+
"eval_samples_per_second": 559.683,
|
| 1044 |
+
"eval_steps_per_second": 34.98,
|
| 1045 |
+
"step": 45000
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.8898885194601995,
|
| 1049 |
+
"grad_norm": 0.053779345005750656,
|
| 1050 |
+
"learning_rate": 0.0004238966666666667,
|
| 1051 |
+
"loss": 0.0104,
|
| 1052 |
+
"step": 45500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8996675141795424,
|
| 1056 |
+
"grad_norm": 0.05005486682057381,
|
| 1057 |
+
"learning_rate": 0.0004200077777777778,
|
| 1058 |
+
"loss": 0.0102,
|
| 1059 |
+
"step": 46000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8996675141795424,
|
| 1063 |
+
"eval_accuracy": 0.9988352380952381,
|
| 1064 |
+
"eval_loss": 0.007613138295710087,
|
| 1065 |
+
"eval_runtime": 52.8966,
|
| 1066 |
+
"eval_samples_per_second": 567.144,
|
| 1067 |
+
"eval_steps_per_second": 35.447,
|
| 1068 |
+
"step": 46000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.9094465088988852,
|
| 1072 |
+
"grad_norm": 0.043240178376436234,
|
| 1073 |
+
"learning_rate": 0.00041611888888888886,
|
| 1074 |
+
"loss": 0.0101,
|
| 1075 |
+
"step": 46500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.9192255036182281,
|
| 1079 |
+
"grad_norm": 0.029988329857587814,
|
| 1080 |
+
"learning_rate": 0.00041223,
|
| 1081 |
+
"loss": 0.01,
|
| 1082 |
+
"step": 47000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.9192255036182281,
|
| 1086 |
+
"eval_accuracy": 0.9988660952380952,
|
| 1087 |
+
"eval_loss": 0.007510754279792309,
|
| 1088 |
+
"eval_runtime": 53.877,
|
| 1089 |
+
"eval_samples_per_second": 556.824,
|
| 1090 |
+
"eval_steps_per_second": 34.801,
|
| 1091 |
+
"step": 47000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.9290044983375709,
|
| 1095 |
+
"grad_norm": 0.028314834460616112,
|
| 1096 |
+
"learning_rate": 0.0004083411111111111,
|
| 1097 |
+
"loss": 0.0104,
|
| 1098 |
+
"step": 47500
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.9387834930569138,
|
| 1102 |
+
"grad_norm": 0.08818221092224121,
|
| 1103 |
+
"learning_rate": 0.00040445222222222226,
|
| 1104 |
+
"loss": 0.0098,
|
| 1105 |
+
"step": 48000
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.9387834930569138,
|
| 1109 |
+
"eval_accuracy": 0.9988974285714286,
|
| 1110 |
+
"eval_loss": 0.007295026443898678,
|
| 1111 |
+
"eval_runtime": 52.7978,
|
| 1112 |
+
"eval_samples_per_second": 568.205,
|
| 1113 |
+
"eval_steps_per_second": 35.513,
|
| 1114 |
+
"step": 48000
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.9485624877762566,
|
| 1118 |
+
"grad_norm": 0.0640278309583664,
|
| 1119 |
+
"learning_rate": 0.00040056333333333337,
|
| 1120 |
+
"loss": 0.0101,
|
| 1121 |
+
"step": 48500
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.9583414824955995,
|
| 1125 |
+
"grad_norm": 0.03510857746005058,
|
| 1126 |
+
"learning_rate": 0.0003966744444444444,
|
| 1127 |
+
"loss": 0.0099,
|
| 1128 |
+
"step": 49000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.9583414824955995,
|
| 1132 |
+
"eval_accuracy": 0.9989037142857143,
|
| 1133 |
+
"eval_loss": 0.007324465550482273,
|
| 1134 |
+
"eval_runtime": 54.4288,
|
| 1135 |
+
"eval_samples_per_second": 551.178,
|
| 1136 |
+
"eval_steps_per_second": 34.449,
|
| 1137 |
+
"step": 49000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9681204772149423,
|
| 1141 |
+
"grad_norm": 0.043459728360176086,
|
| 1142 |
+
"learning_rate": 0.00039278555555555554,
|
| 1143 |
+
"loss": 0.01,
|
| 1144 |
+
"step": 49500
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.9778994719342852,
|
| 1148 |
+
"grad_norm": 0.04011424630880356,
|
| 1149 |
+
"learning_rate": 0.00038889666666666665,
|
| 1150 |
+
"loss": 0.0096,
|
| 1151 |
+
"step": 50000
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.9778994719342852,
|
| 1155 |
+
"eval_accuracy": 0.9989349523809524,
|
| 1156 |
+
"eval_loss": 0.0070013017393648624,
|
| 1157 |
+
"eval_runtime": 53.5062,
|
| 1158 |
+
"eval_samples_per_second": 560.682,
|
| 1159 |
+
"eval_steps_per_second": 35.043,
|
| 1160 |
+
"step": 50000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.987678466653628,
|
| 1164 |
+
"grad_norm": 0.06863726675510406,
|
| 1165 |
+
"learning_rate": 0.00038500777777777777,
|
| 1166 |
+
"loss": 0.0097,
|
| 1167 |
+
"step": 50500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.9974574613729709,
|
| 1171 |
+
"grad_norm": 0.05349302664399147,
|
| 1172 |
+
"learning_rate": 0.0003811188888888889,
|
| 1173 |
+
"loss": 0.0096,
|
| 1174 |
+
"step": 51000
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.9974574613729709,
|
| 1178 |
+
"eval_accuracy": 0.9989138571428572,
|
| 1179 |
+
"eval_loss": 0.007190499920397997,
|
| 1180 |
+
"eval_runtime": 54.3897,
|
| 1181 |
+
"eval_samples_per_second": 551.575,
|
| 1182 |
+
"eval_steps_per_second": 34.473,
|
| 1183 |
+
"step": 51000
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 1.0072364560923137,
|
| 1187 |
+
"grad_norm": 0.08378108590841293,
|
| 1188 |
+
"learning_rate": 0.00037723000000000005,
|
| 1189 |
+
"loss": 0.0091,
|
| 1190 |
+
"step": 51500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.0170154508116567,
|
| 1194 |
+
"grad_norm": 0.0374823622405529,
|
| 1195 |
+
"learning_rate": 0.00037334111111111105,
|
| 1196 |
+
"loss": 0.0092,
|
| 1197 |
+
"step": 52000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.0170154508116567,
|
| 1201 |
+
"eval_accuracy": 0.9989398571428572,
|
| 1202 |
+
"eval_loss": 0.006978238001465797,
|
| 1203 |
+
"eval_runtime": 53.5696,
|
| 1204 |
+
"eval_samples_per_second": 560.019,
|
| 1205 |
+
"eval_steps_per_second": 35.001,
|
| 1206 |
+
"step": 52000
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.0267944455309994,
|
| 1210 |
+
"grad_norm": 0.047528065741062164,
|
| 1211 |
+
"learning_rate": 0.0003694522222222222,
|
| 1212 |
+
"loss": 0.009,
|
| 1213 |
+
"step": 52500
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.0365734402503424,
|
| 1217 |
+
"grad_norm": 0.038852859288454056,
|
| 1218 |
+
"learning_rate": 0.00036556333333333333,
|
| 1219 |
+
"loss": 0.0086,
|
| 1220 |
+
"step": 53000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.0365734402503424,
|
| 1224 |
+
"eval_accuracy": 0.998927761904762,
|
| 1225 |
+
"eval_loss": 0.007132695522159338,
|
| 1226 |
+
"eval_runtime": 54.5713,
|
| 1227 |
+
"eval_samples_per_second": 549.739,
|
| 1228 |
+
"eval_steps_per_second": 34.359,
|
| 1229 |
+
"step": 53000
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.046352434969685,
|
| 1233 |
+
"grad_norm": 0.03156827762722969,
|
| 1234 |
+
"learning_rate": 0.00036167444444444444,
|
| 1235 |
+
"loss": 0.0087,
|
| 1236 |
+
"step": 53500
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.056131429689028,
|
| 1240 |
+
"grad_norm": 0.053986478596925735,
|
| 1241 |
+
"learning_rate": 0.00035778555555555556,
|
| 1242 |
+
"loss": 0.0088,
|
| 1243 |
+
"step": 54000
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.056131429689028,
|
| 1247 |
+
"eval_accuracy": 0.9989908571428572,
|
| 1248 |
+
"eval_loss": 0.00665958970785141,
|
| 1249 |
+
"eval_runtime": 54.0746,
|
| 1250 |
+
"eval_samples_per_second": 554.789,
|
| 1251 |
+
"eval_steps_per_second": 34.674,
|
| 1252 |
+
"step": 54000
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.0659104244083708,
|
| 1256 |
+
"grad_norm": 0.08756107836961746,
|
| 1257 |
+
"learning_rate": 0.0003538966666666667,
|
| 1258 |
+
"loss": 0.0089,
|
| 1259 |
+
"step": 54500
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.0756894191277138,
|
| 1263 |
+
"grad_norm": 0.043076518923044205,
|
| 1264 |
+
"learning_rate": 0.00035000777777777773,
|
| 1265 |
+
"loss": 0.0086,
|
| 1266 |
+
"step": 55000
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.0756894191277138,
|
| 1270 |
+
"eval_accuracy": 0.9989683333333333,
|
| 1271 |
+
"eval_loss": 0.006806574296206236,
|
| 1272 |
+
"eval_runtime": 53.0136,
|
| 1273 |
+
"eval_samples_per_second": 565.893,
|
| 1274 |
+
"eval_steps_per_second": 35.368,
|
| 1275 |
+
"step": 55000
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.0854684138470565,
|
| 1279 |
+
"grad_norm": 0.045110370963811874,
|
| 1280 |
+
"learning_rate": 0.0003461188888888889,
|
| 1281 |
+
"loss": 0.0086,
|
| 1282 |
+
"step": 55500
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.0952474085663995,
|
| 1286 |
+
"grad_norm": 0.07282647490501404,
|
| 1287 |
+
"learning_rate": 0.00034223,
|
| 1288 |
+
"loss": 0.0085,
|
| 1289 |
+
"step": 56000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.0952474085663995,
|
| 1293 |
+
"eval_accuracy": 0.999018619047619,
|
| 1294 |
+
"eval_loss": 0.0064543625339865685,
|
| 1295 |
+
"eval_runtime": 53.2023,
|
| 1296 |
+
"eval_samples_per_second": 563.886,
|
| 1297 |
+
"eval_steps_per_second": 35.243,
|
| 1298 |
+
"step": 56000
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.1050264032857422,
|
| 1302 |
+
"grad_norm": 0.04573039337992668,
|
| 1303 |
+
"learning_rate": 0.0003383411111111111,
|
| 1304 |
+
"loss": 0.0086,
|
| 1305 |
+
"step": 56500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.1148053980050852,
|
| 1309 |
+
"grad_norm": 0.05251363664865494,
|
| 1310 |
+
"learning_rate": 0.00033445222222222223,
|
| 1311 |
+
"loss": 0.0084,
|
| 1312 |
+
"step": 57000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.1148053980050852,
|
| 1316 |
+
"eval_accuracy": 0.9990125714285715,
|
| 1317 |
+
"eval_loss": 0.0065638781525194645,
|
| 1318 |
+
"eval_runtime": 53.3535,
|
| 1319 |
+
"eval_samples_per_second": 562.288,
|
| 1320 |
+
"eval_steps_per_second": 35.143,
|
| 1321 |
+
"step": 57000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.124584392724428,
|
| 1325 |
+
"grad_norm": 0.07058829069137573,
|
| 1326 |
+
"learning_rate": 0.00033056333333333335,
|
| 1327 |
+
"loss": 0.0084,
|
| 1328 |
+
"step": 57500
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.1343633874437709,
|
| 1332 |
+
"grad_norm": 0.07536671310663223,
|
| 1333 |
+
"learning_rate": 0.00032667444444444446,
|
| 1334 |
+
"loss": 0.0087,
|
| 1335 |
+
"step": 58000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 1.1343633874437709,
|
| 1339 |
+
"eval_accuracy": 0.9990162857142857,
|
| 1340 |
+
"eval_loss": 0.006422844249755144,
|
| 1341 |
+
"eval_runtime": 53.4988,
|
| 1342 |
+
"eval_samples_per_second": 560.76,
|
| 1343 |
+
"eval_steps_per_second": 35.048,
|
| 1344 |
+
"step": 58000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.1441423821631136,
|
| 1348 |
+
"grad_norm": 0.039396729320287704,
|
| 1349 |
+
"learning_rate": 0.0003227855555555555,
|
| 1350 |
+
"loss": 0.0083,
|
| 1351 |
+
"step": 58500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 1.1539213768824566,
|
| 1355 |
+
"grad_norm": 0.04912455752491951,
|
| 1356 |
+
"learning_rate": 0.0003188966666666667,
|
| 1357 |
+
"loss": 0.008,
|
| 1358 |
+
"step": 59000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.1539213768824566,
|
| 1362 |
+
"eval_accuracy": 0.9990406190476191,
|
| 1363 |
+
"eval_loss": 0.0063902209512889385,
|
| 1364 |
+
"eval_runtime": 53.4963,
|
| 1365 |
+
"eval_samples_per_second": 560.786,
|
| 1366 |
+
"eval_steps_per_second": 35.049,
|
| 1367 |
+
"step": 59000
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.1637003716017993,
|
| 1371 |
+
"grad_norm": 0.053690288215875626,
|
| 1372 |
+
"learning_rate": 0.00031500777777777774,
|
| 1373 |
+
"loss": 0.0081,
|
| 1374 |
+
"step": 59500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.1734793663211422,
|
| 1378 |
+
"grad_norm": 0.043203726410865784,
|
| 1379 |
+
"learning_rate": 0.00031111888888888886,
|
| 1380 |
+
"loss": 0.008,
|
| 1381 |
+
"step": 60000
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.1734793663211422,
|
| 1385 |
+
"eval_accuracy": 0.999062,
|
| 1386 |
+
"eval_loss": 0.006215290632098913,
|
| 1387 |
+
"eval_runtime": 53.8759,
|
| 1388 |
+
"eval_samples_per_second": 556.835,
|
| 1389 |
+
"eval_steps_per_second": 34.802,
|
| 1390 |
+
"step": 60000
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.183258361040485,
|
| 1394 |
+
"grad_norm": 0.02124057710170746,
|
| 1395 |
+
"learning_rate": 0.00030723,
|
| 1396 |
+
"loss": 0.008,
|
| 1397 |
+
"step": 60500
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.193037355759828,
|
| 1401 |
+
"grad_norm": 0.05668085440993309,
|
| 1402 |
+
"learning_rate": 0.0003033411111111111,
|
| 1403 |
+
"loss": 0.0079,
|
| 1404 |
+
"step": 61000
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 1.193037355759828,
|
| 1408 |
+
"eval_accuracy": 0.9990741428571429,
|
| 1409 |
+
"eval_loss": 0.006143416278064251,
|
| 1410 |
+
"eval_runtime": 53.0541,
|
| 1411 |
+
"eval_samples_per_second": 565.461,
|
| 1412 |
+
"eval_steps_per_second": 35.341,
|
| 1413 |
+
"step": 61000
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.2028163504791707,
|
| 1417 |
+
"grad_norm": 0.03382324427366257,
|
| 1418 |
+
"learning_rate": 0.0002994522222222222,
|
| 1419 |
+
"loss": 0.0081,
|
| 1420 |
+
"step": 61500
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.2125953451985136,
|
| 1424 |
+
"grad_norm": 0.03907141834497452,
|
| 1425 |
+
"learning_rate": 0.00029556333333333336,
|
| 1426 |
+
"loss": 0.008,
|
| 1427 |
+
"step": 62000
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.2125953451985136,
|
| 1431 |
+
"eval_accuracy": 0.999088619047619,
|
| 1432 |
+
"eval_loss": 0.006103618070483208,
|
| 1433 |
+
"eval_runtime": 53.5062,
|
| 1434 |
+
"eval_samples_per_second": 560.682,
|
| 1435 |
+
"eval_steps_per_second": 35.043,
|
| 1436 |
+
"step": 62000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.2223743399178564,
|
| 1440 |
+
"grad_norm": 0.06705312430858612,
|
| 1441 |
+
"learning_rate": 0.0002916744444444444,
|
| 1442 |
+
"loss": 0.0078,
|
| 1443 |
+
"step": 62500
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.2321533346371993,
|
| 1447 |
+
"grad_norm": 0.0315241776406765,
|
| 1448 |
+
"learning_rate": 0.00028778555555555554,
|
| 1449 |
+
"loss": 0.0078,
|
| 1450 |
+
"step": 63000
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.2321533346371993,
|
| 1454 |
+
"eval_accuracy": 0.9991044285714286,
|
| 1455 |
+
"eval_loss": 0.005926877725869417,
|
| 1456 |
+
"eval_runtime": 52.7391,
|
| 1457 |
+
"eval_samples_per_second": 568.838,
|
| 1458 |
+
"eval_steps_per_second": 35.552,
|
| 1459 |
+
"step": 63000
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.241932329356542,
|
| 1463 |
+
"grad_norm": 0.03399759903550148,
|
| 1464 |
+
"learning_rate": 0.0002838966666666667,
|
| 1465 |
+
"loss": 0.0082,
|
| 1466 |
+
"step": 63500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.251711324075885,
|
| 1470 |
+
"grad_norm": 0.031129080802202225,
|
| 1471 |
+
"learning_rate": 0.00028000777777777776,
|
| 1472 |
+
"loss": 0.0076,
|
| 1473 |
+
"step": 64000
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.251711324075885,
|
| 1477 |
+
"eval_accuracy": 0.9990952380952381,
|
| 1478 |
+
"eval_loss": 0.005983012728393078,
|
| 1479 |
+
"eval_runtime": 53.3673,
|
| 1480 |
+
"eval_samples_per_second": 562.142,
|
| 1481 |
+
"eval_steps_per_second": 35.134,
|
| 1482 |
+
"step": 64000
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.2614903187952278,
|
| 1486 |
+
"grad_norm": 0.016778629273176193,
|
| 1487 |
+
"learning_rate": 0.0002761188888888889,
|
| 1488 |
+
"loss": 0.0079,
|
| 1489 |
+
"step": 64500
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 1.2712693135145707,
|
| 1493 |
+
"grad_norm": 0.05320531502366066,
|
| 1494 |
+
"learning_rate": 0.00027223,
|
| 1495 |
+
"loss": 0.0076,
|
| 1496 |
+
"step": 65000
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.2712693135145707,
|
| 1500 |
+
"eval_accuracy": 0.9990500952380953,
|
| 1501 |
+
"eval_loss": 0.0063087414018809795,
|
| 1502 |
+
"eval_runtime": 52.7484,
|
| 1503 |
+
"eval_samples_per_second": 568.737,
|
| 1504 |
+
"eval_steps_per_second": 35.546,
|
| 1505 |
+
"step": 65000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.2810483082339137,
|
| 1509 |
+
"grad_norm": 0.03897105157375336,
|
| 1510 |
+
"learning_rate": 0.0002683411111111111,
|
| 1511 |
+
"loss": 0.0074,
|
| 1512 |
+
"step": 65500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.2908273029532564,
|
| 1516 |
+
"grad_norm": 0.041894931346178055,
|
| 1517 |
+
"learning_rate": 0.0002644522222222222,
|
| 1518 |
+
"loss": 0.0076,
|
| 1519 |
+
"step": 66000
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.2908273029532564,
|
| 1523 |
+
"eval_accuracy": 0.999131619047619,
|
| 1524 |
+
"eval_loss": 0.0057442025281488895,
|
| 1525 |
+
"eval_runtime": 53.3127,
|
| 1526 |
+
"eval_samples_per_second": 562.718,
|
| 1527 |
+
"eval_steps_per_second": 35.17,
|
| 1528 |
+
"step": 66000
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.3006062976725992,
|
| 1532 |
+
"grad_norm": 0.06313379108905792,
|
| 1533 |
+
"learning_rate": 0.0002605633333333333,
|
| 1534 |
+
"loss": 0.0076,
|
| 1535 |
+
"step": 66500
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.3103852923919421,
|
| 1539 |
+
"grad_norm": 0.12118718773126602,
|
| 1540 |
+
"learning_rate": 0.00025667444444444444,
|
| 1541 |
+
"loss": 0.0073,
|
| 1542 |
+
"step": 67000
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.3103852923919421,
|
| 1546 |
+
"eval_accuracy": 0.9991423333333334,
|
| 1547 |
+
"eval_loss": 0.005724221933633089,
|
| 1548 |
+
"eval_runtime": 53.4182,
|
| 1549 |
+
"eval_samples_per_second": 561.607,
|
| 1550 |
+
"eval_steps_per_second": 35.1,
|
| 1551 |
+
"step": 67000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.320164287111285,
|
| 1555 |
+
"grad_norm": 0.024507887661457062,
|
| 1556 |
+
"learning_rate": 0.00025278555555555555,
|
| 1557 |
+
"loss": 0.0078,
|
| 1558 |
+
"step": 67500
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.3299432818306278,
|
| 1562 |
+
"grad_norm": 0.0526452362537384,
|
| 1563 |
+
"learning_rate": 0.00024889666666666666,
|
| 1564 |
+
"loss": 0.0073,
|
| 1565 |
+
"step": 68000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.3299432818306278,
|
| 1569 |
+
"eval_accuracy": 0.9991475714285715,
|
| 1570 |
+
"eval_loss": 0.005621806252747774,
|
| 1571 |
+
"eval_runtime": 53.2584,
|
| 1572 |
+
"eval_samples_per_second": 563.292,
|
| 1573 |
+
"eval_steps_per_second": 35.206,
|
| 1574 |
+
"step": 68000
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.3397222765499706,
|
| 1578 |
+
"grad_norm": 0.0500396266579628,
|
| 1579 |
+
"learning_rate": 0.0002450077777777778,
|
| 1580 |
+
"loss": 0.0075,
|
| 1581 |
+
"step": 68500
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.3495012712693135,
|
| 1585 |
+
"grad_norm": 0.026338981464505196,
|
| 1586 |
+
"learning_rate": 0.0002411188888888889,
|
| 1587 |
+
"loss": 0.0071,
|
| 1588 |
+
"step": 69000
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 1.3495012712693135,
|
| 1592 |
+
"eval_accuracy": 0.9991572857142857,
|
| 1593 |
+
"eval_loss": 0.005518677178770304,
|
| 1594 |
+
"eval_runtime": 53.0868,
|
| 1595 |
+
"eval_samples_per_second": 565.112,
|
| 1596 |
+
"eval_steps_per_second": 35.32,
|
| 1597 |
+
"step": 69000
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.3592802659886565,
|
| 1601 |
+
"grad_norm": 0.05141606554389,
|
| 1602 |
+
"learning_rate": 0.00023722999999999998,
|
| 1603 |
+
"loss": 0.0072,
|
| 1604 |
+
"step": 69500
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 1.3690592607079992,
|
| 1608 |
+
"grad_norm": 0.03224059194326401,
|
| 1609 |
+
"learning_rate": 0.00023334111111111112,
|
| 1610 |
+
"loss": 0.0074,
|
| 1611 |
+
"step": 70000
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.3690592607079992,
|
| 1615 |
+
"eval_accuracy": 0.9991697142857143,
|
| 1616 |
+
"eval_loss": 0.005556654650717974,
|
| 1617 |
+
"eval_runtime": 54.212,
|
| 1618 |
+
"eval_samples_per_second": 553.383,
|
| 1619 |
+
"eval_steps_per_second": 34.586,
|
| 1620 |
+
"step": 70000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.378838255427342,
|
| 1624 |
+
"grad_norm": 0.045589789748191833,
|
| 1625 |
+
"learning_rate": 0.00022945222222222223,
|
| 1626 |
+
"loss": 0.0068,
|
| 1627 |
+
"step": 70500
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.388617250146685,
|
| 1631 |
+
"grad_norm": 0.03591601923108101,
|
| 1632 |
+
"learning_rate": 0.00022556333333333332,
|
| 1633 |
+
"loss": 0.0074,
|
| 1634 |
+
"step": 71000
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.388617250146685,
|
| 1638 |
+
"eval_accuracy": 0.9991771904761905,
|
| 1639 |
+
"eval_loss": 0.005408597644418478,
|
| 1640 |
+
"eval_runtime": 53.882,
|
| 1641 |
+
"eval_samples_per_second": 556.772,
|
| 1642 |
+
"eval_steps_per_second": 34.798,
|
| 1643 |
+
"step": 71000
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.3983962448660279,
|
| 1647 |
+
"grad_norm": 0.035366661846637726,
|
| 1648 |
+
"learning_rate": 0.00022167444444444446,
|
| 1649 |
+
"loss": 0.0071,
|
| 1650 |
+
"step": 71500
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.4081752395853706,
|
| 1654 |
+
"grad_norm": 0.035964544862508774,
|
| 1655 |
+
"learning_rate": 0.00021778555555555557,
|
| 1656 |
+
"loss": 0.007,
|
| 1657 |
+
"step": 72000
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.4081752395853706,
|
| 1661 |
+
"eval_accuracy": 0.9991820476190476,
|
| 1662 |
+
"eval_loss": 0.005390489008277655,
|
| 1663 |
+
"eval_runtime": 53.9869,
|
| 1664 |
+
"eval_samples_per_second": 555.69,
|
| 1665 |
+
"eval_steps_per_second": 34.731,
|
| 1666 |
+
"step": 72000
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.4179542343047133,
|
| 1670 |
+
"grad_norm": 0.046406473964452744,
|
| 1671 |
+
"learning_rate": 0.00021389666666666665,
|
| 1672 |
+
"loss": 0.0069,
|
| 1673 |
+
"step": 72500
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.4277332290240563,
|
| 1677 |
+
"grad_norm": 0.01739337481558323,
|
| 1678 |
+
"learning_rate": 0.00021000777777777777,
|
| 1679 |
+
"loss": 0.0071,
|
| 1680 |
+
"step": 73000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.4277332290240563,
|
| 1684 |
+
"eval_accuracy": 0.999192238095238,
|
| 1685 |
+
"eval_loss": 0.005439835134893656,
|
| 1686 |
+
"eval_runtime": 52.5582,
|
| 1687 |
+
"eval_samples_per_second": 570.796,
|
| 1688 |
+
"eval_steps_per_second": 35.675,
|
| 1689 |
+
"step": 73000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.4375122237433993,
|
| 1693 |
+
"grad_norm": 0.054208699613809586,
|
| 1694 |
+
"learning_rate": 0.0002061188888888889,
|
| 1695 |
+
"loss": 0.0068,
|
| 1696 |
+
"step": 73500
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.447291218462742,
|
| 1700 |
+
"grad_norm": 0.015219291672110558,
|
| 1701 |
+
"learning_rate": 0.00020223,
|
| 1702 |
+
"loss": 0.0065,
|
| 1703 |
+
"step": 74000
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.447291218462742,
|
| 1707 |
+
"eval_accuracy": 0.9992209523809524,
|
| 1708 |
+
"eval_loss": 0.005157183855772018,
|
| 1709 |
+
"eval_runtime": 54.119,
|
| 1710 |
+
"eval_samples_per_second": 554.333,
|
| 1711 |
+
"eval_steps_per_second": 34.646,
|
| 1712 |
+
"step": 74000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.457070213182085,
|
| 1716 |
+
"grad_norm": 0.029242349788546562,
|
| 1717 |
+
"learning_rate": 0.0001983411111111111,
|
| 1718 |
+
"loss": 0.0068,
|
| 1719 |
+
"step": 74500
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.4668492079014277,
|
| 1723 |
+
"grad_norm": 0.07763868570327759,
|
| 1724 |
+
"learning_rate": 0.0001944522222222222,
|
| 1725 |
+
"loss": 0.0066,
|
| 1726 |
+
"step": 75000
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.4668492079014277,
|
| 1730 |
+
"eval_accuracy": 0.9992142380952381,
|
| 1731 |
+
"eval_loss": 0.005214931443333626,
|
| 1732 |
+
"eval_runtime": 53.5783,
|
| 1733 |
+
"eval_samples_per_second": 559.928,
|
| 1734 |
+
"eval_steps_per_second": 34.996,
|
| 1735 |
+
"step": 75000
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 1.4766282026207707,
|
| 1739 |
+
"grad_norm": 0.02636542171239853,
|
| 1740 |
+
"learning_rate": 0.00019056333333333333,
|
| 1741 |
+
"loss": 0.0068,
|
| 1742 |
+
"step": 75500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 1.4864071973401134,
|
| 1746 |
+
"grad_norm": 0.04074472188949585,
|
| 1747 |
+
"learning_rate": 0.00018667444444444445,
|
| 1748 |
+
"loss": 0.0066,
|
| 1749 |
+
"step": 76000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 1.4864071973401134,
|
| 1753 |
+
"eval_accuracy": 0.999215238095238,
|
| 1754 |
+
"eval_loss": 0.005246439483016729,
|
| 1755 |
+
"eval_runtime": 53.1001,
|
| 1756 |
+
"eval_samples_per_second": 564.97,
|
| 1757 |
+
"eval_steps_per_second": 35.311,
|
| 1758 |
+
"step": 76000
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 1.4961861920594564,
|
| 1762 |
+
"grad_norm": 0.044967830181121826,
|
| 1763 |
+
"learning_rate": 0.00018278555555555553,
|
| 1764 |
+
"loss": 0.0066,
|
| 1765 |
+
"step": 76500
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.505965186778799,
|
| 1769 |
+
"grad_norm": 0.05165797472000122,
|
| 1770 |
+
"learning_rate": 0.00017889666666666667,
|
| 1771 |
+
"loss": 0.0069,
|
| 1772 |
+
"step": 77000
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 1.505965186778799,
|
| 1776 |
+
"eval_accuracy": 0.9992458095238095,
|
| 1777 |
+
"eval_loss": 0.005047474056482315,
|
| 1778 |
+
"eval_runtime": 52.941,
|
| 1779 |
+
"eval_samples_per_second": 566.668,
|
| 1780 |
+
"eval_steps_per_second": 35.417,
|
| 1781 |
+
"step": 77000
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.515744181498142,
|
| 1785 |
+
"grad_norm": 0.03628181293606758,
|
| 1786 |
+
"learning_rate": 0.00017500777777777778,
|
| 1787 |
+
"loss": 0.0064,
|
| 1788 |
+
"step": 77500
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.5255231762174848,
|
| 1792 |
+
"grad_norm": 0.06254853308200836,
|
| 1793 |
+
"learning_rate": 0.0001711188888888889,
|
| 1794 |
+
"loss": 0.0062,
|
| 1795 |
+
"step": 78000
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.5255231762174848,
|
| 1799 |
+
"eval_accuracy": 0.9992468571428571,
|
| 1800 |
+
"eval_loss": 0.0050251539796590805,
|
| 1801 |
+
"eval_runtime": 53.5481,
|
| 1802 |
+
"eval_samples_per_second": 560.243,
|
| 1803 |
+
"eval_steps_per_second": 35.015,
|
| 1804 |
+
"step": 78000
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.5353021709368277,
|
| 1808 |
+
"grad_norm": 0.032451432198286057,
|
| 1809 |
+
"learning_rate": 0.00016723,
|
| 1810 |
+
"loss": 0.0068,
|
| 1811 |
+
"step": 78500
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.5450811656561707,
|
| 1815 |
+
"grad_norm": 0.04868290200829506,
|
| 1816 |
+
"learning_rate": 0.0001633411111111111,
|
| 1817 |
+
"loss": 0.0064,
|
| 1818 |
+
"step": 79000
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.5450811656561707,
|
| 1822 |
+
"eval_accuracy": 0.9992534761904762,
|
| 1823 |
+
"eval_loss": 0.004957298748195171,
|
| 1824 |
+
"eval_runtime": 53.2869,
|
| 1825 |
+
"eval_samples_per_second": 562.99,
|
| 1826 |
+
"eval_steps_per_second": 35.187,
|
| 1827 |
+
"step": 79000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.5548601603755134,
|
| 1831 |
+
"grad_norm": 0.036670561879873276,
|
| 1832 |
+
"learning_rate": 0.00015945222222222224,
|
| 1833 |
+
"loss": 0.0064,
|
| 1834 |
+
"step": 79500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.5646391550948562,
|
| 1838 |
+
"grad_norm": 0.10247086733579636,
|
| 1839 |
+
"learning_rate": 0.00015556333333333332,
|
| 1840 |
+
"loss": 0.0065,
|
| 1841 |
+
"step": 80000
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.5646391550948562,
|
| 1845 |
+
"eval_accuracy": 0.9992579047619048,
|
| 1846 |
+
"eval_loss": 0.004946143366396427,
|
| 1847 |
+
"eval_runtime": 53.7183,
|
| 1848 |
+
"eval_samples_per_second": 558.469,
|
| 1849 |
+
"eval_steps_per_second": 34.904,
|
| 1850 |
+
"step": 80000
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.5744181498141991,
|
| 1854 |
+
"grad_norm": 0.04580460116267204,
|
| 1855 |
+
"learning_rate": 0.00015167444444444443,
|
| 1856 |
+
"loss": 0.0064,
|
| 1857 |
+
"step": 80500
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.584197144533542,
|
| 1861 |
+
"grad_norm": 0.03229832649230957,
|
| 1862 |
+
"learning_rate": 0.00014778555555555555,
|
| 1863 |
+
"loss": 0.0067,
|
| 1864 |
+
"step": 81000
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.584197144533542,
|
| 1868 |
+
"eval_accuracy": 0.9992667142857142,
|
| 1869 |
+
"eval_loss": 0.004820096306502819,
|
| 1870 |
+
"eval_runtime": 53.0003,
|
| 1871 |
+
"eval_samples_per_second": 566.035,
|
| 1872 |
+
"eval_steps_per_second": 35.377,
|
| 1873 |
+
"step": 81000
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 1.5939761392528848,
|
| 1877 |
+
"grad_norm": 0.050680823624134064,
|
| 1878 |
+
"learning_rate": 0.00014389666666666666,
|
| 1879 |
+
"loss": 0.0066,
|
| 1880 |
+
"step": 81500
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.6037551339722276,
|
| 1884 |
+
"grad_norm": 0.025311388075351715,
|
| 1885 |
+
"learning_rate": 0.00014000777777777777,
|
| 1886 |
+
"loss": 0.0062,
|
| 1887 |
+
"step": 82000
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 1.6037551339722276,
|
| 1891 |
+
"eval_accuracy": 0.9992829523809523,
|
| 1892 |
+
"eval_loss": 0.004771844483911991,
|
| 1893 |
+
"eval_runtime": 53.4237,
|
| 1894 |
+
"eval_samples_per_second": 561.548,
|
| 1895 |
+
"eval_steps_per_second": 35.097,
|
| 1896 |
+
"step": 82000
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 1.6135341286915705,
|
| 1900 |
+
"grad_norm": 0.05920279771089554,
|
| 1901 |
+
"learning_rate": 0.0001361188888888889,
|
| 1902 |
+
"loss": 0.0058,
|
| 1903 |
+
"step": 82500
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 1.6233131234109135,
|
| 1907 |
+
"grad_norm": 0.01131299789994955,
|
| 1908 |
+
"learning_rate": 0.00013223,
|
| 1909 |
+
"loss": 0.0062,
|
| 1910 |
+
"step": 83000
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 1.6233131234109135,
|
| 1914 |
+
"eval_accuracy": 0.9992792857142857,
|
| 1915 |
+
"eval_loss": 0.0047705951146781445,
|
| 1916 |
+
"eval_runtime": 52.9714,
|
| 1917 |
+
"eval_samples_per_second": 566.343,
|
| 1918 |
+
"eval_steps_per_second": 35.396,
|
| 1919 |
+
"step": 83000
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.6330921181302562,
|
| 1923 |
+
"grad_norm": 0.023239562287926674,
|
| 1924 |
+
"learning_rate": 0.0001283411111111111,
|
| 1925 |
+
"loss": 0.006,
|
| 1926 |
+
"step": 83500
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 1.642871112849599,
|
| 1930 |
+
"grad_norm": 0.02065044827759266,
|
| 1931 |
+
"learning_rate": 0.00012445222222222223,
|
| 1932 |
+
"loss": 0.0066,
|
| 1933 |
+
"step": 84000
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.642871112849599,
|
| 1937 |
+
"eval_accuracy": 0.999290380952381,
|
| 1938 |
+
"eval_loss": 0.00470797810703516,
|
| 1939 |
+
"eval_runtime": 53.326,
|
| 1940 |
+
"eval_samples_per_second": 562.578,
|
| 1941 |
+
"eval_steps_per_second": 35.161,
|
| 1942 |
+
"step": 84000
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.652650107568942,
|
| 1946 |
+
"grad_norm": 0.0221023578196764,
|
| 1947 |
+
"learning_rate": 0.00012056333333333332,
|
| 1948 |
+
"loss": 0.0058,
|
| 1949 |
+
"step": 84500
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.6624291022882849,
|
| 1953 |
+
"grad_norm": 0.06653928756713867,
|
| 1954 |
+
"learning_rate": 0.00011667444444444445,
|
| 1955 |
+
"loss": 0.0062,
|
| 1956 |
+
"step": 85000
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.6624291022882849,
|
| 1960 |
+
"eval_accuracy": 0.9992950952380952,
|
| 1961 |
+
"eval_loss": 0.004687351640313864,
|
| 1962 |
+
"eval_runtime": 53.5876,
|
| 1963 |
+
"eval_samples_per_second": 559.831,
|
| 1964 |
+
"eval_steps_per_second": 34.989,
|
| 1965 |
+
"step": 85000
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 1.6722080970076276,
|
| 1969 |
+
"grad_norm": 0.019194116815924644,
|
| 1970 |
+
"learning_rate": 0.00011278555555555555,
|
| 1971 |
+
"loss": 0.0062,
|
| 1972 |
+
"step": 85500
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 1.6819870917269704,
|
| 1976 |
+
"grad_norm": 0.03486155346035957,
|
| 1977 |
+
"learning_rate": 0.00010889666666666666,
|
| 1978 |
+
"loss": 0.0062,
|
| 1979 |
+
"step": 86000
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 1.6819870917269704,
|
| 1983 |
+
"eval_accuracy": 0.9993017142857142,
|
| 1984 |
+
"eval_loss": 0.004641150124371052,
|
| 1985 |
+
"eval_runtime": 54.2961,
|
| 1986 |
+
"eval_samples_per_second": 552.526,
|
| 1987 |
+
"eval_steps_per_second": 34.533,
|
| 1988 |
+
"step": 86000
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.6917660864463133,
|
| 1992 |
+
"grad_norm": 0.029760519042611122,
|
| 1993 |
+
"learning_rate": 0.00010500777777777779,
|
| 1994 |
+
"loss": 0.0061,
|
| 1995 |
+
"step": 86500
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.7015450811656563,
|
| 1999 |
+
"grad_norm": 0.05030335485935211,
|
| 2000 |
+
"learning_rate": 0.00010111888888888889,
|
| 2001 |
+
"loss": 0.0061,
|
| 2002 |
+
"step": 87000
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.7015450811656563,
|
| 2006 |
+
"eval_accuracy": 0.9993119523809524,
|
| 2007 |
+
"eval_loss": 0.004569541197270155,
|
| 2008 |
+
"eval_runtime": 53.3694,
|
| 2009 |
+
"eval_samples_per_second": 562.12,
|
| 2010 |
+
"eval_steps_per_second": 35.132,
|
| 2011 |
+
"step": 87000
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.711324075884999,
|
| 2015 |
+
"grad_norm": 0.022894462570548058,
|
| 2016 |
+
"learning_rate": 9.723e-05,
|
| 2017 |
+
"loss": 0.0059,
|
| 2018 |
+
"step": 87500
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.7211030706043418,
|
| 2022 |
+
"grad_norm": 0.07328710705041885,
|
| 2023 |
+
"learning_rate": 9.33411111111111e-05,
|
| 2024 |
+
"loss": 0.0059,
|
| 2025 |
+
"step": 88000
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.7211030706043418,
|
| 2029 |
+
"eval_accuracy": 0.999316380952381,
|
| 2030 |
+
"eval_loss": 0.004550817422568798,
|
| 2031 |
+
"eval_runtime": 53.4807,
|
| 2032 |
+
"eval_samples_per_second": 560.95,
|
| 2033 |
+
"eval_steps_per_second": 35.059,
|
| 2034 |
+
"step": 88000
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.7308820653236847,
|
| 2038 |
+
"grad_norm": 0.04035668075084686,
|
| 2039 |
+
"learning_rate": 8.945222222222223e-05,
|
| 2040 |
+
"loss": 0.0059,
|
| 2041 |
+
"step": 88500
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 1.7406610600430277,
|
| 2045 |
+
"grad_norm": 0.060258008539676666,
|
| 2046 |
+
"learning_rate": 8.556333333333333e-05,
|
| 2047 |
+
"loss": 0.0058,
|
| 2048 |
+
"step": 89000
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 1.7406610600430277,
|
| 2052 |
+
"eval_accuracy": 0.9993239047619048,
|
| 2053 |
+
"eval_loss": 0.004507962614297867,
|
| 2054 |
+
"eval_runtime": 53.3734,
|
| 2055 |
+
"eval_samples_per_second": 562.078,
|
| 2056 |
+
"eval_steps_per_second": 35.13,
|
| 2057 |
+
"step": 89000
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 1.7504400547623704,
|
| 2061 |
+
"grad_norm": 0.04366343468427658,
|
| 2062 |
+
"learning_rate": 8.167444444444444e-05,
|
| 2063 |
+
"loss": 0.0057,
|
| 2064 |
+
"step": 89500
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 1.7602190494817131,
|
| 2068 |
+
"grad_norm": 0.016024254262447357,
|
| 2069 |
+
"learning_rate": 7.778555555555555e-05,
|
| 2070 |
+
"loss": 0.0056,
|
| 2071 |
+
"step": 90000
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 1.7602190494817131,
|
| 2075 |
+
"eval_accuracy": 0.9993265238095238,
|
| 2076 |
+
"eval_loss": 0.004456896800547838,
|
| 2077 |
+
"eval_runtime": 53.0281,
|
| 2078 |
+
"eval_samples_per_second": 565.737,
|
| 2079 |
+
"eval_steps_per_second": 35.359,
|
| 2080 |
+
"step": 90000
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.769998044201056,
|
| 2084 |
+
"grad_norm": 0.04971948266029358,
|
| 2085 |
+
"learning_rate": 7.389666666666667e-05,
|
| 2086 |
+
"loss": 0.0059,
|
| 2087 |
+
"step": 90500
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.779777038920399,
|
| 2091 |
+
"grad_norm": 0.0350346602499485,
|
| 2092 |
+
"learning_rate": 7.000777777777778e-05,
|
| 2093 |
+
"loss": 0.006,
|
| 2094 |
+
"step": 91000
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.779777038920399,
|
| 2098 |
+
"eval_accuracy": 0.9993302857142857,
|
| 2099 |
+
"eval_loss": 0.004403200466185808,
|
| 2100 |
+
"eval_runtime": 53.133,
|
| 2101 |
+
"eval_samples_per_second": 564.62,
|
| 2102 |
+
"eval_steps_per_second": 35.289,
|
| 2103 |
+
"step": 91000
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.7895560336397418,
|
| 2107 |
+
"grad_norm": 0.016598312184214592,
|
| 2108 |
+
"learning_rate": 6.611888888888889e-05,
|
| 2109 |
+
"loss": 0.0058,
|
| 2110 |
+
"step": 91500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.7993350283590845,
|
| 2114 |
+
"grad_norm": 0.033121079206466675,
|
| 2115 |
+
"learning_rate": 6.223e-05,
|
| 2116 |
+
"loss": 0.0058,
|
| 2117 |
+
"step": 92000
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.7993350283590845,
|
| 2121 |
+
"eval_accuracy": 0.9993409047619047,
|
| 2122 |
+
"eval_loss": 0.004376650787889957,
|
| 2123 |
+
"eval_runtime": 54.4045,
|
| 2124 |
+
"eval_samples_per_second": 551.425,
|
| 2125 |
+
"eval_steps_per_second": 34.464,
|
| 2126 |
+
"step": 92000
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 1.8091140230784275,
|
| 2130 |
+
"grad_norm": 0.03453979268670082,
|
| 2131 |
+
"learning_rate": 5.834111111111111e-05,
|
| 2132 |
+
"loss": 0.006,
|
| 2133 |
+
"step": 92500
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 1.8188930177977705,
|
| 2137 |
+
"grad_norm": 0.026620876044034958,
|
| 2138 |
+
"learning_rate": 5.4452222222222225e-05,
|
| 2139 |
+
"loss": 0.0057,
|
| 2140 |
+
"step": 93000
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 1.8188930177977705,
|
| 2144 |
+
"eval_accuracy": 0.9993440476190476,
|
| 2145 |
+
"eval_loss": 0.004335285164415836,
|
| 2146 |
+
"eval_runtime": 52.8243,
|
| 2147 |
+
"eval_samples_per_second": 567.921,
|
| 2148 |
+
"eval_steps_per_second": 35.495,
|
| 2149 |
+
"step": 93000
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 1.8286720125171132,
|
| 2153 |
+
"grad_norm": 0.048424337059259415,
|
| 2154 |
+
"learning_rate": 5.056333333333333e-05,
|
| 2155 |
+
"loss": 0.0056,
|
| 2156 |
+
"step": 93500
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 1.838451007236456,
|
| 2160 |
+
"grad_norm": 0.010132824070751667,
|
| 2161 |
+
"learning_rate": 4.6674444444444444e-05,
|
| 2162 |
+
"loss": 0.0055,
|
| 2163 |
+
"step": 94000
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 1.838451007236456,
|
| 2167 |
+
"eval_accuracy": 0.9993485714285715,
|
| 2168 |
+
"eval_loss": 0.004318695981055498,
|
| 2169 |
+
"eval_runtime": 54.1043,
|
| 2170 |
+
"eval_samples_per_second": 554.485,
|
| 2171 |
+
"eval_steps_per_second": 34.655,
|
| 2172 |
+
"step": 94000
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.848230001955799,
|
| 2176 |
+
"grad_norm": 0.02636049874126911,
|
| 2177 |
+
"learning_rate": 4.278555555555556e-05,
|
| 2178 |
+
"loss": 0.0057,
|
| 2179 |
+
"step": 94500
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.8580089966751419,
|
| 2183 |
+
"grad_norm": 0.05795420706272125,
|
| 2184 |
+
"learning_rate": 3.889666666666667e-05,
|
| 2185 |
+
"loss": 0.0053,
|
| 2186 |
+
"step": 95000
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.8580089966751419,
|
| 2190 |
+
"eval_accuracy": 0.9993522857142857,
|
| 2191 |
+
"eval_loss": 0.004322956781834364,
|
| 2192 |
+
"eval_runtime": 53.1807,
|
| 2193 |
+
"eval_samples_per_second": 564.114,
|
| 2194 |
+
"eval_steps_per_second": 35.257,
|
| 2195 |
+
"step": 95000
|
| 2196 |
+
},
|
| 2197 |
+
{
|
| 2198 |
+
"epoch": 1.8677879913944846,
|
| 2199 |
+
"grad_norm": 0.03254598006606102,
|
| 2200 |
+
"learning_rate": 3.5007777777777776e-05,
|
| 2201 |
+
"loss": 0.0057,
|
| 2202 |
+
"step": 95500
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.8775669861138276,
|
| 2206 |
+
"grad_norm": 0.0263524129986763,
|
| 2207 |
+
"learning_rate": 3.111888888888889e-05,
|
| 2208 |
+
"loss": 0.0053,
|
| 2209 |
+
"step": 96000
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 1.8775669861138276,
|
| 2213 |
+
"eval_accuracy": 0.9993573333333333,
|
| 2214 |
+
"eval_loss": 0.004285932518541813,
|
| 2215 |
+
"eval_runtime": 54.0246,
|
| 2216 |
+
"eval_samples_per_second": 555.303,
|
| 2217 |
+
"eval_steps_per_second": 34.706,
|
| 2218 |
+
"step": 96000
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 1.8873459808331705,
|
| 2222 |
+
"grad_norm": 0.03505020588636398,
|
| 2223 |
+
"learning_rate": 2.723e-05,
|
| 2224 |
+
"loss": 0.0054,
|
| 2225 |
+
"step": 96500
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 1.8971249755525132,
|
| 2229 |
+
"grad_norm": 0.03808409720659256,
|
| 2230 |
+
"learning_rate": 2.334111111111111e-05,
|
| 2231 |
+
"loss": 0.0056,
|
| 2232 |
+
"step": 97000
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 1.8971249755525132,
|
| 2236 |
+
"eval_accuracy": 0.9993604761904762,
|
| 2237 |
+
"eval_loss": 0.004236984066665173,
|
| 2238 |
+
"eval_runtime": 52.6503,
|
| 2239 |
+
"eval_samples_per_second": 569.798,
|
| 2240 |
+
"eval_steps_per_second": 35.612,
|
| 2241 |
+
"step": 97000
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 1.906903970271856,
|
| 2245 |
+
"grad_norm": 0.10009113699197769,
|
| 2246 |
+
"learning_rate": 1.945222222222222e-05,
|
| 2247 |
+
"loss": 0.0053,
|
| 2248 |
+
"step": 97500
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 1.916682964991199,
|
| 2252 |
+
"grad_norm": 0.020276788622140884,
|
| 2253 |
+
"learning_rate": 1.5563333333333334e-05,
|
| 2254 |
+
"loss": 0.0054,
|
| 2255 |
+
"step": 98000
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 1.916682964991199,
|
| 2259 |
+
"eval_accuracy": 0.999362619047619,
|
| 2260 |
+
"eval_loss": 0.004235610365867615,
|
| 2261 |
+
"eval_runtime": 53.2133,
|
| 2262 |
+
"eval_samples_per_second": 563.769,
|
| 2263 |
+
"eval_steps_per_second": 35.236,
|
| 2264 |
+
"step": 98000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.926461959710542,
|
| 2268 |
+
"grad_norm": 0.02707495540380478,
|
| 2269 |
+
"learning_rate": 1.1674444444444444e-05,
|
| 2270 |
+
"loss": 0.0056,
|
| 2271 |
+
"step": 98500
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.9362409544298846,
|
| 2275 |
+
"grad_norm": 0.07092906534671783,
|
| 2276 |
+
"learning_rate": 7.785555555555556e-06,
|
| 2277 |
+
"loss": 0.0054,
|
| 2278 |
+
"step": 99000
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.9362409544298846,
|
| 2282 |
+
"eval_accuracy": 0.9993623333333334,
|
| 2283 |
+
"eval_loss": 0.00422343285754323,
|
| 2284 |
+
"eval_runtime": 53.1912,
|
| 2285 |
+
"eval_samples_per_second": 564.003,
|
| 2286 |
+
"eval_steps_per_second": 35.25,
|
| 2287 |
+
"step": 99000
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 1.9460199491492274,
|
| 2291 |
+
"grad_norm": 0.04465750977396965,
|
| 2292 |
+
"learning_rate": 3.896666666666667e-06,
|
| 2293 |
+
"loss": 0.0054,
|
| 2294 |
+
"step": 99500
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 1.9557989438685703,
|
| 2298 |
+
"grad_norm": 0.041641559451818466,
|
| 2299 |
+
"learning_rate": 7.777777777777778e-09,
|
| 2300 |
+
"loss": 0.0056,
|
| 2301 |
+
"step": 100000
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 1.9557989438685703,
|
| 2305 |
+
"eval_accuracy": 0.9993655714285714,
|
| 2306 |
+
"eval_loss": 0.0042214160785079,
|
| 2307 |
+
"eval_runtime": 52.9182,
|
| 2308 |
+
"eval_samples_per_second": 566.912,
|
| 2309 |
+
"eval_steps_per_second": 35.432,
|
| 2310 |
+
"step": 100000
|
| 2311 |
+
}
|
| 2312 |
+
],
|
| 2313 |
+
"logging_steps": 500,
|
| 2314 |
+
"max_steps": 100000,
|
| 2315 |
+
"num_input_tokens_seen": 0,
|
| 2316 |
+
"num_train_epochs": 2,
|
| 2317 |
+
"save_steps": 1000,
|
| 2318 |
+
"stateful_callbacks": {
|
| 2319 |
+
"EarlyStoppingCallback": {
|
| 2320 |
+
"args": {
|
| 2321 |
+
"early_stopping_patience": 7,
|
| 2322 |
+
"early_stopping_threshold": 0.0
|
| 2323 |
+
},
|
| 2324 |
+
"attributes": {
|
| 2325 |
+
"early_stopping_patience_counter": 0
|
| 2326 |
+
}
|
| 2327 |
+
},
|
| 2328 |
+
"TrainerControl": {
|
| 2329 |
+
"args": {
|
| 2330 |
+
"should_epoch_stop": false,
|
| 2331 |
+
"should_evaluate": false,
|
| 2332 |
+
"should_log": false,
|
| 2333 |
+
"should_save": true,
|
| 2334 |
+
"should_training_stop": true
|
| 2335 |
+
},
|
| 2336 |
+
"attributes": {}
|
| 2337 |
+
}
|
| 2338 |
+
},
|
| 2339 |
+
"total_flos": 7.4014585085952e+16,
|
| 2340 |
+
"train_batch_size": 8,
|
| 2341 |
+
"trial_name": null,
|
| 2342 |
+
"trial_params": null
|
| 2343 |
+
}
|