Upload 10 files
Browse files- config.json +10 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +212 -0
- trainer_state.json +919 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"d_model": 768,
|
| 3 |
+
"n_layer": 24,
|
| 4 |
+
"vocab_size": 50277,
|
| 5 |
+
"ssm_cfg": {},
|
| 6 |
+
"rms_norm": true,
|
| 7 |
+
"residual_in_fp32": true,
|
| 8 |
+
"fused_add_norm": true,
|
| 9 |
+
"pad_vocab_size_multiple": 8
|
| 10 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e79e4ad7df87eabd355a87d71a0d0b57adb1227019f848664dacceda6a4da1a
|
| 3 |
+
size 1033228154
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dc598418b9b1817d8ad183134037da3b6c777a8b5b7d5643fe1ec9ed258753f
|
| 3 |
+
size 259616210
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8341b7ef9b206ab7313fb1cdd7712848cd3501a267b84cafd58b0c2ada5c6cfa
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|padding|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"50254": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50255": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50256": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50257": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50258": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50259": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50260": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50261": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50262": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50263": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50264": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50265": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50266": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50267": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50268": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50269": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50270": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50271": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50272": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50273": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50274": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50275": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50276": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
}
|
| 204 |
+
},
|
| 205 |
+
"bos_token": "<|endoftext|>",
|
| 206 |
+
"clean_up_tokenization_spaces": true,
|
| 207 |
+
"eos_token": "<|endoftext|>",
|
| 208 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 209 |
+
"pad_token": "<|endoftext|>",
|
| 210 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 211 |
+
"unk_token": "<|endoftext|>"
|
| 212 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,919 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9907100199071002,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 75000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0004966821499668214,
|
| 14 |
+
"loss": 1.4142,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 0.000493364299933643,
|
| 20 |
+
"loss": 1.4047,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 0.0004900464499004645,
|
| 26 |
+
"loss": 1.4055,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 0.000486728599867286,
|
| 32 |
+
"loss": 1.405,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.07,
|
| 37 |
+
"learning_rate": 0.0004834107498341075,
|
| 38 |
+
"loss": 1.4066,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.08,
|
| 43 |
+
"learning_rate": 0.000480092899800929,
|
| 44 |
+
"loss": 1.392,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 0.0004767750497677505,
|
| 50 |
+
"loss": 1.3947,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11,
|
| 55 |
+
"learning_rate": 0.000473457199734572,
|
| 56 |
+
"loss": 1.3762,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.12,
|
| 61 |
+
"learning_rate": 0.0004701393497013935,
|
| 62 |
+
"loss": 1.3958,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.13,
|
| 67 |
+
"learning_rate": 0.00046682149966821503,
|
| 68 |
+
"loss": 1.3809,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.15,
|
| 73 |
+
"learning_rate": 0.0004635036496350365,
|
| 74 |
+
"loss": 1.3802,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.16,
|
| 79 |
+
"learning_rate": 0.00046018579960185803,
|
| 80 |
+
"loss": 1.3939,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.17,
|
| 85 |
+
"learning_rate": 0.0004568679495686795,
|
| 86 |
+
"loss": 1.3897,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19,
|
| 91 |
+
"learning_rate": 0.00045355009953550104,
|
| 92 |
+
"loss": 1.3919,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2,
|
| 97 |
+
"learning_rate": 0.0004502322495023225,
|
| 98 |
+
"loss": 1.3809,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.21,
|
| 103 |
+
"learning_rate": 0.00044691439946914404,
|
| 104 |
+
"loss": 1.3892,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.23,
|
| 109 |
+
"learning_rate": 0.0004435965494359655,
|
| 110 |
+
"loss": 1.3906,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.24,
|
| 115 |
+
"learning_rate": 0.00044027869940278704,
|
| 116 |
+
"loss": 1.3814,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.25,
|
| 121 |
+
"learning_rate": 0.0004369608493696085,
|
| 122 |
+
"loss": 1.3844,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.27,
|
| 127 |
+
"learning_rate": 0.00043364299933643,
|
| 128 |
+
"loss": 1.3937,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.28,
|
| 133 |
+
"learning_rate": 0.0004303251493032515,
|
| 134 |
+
"loss": 1.3816,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.29,
|
| 139 |
+
"learning_rate": 0.000427007299270073,
|
| 140 |
+
"loss": 1.3878,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.31,
|
| 145 |
+
"learning_rate": 0.0004236894492368945,
|
| 146 |
+
"loss": 1.3933,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.32,
|
| 151 |
+
"learning_rate": 0.000420371599203716,
|
| 152 |
+
"loss": 1.3822,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.33,
|
| 157 |
+
"learning_rate": 0.00041705374917053753,
|
| 158 |
+
"loss": 1.3863,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.35,
|
| 163 |
+
"learning_rate": 0.000413735899137359,
|
| 164 |
+
"loss": 1.4047,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.36,
|
| 169 |
+
"learning_rate": 0.00041041804910418053,
|
| 170 |
+
"loss": 1.3921,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.37,
|
| 175 |
+
"learning_rate": 0.000407100199071002,
|
| 176 |
+
"loss": 1.3822,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.38,
|
| 181 |
+
"learning_rate": 0.00040378234903782354,
|
| 182 |
+
"loss": 1.3941,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.4,
|
| 187 |
+
"learning_rate": 0.000400464499004645,
|
| 188 |
+
"loss": 1.3849,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.41,
|
| 193 |
+
"learning_rate": 0.00039714664897146654,
|
| 194 |
+
"loss": 1.3709,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.42,
|
| 199 |
+
"learning_rate": 0.000393828798938288,
|
| 200 |
+
"loss": 1.3679,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.44,
|
| 205 |
+
"learning_rate": 0.00039051094890510954,
|
| 206 |
+
"loss": 1.3756,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.45,
|
| 211 |
+
"learning_rate": 0.000387193098871931,
|
| 212 |
+
"loss": 1.397,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.46,
|
| 217 |
+
"learning_rate": 0.00038387524883875255,
|
| 218 |
+
"loss": 1.4014,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.48,
|
| 223 |
+
"learning_rate": 0.00038055739880557397,
|
| 224 |
+
"loss": 1.3892,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.49,
|
| 229 |
+
"learning_rate": 0.00037723954877239544,
|
| 230 |
+
"loss": 1.4107,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.5,
|
| 235 |
+
"learning_rate": 0.00037392169873921697,
|
| 236 |
+
"loss": 1.4083,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.52,
|
| 241 |
+
"learning_rate": 0.00037060384870603845,
|
| 242 |
+
"loss": 1.3963,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.53,
|
| 247 |
+
"learning_rate": 0.00036728599867286,
|
| 248 |
+
"loss": 1.3899,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.54,
|
| 253 |
+
"learning_rate": 0.00036396814863968145,
|
| 254 |
+
"loss": 1.3972,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.56,
|
| 259 |
+
"learning_rate": 0.000360650298606503,
|
| 260 |
+
"loss": 1.3851,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.57,
|
| 265 |
+
"learning_rate": 0.00035733244857332445,
|
| 266 |
+
"loss": 1.3899,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.58,
|
| 271 |
+
"learning_rate": 0.000354014598540146,
|
| 272 |
+
"loss": 1.3788,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.6,
|
| 277 |
+
"learning_rate": 0.00035069674850696746,
|
| 278 |
+
"loss": 1.3806,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.61,
|
| 283 |
+
"learning_rate": 0.000347378898473789,
|
| 284 |
+
"loss": 1.3829,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.62,
|
| 289 |
+
"learning_rate": 0.00034406104844061046,
|
| 290 |
+
"loss": 1.3742,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.64,
|
| 295 |
+
"learning_rate": 0.000340743198407432,
|
| 296 |
+
"loss": 1.381,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.65,
|
| 301 |
+
"learning_rate": 0.00033742534837425347,
|
| 302 |
+
"loss": 1.3711,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.66,
|
| 307 |
+
"learning_rate": 0.000334107498341075,
|
| 308 |
+
"loss": 1.3752,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.68,
|
| 313 |
+
"learning_rate": 0.00033078964830789647,
|
| 314 |
+
"loss": 1.3776,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.69,
|
| 319 |
+
"learning_rate": 0.000327471798274718,
|
| 320 |
+
"loss": 1.3775,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.7,
|
| 325 |
+
"learning_rate": 0.00032415394824153947,
|
| 326 |
+
"loss": 1.3608,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.72,
|
| 331 |
+
"learning_rate": 0.000320836098208361,
|
| 332 |
+
"loss": 1.3636,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.73,
|
| 337 |
+
"learning_rate": 0.0003175182481751825,
|
| 338 |
+
"loss": 1.3684,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.74,
|
| 343 |
+
"learning_rate": 0.00031420039814200395,
|
| 344 |
+
"loss": 1.3777,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.76,
|
| 349 |
+
"learning_rate": 0.0003108825481088255,
|
| 350 |
+
"loss": 1.3497,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.77,
|
| 355 |
+
"learning_rate": 0.00030756469807564695,
|
| 356 |
+
"loss": 1.3621,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.78,
|
| 361 |
+
"learning_rate": 0.0003042468480424685,
|
| 362 |
+
"loss": 1.3717,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.8,
|
| 367 |
+
"learning_rate": 0.00030092899800928996,
|
| 368 |
+
"loss": 1.3637,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.81,
|
| 373 |
+
"learning_rate": 0.0002976111479761115,
|
| 374 |
+
"loss": 1.3502,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.82,
|
| 379 |
+
"learning_rate": 0.00029429329794293296,
|
| 380 |
+
"loss": 1.3559,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.84,
|
| 385 |
+
"learning_rate": 0.0002909754479097545,
|
| 386 |
+
"loss": 1.3595,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.85,
|
| 391 |
+
"learning_rate": 0.00028765759787657597,
|
| 392 |
+
"loss": 1.3525,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.86,
|
| 397 |
+
"learning_rate": 0.0002843397478433975,
|
| 398 |
+
"loss": 1.3633,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.88,
|
| 403 |
+
"learning_rate": 0.00028102189781021897,
|
| 404 |
+
"loss": 1.3645,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.89,
|
| 409 |
+
"learning_rate": 0.0002777040477770405,
|
| 410 |
+
"loss": 1.3665,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.9,
|
| 415 |
+
"learning_rate": 0.000274386197743862,
|
| 416 |
+
"loss": 1.367,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.92,
|
| 421 |
+
"learning_rate": 0.0002710683477106835,
|
| 422 |
+
"loss": 1.3482,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.93,
|
| 427 |
+
"learning_rate": 0.000267750497677505,
|
| 428 |
+
"loss": 1.3663,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.94,
|
| 433 |
+
"learning_rate": 0.0002644326476443265,
|
| 434 |
+
"loss": 1.3555,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.96,
|
| 439 |
+
"learning_rate": 0.000261114797611148,
|
| 440 |
+
"loss": 1.3623,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.97,
|
| 445 |
+
"learning_rate": 0.00025779694757796946,
|
| 446 |
+
"loss": 1.3656,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.98,
|
| 451 |
+
"learning_rate": 0.000254479097544791,
|
| 452 |
+
"loss": 1.3651,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.0,
|
| 457 |
+
"learning_rate": 0.00025116124751161246,
|
| 458 |
+
"loss": 1.3712,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.01,
|
| 463 |
+
"learning_rate": 0.000247843397478434,
|
| 464 |
+
"loss": 1.3459,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.02,
|
| 469 |
+
"learning_rate": 0.00024452554744525546,
|
| 470 |
+
"loss": 1.3334,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.04,
|
| 475 |
+
"learning_rate": 0.000241207697412077,
|
| 476 |
+
"loss": 1.3231,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.05,
|
| 481 |
+
"learning_rate": 0.0002378898473788985,
|
| 482 |
+
"loss": 1.3191,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.06,
|
| 487 |
+
"learning_rate": 0.00023457199734572,
|
| 488 |
+
"loss": 1.3232,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.07,
|
| 493 |
+
"learning_rate": 0.0002312541473125415,
|
| 494 |
+
"loss": 1.3239,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.09,
|
| 499 |
+
"learning_rate": 0.00022793629727936297,
|
| 500 |
+
"loss": 1.3194,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.1,
|
| 505 |
+
"learning_rate": 0.00022461844724618447,
|
| 506 |
+
"loss": 1.3074,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.11,
|
| 511 |
+
"learning_rate": 0.00022130059721300598,
|
| 512 |
+
"loss": 1.3191,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.13,
|
| 517 |
+
"learning_rate": 0.00021798274717982748,
|
| 518 |
+
"loss": 1.3092,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.14,
|
| 523 |
+
"learning_rate": 0.00021466489714664898,
|
| 524 |
+
"loss": 1.3141,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.15,
|
| 529 |
+
"learning_rate": 0.00021134704711347048,
|
| 530 |
+
"loss": 1.3247,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.17,
|
| 535 |
+
"learning_rate": 0.00020802919708029198,
|
| 536 |
+
"loss": 1.3163,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.18,
|
| 541 |
+
"learning_rate": 0.00020471134704711349,
|
| 542 |
+
"loss": 1.3124,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.19,
|
| 547 |
+
"learning_rate": 0.00020139349701393496,
|
| 548 |
+
"loss": 1.3151,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.21,
|
| 553 |
+
"learning_rate": 0.00019807564698075646,
|
| 554 |
+
"loss": 1.3062,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.22,
|
| 559 |
+
"learning_rate": 0.00019475779694757796,
|
| 560 |
+
"loss": 1.3237,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.23,
|
| 565 |
+
"learning_rate": 0.00019143994691439947,
|
| 566 |
+
"loss": 1.3143,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.25,
|
| 571 |
+
"learning_rate": 0.00018812209688122097,
|
| 572 |
+
"loss": 1.3007,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.26,
|
| 577 |
+
"learning_rate": 0.00018480424684804247,
|
| 578 |
+
"loss": 1.3142,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.27,
|
| 583 |
+
"learning_rate": 0.00018148639681486397,
|
| 584 |
+
"loss": 1.3144,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.29,
|
| 589 |
+
"learning_rate": 0.00017816854678168547,
|
| 590 |
+
"loss": 1.3175,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3,
|
| 595 |
+
"learning_rate": 0.00017485069674850697,
|
| 596 |
+
"loss": 1.3011,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.31,
|
| 601 |
+
"learning_rate": 0.00017153284671532848,
|
| 602 |
+
"loss": 1.3161,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.33,
|
| 607 |
+
"learning_rate": 0.00016821499668214995,
|
| 608 |
+
"loss": 1.295,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.34,
|
| 613 |
+
"learning_rate": 0.00016489714664897145,
|
| 614 |
+
"loss": 1.3161,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.35,
|
| 619 |
+
"learning_rate": 0.00016157929661579295,
|
| 620 |
+
"loss": 1.3122,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.37,
|
| 625 |
+
"learning_rate": 0.00015826144658261446,
|
| 626 |
+
"loss": 1.304,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.38,
|
| 631 |
+
"learning_rate": 0.00015494359654943596,
|
| 632 |
+
"loss": 1.3086,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.39,
|
| 637 |
+
"learning_rate": 0.00015162574651625746,
|
| 638 |
+
"loss": 1.2964,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.41,
|
| 643 |
+
"learning_rate": 0.00014830789648307896,
|
| 644 |
+
"loss": 1.3073,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.42,
|
| 649 |
+
"learning_rate": 0.00014499004644990046,
|
| 650 |
+
"loss": 1.2976,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.43,
|
| 655 |
+
"learning_rate": 0.00014167219641672197,
|
| 656 |
+
"loss": 1.2988,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.45,
|
| 661 |
+
"learning_rate": 0.00013835434638354347,
|
| 662 |
+
"loss": 1.3038,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.46,
|
| 667 |
+
"learning_rate": 0.00013503649635036497,
|
| 668 |
+
"loss": 1.3085,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.47,
|
| 673 |
+
"learning_rate": 0.00013171864631718647,
|
| 674 |
+
"loss": 1.2942,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.49,
|
| 679 |
+
"learning_rate": 0.00012840079628400797,
|
| 680 |
+
"loss": 1.298,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5,
|
| 685 |
+
"learning_rate": 0.00012508294625082948,
|
| 686 |
+
"loss": 1.3083,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.51,
|
| 691 |
+
"learning_rate": 0.00012176509621765096,
|
| 692 |
+
"loss": 1.3074,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.53,
|
| 697 |
+
"learning_rate": 0.00011844724618447247,
|
| 698 |
+
"loss": 1.2952,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.54,
|
| 703 |
+
"learning_rate": 0.00011512939615129397,
|
| 704 |
+
"loss": 1.2934,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.55,
|
| 709 |
+
"learning_rate": 0.00011181154611811546,
|
| 710 |
+
"loss": 1.2949,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.57,
|
| 715 |
+
"learning_rate": 0.00010849369608493696,
|
| 716 |
+
"loss": 1.2845,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.58,
|
| 721 |
+
"learning_rate": 0.00010517584605175846,
|
| 722 |
+
"loss": 1.2978,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.59,
|
| 727 |
+
"learning_rate": 0.00010185799601857996,
|
| 728 |
+
"loss": 1.279,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.61,
|
| 733 |
+
"learning_rate": 9.854014598540146e-05,
|
| 734 |
+
"loss": 1.2962,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.62,
|
| 739 |
+
"learning_rate": 9.522229595222296e-05,
|
| 740 |
+
"loss": 1.3042,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.63,
|
| 745 |
+
"learning_rate": 9.190444591904445e-05,
|
| 746 |
+
"loss": 1.2836,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.65,
|
| 751 |
+
"learning_rate": 8.858659588586595e-05,
|
| 752 |
+
"loss": 1.3003,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.66,
|
| 757 |
+
"learning_rate": 8.526874585268746e-05,
|
| 758 |
+
"loss": 1.2998,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.67,
|
| 763 |
+
"learning_rate": 8.195089581950896e-05,
|
| 764 |
+
"loss": 1.2924,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.69,
|
| 769 |
+
"learning_rate": 7.863304578633046e-05,
|
| 770 |
+
"loss": 1.2915,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.7,
|
| 775 |
+
"learning_rate": 7.531519575315196e-05,
|
| 776 |
+
"loss": 1.2986,
|
| 777 |
+
"step": 64000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.71,
|
| 781 |
+
"learning_rate": 7.199734571997346e-05,
|
| 782 |
+
"loss": 1.3072,
|
| 783 |
+
"step": 64500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.73,
|
| 787 |
+
"learning_rate": 6.867949568679497e-05,
|
| 788 |
+
"loss": 1.2975,
|
| 789 |
+
"step": 65000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.74,
|
| 793 |
+
"learning_rate": 6.536164565361647e-05,
|
| 794 |
+
"loss": 1.2987,
|
| 795 |
+
"step": 65500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.75,
|
| 799 |
+
"learning_rate": 6.204379562043796e-05,
|
| 800 |
+
"loss": 1.2907,
|
| 801 |
+
"step": 66000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.77,
|
| 805 |
+
"learning_rate": 5.872594558725946e-05,
|
| 806 |
+
"loss": 1.2932,
|
| 807 |
+
"step": 66500
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.78,
|
| 811 |
+
"learning_rate": 5.540809555408095e-05,
|
| 812 |
+
"loss": 1.2993,
|
| 813 |
+
"step": 67000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.79,
|
| 817 |
+
"learning_rate": 5.2090245520902455e-05,
|
| 818 |
+
"loss": 1.2919,
|
| 819 |
+
"step": 67500
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.8,
|
| 823 |
+
"learning_rate": 4.877239548772396e-05,
|
| 824 |
+
"loss": 1.2915,
|
| 825 |
+
"step": 68000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.82,
|
| 829 |
+
"learning_rate": 4.545454545454546e-05,
|
| 830 |
+
"loss": 1.2974,
|
| 831 |
+
"step": 68500
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.83,
|
| 835 |
+
"learning_rate": 4.213669542136696e-05,
|
| 836 |
+
"loss": 1.2813,
|
| 837 |
+
"step": 69000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.84,
|
| 841 |
+
"learning_rate": 3.881884538818845e-05,
|
| 842 |
+
"loss": 1.2866,
|
| 843 |
+
"step": 69500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.86,
|
| 847 |
+
"learning_rate": 3.550099535500995e-05,
|
| 848 |
+
"loss": 1.2861,
|
| 849 |
+
"step": 70000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.87,
|
| 853 |
+
"learning_rate": 3.218314532183145e-05,
|
| 854 |
+
"loss": 1.2921,
|
| 855 |
+
"step": 70500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.88,
|
| 859 |
+
"learning_rate": 2.886529528865295e-05,
|
| 860 |
+
"loss": 1.2973,
|
| 861 |
+
"step": 71000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.9,
|
| 865 |
+
"learning_rate": 2.5547445255474453e-05,
|
| 866 |
+
"loss": 1.2901,
|
| 867 |
+
"step": 71500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.91,
|
| 871 |
+
"learning_rate": 2.2229595222295955e-05,
|
| 872 |
+
"loss": 1.291,
|
| 873 |
+
"step": 72000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.92,
|
| 877 |
+
"learning_rate": 1.8911745189117453e-05,
|
| 878 |
+
"loss": 1.2768,
|
| 879 |
+
"step": 72500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.94,
|
| 883 |
+
"learning_rate": 1.559389515593895e-05,
|
| 884 |
+
"loss": 1.2867,
|
| 885 |
+
"step": 73000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.95,
|
| 889 |
+
"learning_rate": 1.227604512276045e-05,
|
| 890 |
+
"loss": 1.292,
|
| 891 |
+
"step": 73500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.96,
|
| 895 |
+
"learning_rate": 8.958195089581952e-06,
|
| 896 |
+
"loss": 1.2956,
|
| 897 |
+
"step": 74000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.98,
|
| 901 |
+
"learning_rate": 5.64034505640345e-06,
|
| 902 |
+
"loss": 1.294,
|
| 903 |
+
"step": 74500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.99,
|
| 907 |
+
"learning_rate": 2.32249502322495e-06,
|
| 908 |
+
"loss": 1.2918,
|
| 909 |
+
"step": 75000
|
| 910 |
+
}
|
| 911 |
+
],
|
| 912 |
+
"logging_steps": 500,
|
| 913 |
+
"max_steps": 75350,
|
| 914 |
+
"num_train_epochs": 2,
|
| 915 |
+
"save_steps": 5000,
|
| 916 |
+
"total_flos": 0.0,
|
| 917 |
+
"trial_name": null,
|
| 918 |
+
"trial_params": null
|
| 919 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b63bcdd5df5508bcb62be1748470851a8c61d2406d543cb03e841aa00d2e295
|
| 3 |
+
size 4600
|