Upload folder using huggingface_hub
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +213 -0
- trainer_state.json +739 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8ac38f03a2975fafddd990926eb0f03a52e198d43a3bbede3e0615e7fdb82d3
|
| 3 |
+
size 5549215498
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36fba6f535f20784de312a6f8a340bc5bb682088c8fb4fab034d109a670777e4
|
| 3 |
+
size 5548078554
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e3d0159ff77beb01c4ff4de7952de2dcf44098563321b346959d3d2bd4b444
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29f4c8358d02f79823020edc640d6598dbc039e31414008cc1f0104226ceb676
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 207 |
+
"clean_up_tokenization_spaces": true,
|
| 208 |
+
"eos_token": "<|endoftext|>",
|
| 209 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 210 |
+
"pad_token": "<|endoftext|>",
|
| 211 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 212 |
+
"unk_token": "<|endoftext|>"
|
| 213 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9976693857166639,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 4.9583749583749586e-05,
|
| 14 |
+
"loss": 0.7997,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 4.916749916749917e-05,
|
| 20 |
+
"loss": 0.5713,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 4.8751248751248754e-05,
|
| 26 |
+
"loss": 0.5638,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 4.833499833499834e-05,
|
| 32 |
+
"loss": 0.5656,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"learning_rate": 4.791874791874792e-05,
|
| 38 |
+
"loss": 0.5687,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1,
|
| 43 |
+
"learning_rate": 4.7502497502497505e-05,
|
| 44 |
+
"loss": 0.59,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"learning_rate": 4.708624708624709e-05,
|
| 50 |
+
"loss": 0.5713,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13,
|
| 55 |
+
"learning_rate": 4.666999666999667e-05,
|
| 56 |
+
"loss": 0.5466,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.15,
|
| 61 |
+
"learning_rate": 4.6253746253746256e-05,
|
| 62 |
+
"loss": 0.5835,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.17,
|
| 67 |
+
"learning_rate": 4.583749583749584e-05,
|
| 68 |
+
"loss": 0.5822,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.18,
|
| 73 |
+
"learning_rate": 4.5421245421245424e-05,
|
| 74 |
+
"loss": 0.5591,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.2,
|
| 79 |
+
"learning_rate": 4.500499500499501e-05,
|
| 80 |
+
"loss": 0.5804,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.22,
|
| 85 |
+
"learning_rate": 4.458874458874459e-05,
|
| 86 |
+
"loss": 0.579,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.23,
|
| 91 |
+
"learning_rate": 4.4172494172494175e-05,
|
| 92 |
+
"loss": 0.5462,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.25,
|
| 97 |
+
"learning_rate": 4.375624375624376e-05,
|
| 98 |
+
"loss": 0.5822,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.27,
|
| 103 |
+
"learning_rate": 4.333999333999334e-05,
|
| 104 |
+
"loss": 0.5678,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.28,
|
| 109 |
+
"learning_rate": 4.2923742923742926e-05,
|
| 110 |
+
"loss": 0.5657,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.3,
|
| 115 |
+
"learning_rate": 4.250749250749251e-05,
|
| 116 |
+
"loss": 0.578,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.32,
|
| 121 |
+
"learning_rate": 4.2091242091242094e-05,
|
| 122 |
+
"loss": 0.5688,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.33,
|
| 127 |
+
"learning_rate": 4.167499167499168e-05,
|
| 128 |
+
"loss": 0.5389,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.35,
|
| 133 |
+
"learning_rate": 4.125874125874126e-05,
|
| 134 |
+
"loss": 0.5079,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.37,
|
| 139 |
+
"learning_rate": 4.0842490842490845e-05,
|
| 140 |
+
"loss": 0.5762,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.38,
|
| 145 |
+
"learning_rate": 4.042624042624043e-05,
|
| 146 |
+
"loss": 0.5532,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.4,
|
| 151 |
+
"learning_rate": 4.000999000999001e-05,
|
| 152 |
+
"loss": 0.5315,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.42,
|
| 157 |
+
"learning_rate": 3.9593739593739596e-05,
|
| 158 |
+
"loss": 0.5308,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.43,
|
| 163 |
+
"learning_rate": 3.917748917748918e-05,
|
| 164 |
+
"loss": 0.5444,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.45,
|
| 169 |
+
"learning_rate": 3.8761238761238764e-05,
|
| 170 |
+
"loss": 0.533,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.47,
|
| 175 |
+
"learning_rate": 3.834498834498835e-05,
|
| 176 |
+
"loss": 0.5504,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.48,
|
| 181 |
+
"learning_rate": 3.792873792873793e-05,
|
| 182 |
+
"loss": 0.5248,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.5,
|
| 187 |
+
"learning_rate": 3.7512487512487515e-05,
|
| 188 |
+
"loss": 0.5588,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.52,
|
| 193 |
+
"learning_rate": 3.70962370962371e-05,
|
| 194 |
+
"loss": 0.5198,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.53,
|
| 199 |
+
"learning_rate": 3.667998667998668e-05,
|
| 200 |
+
"loss": 0.5509,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.55,
|
| 205 |
+
"learning_rate": 3.6263736263736266e-05,
|
| 206 |
+
"loss": 0.5105,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.57,
|
| 211 |
+
"learning_rate": 3.584748584748585e-05,
|
| 212 |
+
"loss": 0.5441,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.58,
|
| 217 |
+
"learning_rate": 3.5431235431235434e-05,
|
| 218 |
+
"loss": 0.5263,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6,
|
| 223 |
+
"learning_rate": 3.501498501498502e-05,
|
| 224 |
+
"loss": 0.5168,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.62,
|
| 229 |
+
"learning_rate": 3.45987345987346e-05,
|
| 230 |
+
"loss": 0.5312,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.63,
|
| 235 |
+
"learning_rate": 3.4182484182484185e-05,
|
| 236 |
+
"loss": 0.5447,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.65,
|
| 241 |
+
"learning_rate": 3.376623376623377e-05,
|
| 242 |
+
"loss": 0.5103,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.67,
|
| 247 |
+
"learning_rate": 3.334998334998335e-05,
|
| 248 |
+
"loss": 0.5377,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.68,
|
| 253 |
+
"learning_rate": 3.2933732933732936e-05,
|
| 254 |
+
"loss": 0.5388,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.7,
|
| 259 |
+
"learning_rate": 3.251748251748252e-05,
|
| 260 |
+
"loss": 0.5226,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.72,
|
| 265 |
+
"learning_rate": 3.2101232101232104e-05,
|
| 266 |
+
"loss": 0.536,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.73,
|
| 271 |
+
"learning_rate": 3.168498168498169e-05,
|
| 272 |
+
"loss": 0.551,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.75,
|
| 277 |
+
"learning_rate": 3.126873126873127e-05,
|
| 278 |
+
"loss": 0.5245,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.77,
|
| 283 |
+
"learning_rate": 3.0852480852480855e-05,
|
| 284 |
+
"loss": 0.5272,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.78,
|
| 289 |
+
"learning_rate": 3.043623043623044e-05,
|
| 290 |
+
"loss": 0.529,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.8,
|
| 295 |
+
"learning_rate": 3.0019980019980022e-05,
|
| 296 |
+
"loss": 0.5391,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.82,
|
| 301 |
+
"learning_rate": 2.9603729603729606e-05,
|
| 302 |
+
"loss": 0.5241,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.83,
|
| 307 |
+
"learning_rate": 2.918747918747919e-05,
|
| 308 |
+
"loss": 0.4842,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.85,
|
| 313 |
+
"learning_rate": 2.8771228771228777e-05,
|
| 314 |
+
"loss": 0.5078,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.87,
|
| 319 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 320 |
+
"loss": 0.5291,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.88,
|
| 325 |
+
"learning_rate": 2.7938727938727938e-05,
|
| 326 |
+
"loss": 0.5165,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.9,
|
| 331 |
+
"learning_rate": 2.7522477522477525e-05,
|
| 332 |
+
"loss": 0.5039,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.92,
|
| 337 |
+
"learning_rate": 2.7106227106227105e-05,
|
| 338 |
+
"loss": 0.5038,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.93,
|
| 343 |
+
"learning_rate": 2.6689976689976692e-05,
|
| 344 |
+
"loss": 0.5282,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.95,
|
| 349 |
+
"learning_rate": 2.6273726273726273e-05,
|
| 350 |
+
"loss": 0.4997,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.97,
|
| 355 |
+
"learning_rate": 2.585747585747586e-05,
|
| 356 |
+
"loss": 0.5096,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.98,
|
| 361 |
+
"learning_rate": 2.544122544122544e-05,
|
| 362 |
+
"loss": 0.504,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.0,
|
| 367 |
+
"learning_rate": 2.5024975024975027e-05,
|
| 368 |
+
"loss": 0.4911,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.02,
|
| 373 |
+
"learning_rate": 2.4608724608724608e-05,
|
| 374 |
+
"loss": 0.3976,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.03,
|
| 379 |
+
"learning_rate": 2.4192474192474195e-05,
|
| 380 |
+
"loss": 0.3728,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.05,
|
| 385 |
+
"learning_rate": 2.377622377622378e-05,
|
| 386 |
+
"loss": 0.3908,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.07,
|
| 391 |
+
"learning_rate": 2.3359973359973362e-05,
|
| 392 |
+
"loss": 0.366,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.08,
|
| 397 |
+
"learning_rate": 2.2943722943722946e-05,
|
| 398 |
+
"loss": 0.3728,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.1,
|
| 403 |
+
"learning_rate": 2.252747252747253e-05,
|
| 404 |
+
"loss": 0.3972,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.12,
|
| 409 |
+
"learning_rate": 2.2111222111222114e-05,
|
| 410 |
+
"loss": 0.3567,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.13,
|
| 415 |
+
"learning_rate": 2.1694971694971697e-05,
|
| 416 |
+
"loss": 0.3751,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.15,
|
| 421 |
+
"learning_rate": 2.127872127872128e-05,
|
| 422 |
+
"loss": 0.3915,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.17,
|
| 427 |
+
"learning_rate": 2.0862470862470865e-05,
|
| 428 |
+
"loss": 0.3891,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.18,
|
| 433 |
+
"learning_rate": 2.0446220446220445e-05,
|
| 434 |
+
"loss": 0.3679,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.2,
|
| 439 |
+
"learning_rate": 2.002997002997003e-05,
|
| 440 |
+
"loss": 0.369,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.22,
|
| 445 |
+
"learning_rate": 1.9613719613719613e-05,
|
| 446 |
+
"loss": 0.3613,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.23,
|
| 451 |
+
"learning_rate": 1.9197469197469197e-05,
|
| 452 |
+
"loss": 0.3768,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.25,
|
| 457 |
+
"learning_rate": 1.878121878121878e-05,
|
| 458 |
+
"loss": 0.3695,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.27,
|
| 463 |
+
"learning_rate": 1.8364968364968367e-05,
|
| 464 |
+
"loss": 0.36,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.28,
|
| 469 |
+
"learning_rate": 1.794871794871795e-05,
|
| 470 |
+
"loss": 0.3642,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.3,
|
| 475 |
+
"learning_rate": 1.7532467532467535e-05,
|
| 476 |
+
"loss": 0.3726,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.32,
|
| 481 |
+
"learning_rate": 1.711621711621712e-05,
|
| 482 |
+
"loss": 0.3851,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.33,
|
| 487 |
+
"learning_rate": 1.6699966699966702e-05,
|
| 488 |
+
"loss": 0.3561,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.35,
|
| 493 |
+
"learning_rate": 1.6283716283716286e-05,
|
| 494 |
+
"loss": 0.3779,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.37,
|
| 499 |
+
"learning_rate": 1.586746586746587e-05,
|
| 500 |
+
"loss": 0.3684,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.38,
|
| 505 |
+
"learning_rate": 1.5451215451215454e-05,
|
| 506 |
+
"loss": 0.3671,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.4,
|
| 511 |
+
"learning_rate": 1.5034965034965034e-05,
|
| 512 |
+
"loss": 0.3754,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.42,
|
| 517 |
+
"learning_rate": 1.4618714618714618e-05,
|
| 518 |
+
"loss": 0.3694,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.43,
|
| 523 |
+
"learning_rate": 1.4202464202464203e-05,
|
| 524 |
+
"loss": 0.375,
|
| 525 |
+
"step": 4300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.45,
|
| 529 |
+
"learning_rate": 1.3786213786213787e-05,
|
| 530 |
+
"loss": 0.3926,
|
| 531 |
+
"step": 4350
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.46,
|
| 535 |
+
"learning_rate": 1.336996336996337e-05,
|
| 536 |
+
"loss": 0.3766,
|
| 537 |
+
"step": 4400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.48,
|
| 541 |
+
"learning_rate": 1.2953712953712954e-05,
|
| 542 |
+
"loss": 0.366,
|
| 543 |
+
"step": 4450
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.5,
|
| 547 |
+
"learning_rate": 1.2537462537462538e-05,
|
| 548 |
+
"loss": 0.3651,
|
| 549 |
+
"step": 4500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.51,
|
| 553 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 554 |
+
"loss": 0.3738,
|
| 555 |
+
"step": 4550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.53,
|
| 559 |
+
"learning_rate": 1.1704961704961706e-05,
|
| 560 |
+
"loss": 0.3833,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.55,
|
| 565 |
+
"learning_rate": 1.128871128871129e-05,
|
| 566 |
+
"loss": 0.3555,
|
| 567 |
+
"step": 4650
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.56,
|
| 571 |
+
"learning_rate": 1.0872460872460873e-05,
|
| 572 |
+
"loss": 0.3889,
|
| 573 |
+
"step": 4700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.58,
|
| 577 |
+
"learning_rate": 1.0456210456210457e-05,
|
| 578 |
+
"loss": 0.3683,
|
| 579 |
+
"step": 4750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.6,
|
| 583 |
+
"learning_rate": 1.003996003996004e-05,
|
| 584 |
+
"loss": 0.381,
|
| 585 |
+
"step": 4800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.61,
|
| 589 |
+
"learning_rate": 9.623709623709624e-06,
|
| 590 |
+
"loss": 0.3851,
|
| 591 |
+
"step": 4850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.63,
|
| 595 |
+
"learning_rate": 9.207459207459208e-06,
|
| 596 |
+
"loss": 0.3851,
|
| 597 |
+
"step": 4900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.65,
|
| 601 |
+
"learning_rate": 8.791208791208792e-06,
|
| 602 |
+
"loss": 0.3776,
|
| 603 |
+
"step": 4950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.66,
|
| 607 |
+
"learning_rate": 8.374958374958376e-06,
|
| 608 |
+
"loss": 0.3722,
|
| 609 |
+
"step": 5000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.68,
|
| 613 |
+
"learning_rate": 7.95870795870796e-06,
|
| 614 |
+
"loss": 0.3529,
|
| 615 |
+
"step": 5050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.7,
|
| 619 |
+
"learning_rate": 7.542457542457542e-06,
|
| 620 |
+
"loss": 0.3695,
|
| 621 |
+
"step": 5100
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.71,
|
| 625 |
+
"learning_rate": 7.126207126207127e-06,
|
| 626 |
+
"loss": 0.3768,
|
| 627 |
+
"step": 5150
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.73,
|
| 631 |
+
"learning_rate": 6.709956709956711e-06,
|
| 632 |
+
"loss": 0.3703,
|
| 633 |
+
"step": 5200
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.75,
|
| 637 |
+
"learning_rate": 6.2937062937062944e-06,
|
| 638 |
+
"loss": 0.386,
|
| 639 |
+
"step": 5250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.76,
|
| 643 |
+
"learning_rate": 5.877455877455878e-06,
|
| 644 |
+
"loss": 0.3754,
|
| 645 |
+
"step": 5300
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.78,
|
| 649 |
+
"learning_rate": 5.461205461205462e-06,
|
| 650 |
+
"loss": 0.3691,
|
| 651 |
+
"step": 5350
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.8,
|
| 655 |
+
"learning_rate": 5.044955044955045e-06,
|
| 656 |
+
"loss": 0.3684,
|
| 657 |
+
"step": 5400
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.81,
|
| 661 |
+
"learning_rate": 4.628704628704629e-06,
|
| 662 |
+
"loss": 0.3665,
|
| 663 |
+
"step": 5450
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.83,
|
| 667 |
+
"learning_rate": 4.212454212454213e-06,
|
| 668 |
+
"loss": 0.3646,
|
| 669 |
+
"step": 5500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.85,
|
| 673 |
+
"learning_rate": 3.796203796203796e-06,
|
| 674 |
+
"loss": 0.3644,
|
| 675 |
+
"step": 5550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.86,
|
| 679 |
+
"learning_rate": 3.3799533799533803e-06,
|
| 680 |
+
"loss": 0.377,
|
| 681 |
+
"step": 5600
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.88,
|
| 685 |
+
"learning_rate": 2.9637029637029636e-06,
|
| 686 |
+
"loss": 0.3781,
|
| 687 |
+
"step": 5650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.9,
|
| 691 |
+
"learning_rate": 2.5474525474525478e-06,
|
| 692 |
+
"loss": 0.3593,
|
| 693 |
+
"step": 5700
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.91,
|
| 697 |
+
"learning_rate": 2.131202131202131e-06,
|
| 698 |
+
"loss": 0.3967,
|
| 699 |
+
"step": 5750
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.93,
|
| 703 |
+
"learning_rate": 1.7149517149517148e-06,
|
| 704 |
+
"loss": 0.3754,
|
| 705 |
+
"step": 5800
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.95,
|
| 709 |
+
"learning_rate": 1.2987012987012988e-06,
|
| 710 |
+
"loss": 0.3419,
|
| 711 |
+
"step": 5850
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.96,
|
| 715 |
+
"learning_rate": 8.824508824508825e-07,
|
| 716 |
+
"loss": 0.352,
|
| 717 |
+
"step": 5900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.98,
|
| 721 |
+
"learning_rate": 4.662004662004662e-07,
|
| 722 |
+
"loss": 0.3515,
|
| 723 |
+
"step": 5950
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.0,
|
| 727 |
+
"learning_rate": 4.9950049950049954e-08,
|
| 728 |
+
"loss": 0.3678,
|
| 729 |
+
"step": 6000
|
| 730 |
+
}
|
| 731 |
+
],
|
| 732 |
+
"logging_steps": 50,
|
| 733 |
+
"max_steps": 6006,
|
| 734 |
+
"num_train_epochs": 2,
|
| 735 |
+
"save_steps": 500,
|
| 736 |
+
"total_flos": 0.0,
|
| 737 |
+
"trial_name": null,
|
| 738 |
+
"trial_params": null
|
| 739 |
+
}
|