Upload folder using huggingface_hub
Browse files- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +212 -0
- trainer_state.json +761 -0
- training_args.bin +3 -0
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:151e238b1050a7ef0d0da3c36e3851a7f46b07f446691a0f3a18b7d515c62366
|
| 3 |
+
size 714062243
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ccf48dc42084ffe18c52ae49d2179afd087b4f3bab2c0e270a42273f69a8ce2
|
| 3 |
+
size 1465
|
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 +1,761 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.357279084551812,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"grad_norm": 1.6613423824310303,
|
| 14 |
+
"learning_rate": 6.361323155216286e-07,
|
| 15 |
+
"loss": 2.3639,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13,
|
| 20 |
+
"grad_norm": 1.3924915790557861,
|
| 21 |
+
"learning_rate": 1.2722646310432571e-06,
|
| 22 |
+
"loss": 2.3559,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.19,
|
| 27 |
+
"grad_norm": 0.9411530494689941,
|
| 28 |
+
"learning_rate": 1.908396946564886e-06,
|
| 29 |
+
"loss": 2.3245,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.25,
|
| 34 |
+
"grad_norm": 0.7608889937400818,
|
| 35 |
+
"learning_rate": 2.5445292620865143e-06,
|
| 36 |
+
"loss": 2.2691,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.32,
|
| 41 |
+
"grad_norm": 0.8099371790885925,
|
| 42 |
+
"learning_rate": 3.1806615776081427e-06,
|
| 43 |
+
"loss": 2.2409,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.38,
|
| 48 |
+
"grad_norm": 0.6795283555984497,
|
| 49 |
+
"learning_rate": 3.816793893129772e-06,
|
| 50 |
+
"loss": 2.2435,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.45,
|
| 55 |
+
"grad_norm": 0.6041733622550964,
|
| 56 |
+
"learning_rate": 4.4529262086514e-06,
|
| 57 |
+
"loss": 2.2375,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.51,
|
| 62 |
+
"grad_norm": 0.644061803817749,
|
| 63 |
+
"learning_rate": 5.0890585241730285e-06,
|
| 64 |
+
"loss": 2.2012,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.57,
|
| 69 |
+
"grad_norm": 0.6609583497047424,
|
| 70 |
+
"learning_rate": 5.725190839694656e-06,
|
| 71 |
+
"loss": 2.213,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.64,
|
| 76 |
+
"grad_norm": 0.6314918994903564,
|
| 77 |
+
"learning_rate": 6.3613231552162854e-06,
|
| 78 |
+
"loss": 2.2088,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.7,
|
| 83 |
+
"grad_norm": 0.6217303276062012,
|
| 84 |
+
"learning_rate": 6.997455470737914e-06,
|
| 85 |
+
"loss": 2.1823,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.76,
|
| 90 |
+
"grad_norm": 0.624250054359436,
|
| 91 |
+
"learning_rate": 7.633587786259543e-06,
|
| 92 |
+
"loss": 2.1685,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.83,
|
| 97 |
+
"grad_norm": 0.692873477935791,
|
| 98 |
+
"learning_rate": 8.26972010178117e-06,
|
| 99 |
+
"loss": 2.166,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.89,
|
| 104 |
+
"grad_norm": 0.6286394000053406,
|
| 105 |
+
"learning_rate": 8.9058524173028e-06,
|
| 106 |
+
"loss": 2.1521,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.95,
|
| 111 |
+
"grad_norm": 0.6370307803153992,
|
| 112 |
+
"learning_rate": 9.54198473282443e-06,
|
| 113 |
+
"loss": 2.149,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.02,
|
| 118 |
+
"grad_norm": 0.614319384098053,
|
| 119 |
+
"learning_rate": 9.999903358354628e-06,
|
| 120 |
+
"loss": 2.1586,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.08,
|
| 125 |
+
"grad_norm": 0.6239405274391174,
|
| 126 |
+
"learning_rate": 9.997980516292023e-06,
|
| 127 |
+
"loss": 2.1352,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.14,
|
| 132 |
+
"grad_norm": 0.6648218631744385,
|
| 133 |
+
"learning_rate": 9.99359341519765e-06,
|
| 134 |
+
"loss": 2.1352,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.21,
|
| 139 |
+
"grad_norm": 0.6202364563941956,
|
| 140 |
+
"learning_rate": 9.986744218135864e-06,
|
| 141 |
+
"loss": 2.1187,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.27,
|
| 146 |
+
"grad_norm": 0.6447356939315796,
|
| 147 |
+
"learning_rate": 9.977436302109771e-06,
|
| 148 |
+
"loss": 2.1135,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.27,
|
| 153 |
+
"eval_loss": 1.9783179759979248,
|
| 154 |
+
"eval_runtime": 2.6728,
|
| 155 |
+
"eval_samples_per_second": 187.071,
|
| 156 |
+
"eval_steps_per_second": 23.571,
|
| 157 |
+
"step": 500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.34,
|
| 161 |
+
"grad_norm": 0.6953230500221252,
|
| 162 |
+
"learning_rate": 9.96567425639619e-06,
|
| 163 |
+
"loss": 2.1071,
|
| 164 |
+
"step": 525
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.4,
|
| 168 |
+
"grad_norm": 0.6353166103363037,
|
| 169 |
+
"learning_rate": 9.951463880282912e-06,
|
| 170 |
+
"loss": 2.109,
|
| 171 |
+
"step": 550
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.46,
|
| 175 |
+
"grad_norm": 0.5800075531005859,
|
| 176 |
+
"learning_rate": 9.93481218020935e-06,
|
| 177 |
+
"loss": 2.1165,
|
| 178 |
+
"step": 575
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.53,
|
| 182 |
+
"grad_norm": 0.6457290053367615,
|
| 183 |
+
"learning_rate": 9.915727366312012e-06,
|
| 184 |
+
"loss": 2.1009,
|
| 185 |
+
"step": 600
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.59,
|
| 189 |
+
"grad_norm": 0.5942001938819885,
|
| 190 |
+
"learning_rate": 9.894218848376482e-06,
|
| 191 |
+
"loss": 2.1133,
|
| 192 |
+
"step": 625
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.65,
|
| 196 |
+
"grad_norm": 0.6016191244125366,
|
| 197 |
+
"learning_rate": 9.870297231197922e-06,
|
| 198 |
+
"loss": 2.111,
|
| 199 |
+
"step": 650
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.72,
|
| 203 |
+
"grad_norm": 0.6793413758277893,
|
| 204 |
+
"learning_rate": 9.843974309352356e-06,
|
| 205 |
+
"loss": 2.0791,
|
| 206 |
+
"step": 675
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.78,
|
| 210 |
+
"grad_norm": 0.6286611557006836,
|
| 211 |
+
"learning_rate": 9.81526306138136e-06,
|
| 212 |
+
"loss": 2.1128,
|
| 213 |
+
"step": 700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.84,
|
| 217 |
+
"grad_norm": 0.6072127223014832,
|
| 218 |
+
"learning_rate": 9.784177643392958e-06,
|
| 219 |
+
"loss": 2.0818,
|
| 220 |
+
"step": 725
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.91,
|
| 224 |
+
"grad_norm": 0.581510066986084,
|
| 225 |
+
"learning_rate": 9.750733382081965e-06,
|
| 226 |
+
"loss": 2.0686,
|
| 227 |
+
"step": 750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.97,
|
| 231 |
+
"grad_norm": 0.607868492603302,
|
| 232 |
+
"learning_rate": 9.714946767173124e-06,
|
| 233 |
+
"loss": 2.0733,
|
| 234 |
+
"step": 775
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.03,
|
| 238 |
+
"grad_norm": 0.7183848023414612,
|
| 239 |
+
"learning_rate": 9.676835443290842e-06,
|
| 240 |
+
"loss": 2.0666,
|
| 241 |
+
"step": 800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.1,
|
| 245 |
+
"grad_norm": 0.6486113667488098,
|
| 246 |
+
"learning_rate": 9.63641820125949e-06,
|
| 247 |
+
"loss": 2.0623,
|
| 248 |
+
"step": 825
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.16,
|
| 252 |
+
"grad_norm": 0.6377106308937073,
|
| 253 |
+
"learning_rate": 9.593714968838568e-06,
|
| 254 |
+
"loss": 2.0564,
|
| 255 |
+
"step": 850
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.23,
|
| 259 |
+
"grad_norm": 0.5825337171554565,
|
| 260 |
+
"learning_rate": 9.548746800897305e-06,
|
| 261 |
+
"loss": 2.0636,
|
| 262 |
+
"step": 875
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.29,
|
| 266 |
+
"grad_norm": 0.6640869975090027,
|
| 267 |
+
"learning_rate": 9.501535869033537e-06,
|
| 268 |
+
"loss": 2.0637,
|
| 269 |
+
"step": 900
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.35,
|
| 273 |
+
"grad_norm": 0.604284405708313,
|
| 274 |
+
"learning_rate": 9.452105450641974e-06,
|
| 275 |
+
"loss": 2.063,
|
| 276 |
+
"step": 925
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.42,
|
| 280 |
+
"grad_norm": 0.6545228362083435,
|
| 281 |
+
"learning_rate": 9.400479917437267e-06,
|
| 282 |
+
"loss": 2.0379,
|
| 283 |
+
"step": 950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.48,
|
| 287 |
+
"grad_norm": 0.6467187404632568,
|
| 288 |
+
"learning_rate": 9.346684723437504e-06,
|
| 289 |
+
"loss": 2.0654,
|
| 290 |
+
"step": 975
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.54,
|
| 294 |
+
"grad_norm": 0.6103580594062805,
|
| 295 |
+
"learning_rate": 9.290746392414084e-06,
|
| 296 |
+
"loss": 2.0503,
|
| 297 |
+
"step": 1000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.54,
|
| 301 |
+
"eval_loss": 1.9211387634277344,
|
| 302 |
+
"eval_runtime": 2.6351,
|
| 303 |
+
"eval_samples_per_second": 189.749,
|
| 304 |
+
"eval_steps_per_second": 23.908,
|
| 305 |
+
"step": 1000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.61,
|
| 309 |
+
"grad_norm": 0.6254684329032898,
|
| 310 |
+
"learning_rate": 9.232692504814154e-06,
|
| 311 |
+
"loss": 2.0655,
|
| 312 |
+
"step": 1025
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.67,
|
| 316 |
+
"grad_norm": 0.6028435230255127,
|
| 317 |
+
"learning_rate": 9.172551684162025e-06,
|
| 318 |
+
"loss": 2.0678,
|
| 319 |
+
"step": 1050
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.73,
|
| 323 |
+
"grad_norm": 0.609348714351654,
|
| 324 |
+
"learning_rate": 9.110353582946341e-06,
|
| 325 |
+
"loss": 2.0406,
|
| 326 |
+
"step": 1075
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.8,
|
| 330 |
+
"grad_norm": 0.6535661816596985,
|
| 331 |
+
"learning_rate": 9.046128867999867e-06,
|
| 332 |
+
"loss": 2.072,
|
| 333 |
+
"step": 1100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.86,
|
| 337 |
+
"grad_norm": 0.6350586414337158,
|
| 338 |
+
"learning_rate": 8.979909205379198e-06,
|
| 339 |
+
"loss": 2.0436,
|
| 340 |
+
"step": 1125
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.92,
|
| 344 |
+
"grad_norm": 0.6003224849700928,
|
| 345 |
+
"learning_rate": 8.911727244751763e-06,
|
| 346 |
+
"loss": 2.0428,
|
| 347 |
+
"step": 1150
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.99,
|
| 351 |
+
"grad_norm": 0.6171026825904846,
|
| 352 |
+
"learning_rate": 8.84161660329789e-06,
|
| 353 |
+
"loss": 2.0466,
|
| 354 |
+
"step": 1175
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.05,
|
| 358 |
+
"grad_norm": 0.6239070892333984,
|
| 359 |
+
"learning_rate": 8.76961184913581e-06,
|
| 360 |
+
"loss": 2.0201,
|
| 361 |
+
"step": 1200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 3.12,
|
| 365 |
+
"grad_norm": 0.6221436858177185,
|
| 366 |
+
"learning_rate": 8.695748484277833e-06,
|
| 367 |
+
"loss": 2.0281,
|
| 368 |
+
"step": 1225
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.18,
|
| 372 |
+
"grad_norm": 0.6175958514213562,
|
| 373 |
+
"learning_rate": 8.620062927126021e-06,
|
| 374 |
+
"loss": 2.0472,
|
| 375 |
+
"step": 1250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.24,
|
| 379 |
+
"grad_norm": 0.6366366147994995,
|
| 380 |
+
"learning_rate": 8.54259249451608e-06,
|
| 381 |
+
"loss": 2.0326,
|
| 382 |
+
"step": 1275
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 3.31,
|
| 386 |
+
"grad_norm": 0.6660250425338745,
|
| 387 |
+
"learning_rate": 8.463375383318254e-06,
|
| 388 |
+
"loss": 2.0263,
|
| 389 |
+
"step": 1300
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.37,
|
| 393 |
+
"grad_norm": 0.5739914178848267,
|
| 394 |
+
"learning_rate": 8.382450651604316e-06,
|
| 395 |
+
"loss": 2.0265,
|
| 396 |
+
"step": 1325
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.43,
|
| 400 |
+
"grad_norm": 0.6790344715118408,
|
| 401 |
+
"learning_rate": 8.29985819938996e-06,
|
| 402 |
+
"loss": 2.0219,
|
| 403 |
+
"step": 1350
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.5,
|
| 407 |
+
"grad_norm": 0.6223481893539429,
|
| 408 |
+
"learning_rate": 8.215638748962047e-06,
|
| 409 |
+
"loss": 1.9994,
|
| 410 |
+
"step": 1375
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.56,
|
| 414 |
+
"grad_norm": 0.5811251997947693,
|
| 415 |
+
"learning_rate": 8.129833824800453e-06,
|
| 416 |
+
"loss": 2.0206,
|
| 417 |
+
"step": 1400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.62,
|
| 421 |
+
"grad_norm": 0.5943218469619751,
|
| 422 |
+
"learning_rate": 8.042485733104382e-06,
|
| 423 |
+
"loss": 2.0131,
|
| 424 |
+
"step": 1425
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.69,
|
| 428 |
+
"grad_norm": 0.595011293888092,
|
| 429 |
+
"learning_rate": 7.953637540933252e-06,
|
| 430 |
+
"loss": 2.0231,
|
| 431 |
+
"step": 1450
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.75,
|
| 435 |
+
"grad_norm": 0.7110486030578613,
|
| 436 |
+
"learning_rate": 7.863333054972443e-06,
|
| 437 |
+
"loss": 2.0297,
|
| 438 |
+
"step": 1475
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.81,
|
| 442 |
+
"grad_norm": 0.6503390073776245,
|
| 443 |
+
"learning_rate": 7.771616799934372e-06,
|
| 444 |
+
"loss": 2.0163,
|
| 445 |
+
"step": 1500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 3.81,
|
| 449 |
+
"eval_loss": 1.8906679153442383,
|
| 450 |
+
"eval_runtime": 2.6486,
|
| 451 |
+
"eval_samples_per_second": 188.781,
|
| 452 |
+
"eval_steps_per_second": 23.786,
|
| 453 |
+
"step": 1500
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.88,
|
| 457 |
+
"grad_norm": 0.6919596791267395,
|
| 458 |
+
"learning_rate": 7.67853399660553e-06,
|
| 459 |
+
"loss": 2.0236,
|
| 460 |
+
"step": 1525
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.94,
|
| 464 |
+
"grad_norm": 0.6393699645996094,
|
| 465 |
+
"learning_rate": 7.584130539550348e-06,
|
| 466 |
+
"loss": 2.0241,
|
| 467 |
+
"step": 1550
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.01,
|
| 471 |
+
"grad_norm": 0.6010494232177734,
|
| 472 |
+
"learning_rate": 7.488452974482818e-06,
|
| 473 |
+
"loss": 2.0123,
|
| 474 |
+
"step": 1575
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.07,
|
| 478 |
+
"grad_norm": 0.6905403733253479,
|
| 479 |
+
"learning_rate": 7.3915484753171055e-06,
|
| 480 |
+
"loss": 2.0073,
|
| 481 |
+
"step": 1600
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 4.13,
|
| 485 |
+
"grad_norm": 0.6041144728660583,
|
| 486 |
+
"learning_rate": 7.293464820908392e-06,
|
| 487 |
+
"loss": 2.0118,
|
| 488 |
+
"step": 1625
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.2,
|
| 492 |
+
"grad_norm": 0.6558405756950378,
|
| 493 |
+
"learning_rate": 7.194250371495467e-06,
|
| 494 |
+
"loss": 2.0059,
|
| 495 |
+
"step": 1650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.26,
|
| 499 |
+
"grad_norm": 0.6472019553184509,
|
| 500 |
+
"learning_rate": 7.093954044856674e-06,
|
| 501 |
+
"loss": 1.9895,
|
| 502 |
+
"step": 1675
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 4.32,
|
| 506 |
+
"grad_norm": 0.6358299255371094,
|
| 507 |
+
"learning_rate": 6.992625292190942e-06,
|
| 508 |
+
"loss": 1.9934,
|
| 509 |
+
"step": 1700
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.39,
|
| 513 |
+
"grad_norm": 0.828366219997406,
|
| 514 |
+
"learning_rate": 6.89031407373584e-06,
|
| 515 |
+
"loss": 2.0051,
|
| 516 |
+
"step": 1725
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.45,
|
| 520 |
+
"grad_norm": 0.5889772176742554,
|
| 521 |
+
"learning_rate": 6.787070834134618e-06,
|
| 522 |
+
"loss": 2.0057,
|
| 523 |
+
"step": 1750
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 4.51,
|
| 527 |
+
"grad_norm": 0.6443700790405273,
|
| 528 |
+
"learning_rate": 6.682946477564438e-06,
|
| 529 |
+
"loss": 1.9983,
|
| 530 |
+
"step": 1775
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.58,
|
| 534 |
+
"grad_norm": 0.6555039286613464,
|
| 535 |
+
"learning_rate": 6.57799234263802e-06,
|
| 536 |
+
"loss": 2.0049,
|
| 537 |
+
"step": 1800
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.64,
|
| 541 |
+
"grad_norm": 0.5760651230812073,
|
| 542 |
+
"learning_rate": 6.47226017709109e-06,
|
| 543 |
+
"loss": 1.9864,
|
| 544 |
+
"step": 1825
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.7,
|
| 548 |
+
"grad_norm": 0.6189552545547485,
|
| 549 |
+
"learning_rate": 6.365802112268104e-06,
|
| 550 |
+
"loss": 2.0114,
|
| 551 |
+
"step": 1850
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 4.77,
|
| 555 |
+
"grad_norm": 0.5847841501235962,
|
| 556 |
+
"learning_rate": 6.258670637418851e-06,
|
| 557 |
+
"loss": 1.9923,
|
| 558 |
+
"step": 1875
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 4.83,
|
| 562 |
+
"grad_norm": 0.5979297757148743,
|
| 563 |
+
"learning_rate": 6.150918573818569e-06,
|
| 564 |
+
"loss": 1.9992,
|
| 565 |
+
"step": 1900
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 4.9,
|
| 569 |
+
"grad_norm": 0.6612520813941956,
|
| 570 |
+
"learning_rate": 6.042599048724366e-06,
|
| 571 |
+
"loss": 2.0062,
|
| 572 |
+
"step": 1925
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.96,
|
| 576 |
+
"grad_norm": 0.6389756202697754,
|
| 577 |
+
"learning_rate": 5.933765469180779e-06,
|
| 578 |
+
"loss": 1.9897,
|
| 579 |
+
"step": 1950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 5.02,
|
| 583 |
+
"grad_norm": 0.5569688081741333,
|
| 584 |
+
"learning_rate": 5.82447149568738e-06,
|
| 585 |
+
"loss": 1.9913,
|
| 586 |
+
"step": 1975
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 5.09,
|
| 590 |
+
"grad_norm": 0.6268473267555237,
|
| 591 |
+
"learning_rate": 5.714771015741414e-06,
|
| 592 |
+
"loss": 1.9881,
|
| 593 |
+
"step": 2000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.09,
|
| 597 |
+
"eval_loss": 1.872865915298462,
|
| 598 |
+
"eval_runtime": 2.6614,
|
| 599 |
+
"eval_samples_per_second": 187.873,
|
| 600 |
+
"eval_steps_per_second": 23.672,
|
| 601 |
+
"step": 2000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 5.15,
|
| 605 |
+
"grad_norm": 0.6172594428062439,
|
| 606 |
+
"learning_rate": 5.604718117268515e-06,
|
| 607 |
+
"loss": 1.9858,
|
| 608 |
+
"step": 2025
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 5.21,
|
| 612 |
+
"grad_norm": 0.6328703165054321,
|
| 613 |
+
"learning_rate": 5.494367061954609e-06,
|
| 614 |
+
"loss": 1.9934,
|
| 615 |
+
"step": 2050
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 5.28,
|
| 619 |
+
"grad_norm": 0.6563747525215149,
|
| 620 |
+
"learning_rate": 5.383772258492135e-06,
|
| 621 |
+
"loss": 1.9751,
|
| 622 |
+
"step": 2075
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 5.34,
|
| 626 |
+
"grad_norm": 0.5623390078544617,
|
| 627 |
+
"learning_rate": 5.2729882357537864e-06,
|
| 628 |
+
"loss": 1.9911,
|
| 629 |
+
"step": 2100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 5.4,
|
| 633 |
+
"grad_norm": 0.5955666303634644,
|
| 634 |
+
"learning_rate": 5.162069615906998e-06,
|
| 635 |
+
"loss": 1.9852,
|
| 636 |
+
"step": 2125
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 5.47,
|
| 640 |
+
"grad_norm": 0.6157717108726501,
|
| 641 |
+
"learning_rate": 5.051071087482442e-06,
|
| 642 |
+
"loss": 1.967,
|
| 643 |
+
"step": 2150
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 5.53,
|
| 647 |
+
"grad_norm": 0.7150459289550781,
|
| 648 |
+
"learning_rate": 4.940047378409786e-06,
|
| 649 |
+
"loss": 1.9798,
|
| 650 |
+
"step": 2175
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 5.59,
|
| 654 |
+
"grad_norm": 0.5714321732521057,
|
| 655 |
+
"learning_rate": 4.829053229034043e-06,
|
| 656 |
+
"loss": 1.9864,
|
| 657 |
+
"step": 2200
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 5.66,
|
| 661 |
+
"grad_norm": 0.5759787559509277,
|
| 662 |
+
"learning_rate": 4.718143365125784e-06,
|
| 663 |
+
"loss": 1.9802,
|
| 664 |
+
"step": 2225
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 5.72,
|
| 668 |
+
"grad_norm": 0.6573282480239868,
|
| 669 |
+
"learning_rate": 4.6073724708985575e-06,
|
| 670 |
+
"loss": 1.9851,
|
| 671 |
+
"step": 2250
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 5.79,
|
| 675 |
+
"grad_norm": 0.6285906434059143,
|
| 676 |
+
"learning_rate": 4.496795162046774e-06,
|
| 677 |
+
"loss": 1.9794,
|
| 678 |
+
"step": 2275
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 5.85,
|
| 682 |
+
"grad_norm": 0.645057201385498,
|
| 683 |
+
"learning_rate": 4.386465958817396e-06,
|
| 684 |
+
"loss": 1.9776,
|
| 685 |
+
"step": 2300
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 5.91,
|
| 689 |
+
"grad_norm": 0.6082957983016968,
|
| 690 |
+
"learning_rate": 4.276439259128667e-06,
|
| 691 |
+
"loss": 1.987,
|
| 692 |
+
"step": 2325
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 5.98,
|
| 696 |
+
"grad_norm": 0.6126915216445923,
|
| 697 |
+
"learning_rate": 4.1667693117491784e-06,
|
| 698 |
+
"loss": 1.9837,
|
| 699 |
+
"step": 2350
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.04,
|
| 703 |
+
"grad_norm": 0.5728232860565186,
|
| 704 |
+
"learning_rate": 4.057510189550456e-06,
|
| 705 |
+
"loss": 1.9822,
|
| 706 |
+
"step": 2375
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 6.1,
|
| 710 |
+
"grad_norm": 0.6158954501152039,
|
| 711 |
+
"learning_rate": 3.9487157628462784e-06,
|
| 712 |
+
"loss": 1.9709,
|
| 713 |
+
"step": 2400
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 6.17,
|
| 717 |
+
"grad_norm": 0.5914610028266907,
|
| 718 |
+
"learning_rate": 3.840439672831872e-06,
|
| 719 |
+
"loss": 1.9841,
|
| 720 |
+
"step": 2425
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 6.23,
|
| 724 |
+
"grad_norm": 0.6070579290390015,
|
| 725 |
+
"learning_rate": 3.7327353051360703e-06,
|
| 726 |
+
"loss": 1.965,
|
| 727 |
+
"step": 2450
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 6.29,
|
| 731 |
+
"grad_norm": 0.6792969107627869,
|
| 732 |
+
"learning_rate": 3.625655763499467e-06,
|
| 733 |
+
"loss": 1.9792,
|
| 734 |
+
"step": 2475
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.36,
|
| 738 |
+
"grad_norm": 0.5990138053894043,
|
| 739 |
+
"learning_rate": 3.5192538435915834e-06,
|
| 740 |
+
"loss": 1.9739,
|
| 741 |
+
"step": 2500
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.36,
|
| 745 |
+
"eval_loss": 1.862921118736267,
|
| 746 |
+
"eval_runtime": 2.6134,
|
| 747 |
+
"eval_samples_per_second": 191.32,
|
| 748 |
+
"eval_steps_per_second": 24.106,
|
| 749 |
+
"step": 2500
|
| 750 |
+
}
|
| 751 |
+
],
|
| 752 |
+
"logging_steps": 25,
|
| 753 |
+
"max_steps": 3930,
|
| 754 |
+
"num_input_tokens_seen": 0,
|
| 755 |
+
"num_train_epochs": 10,
|
| 756 |
+
"save_steps": 500,
|
| 757 |
+
"total_flos": 0.0,
|
| 758 |
+
"train_batch_size": 8,
|
| 759 |
+
"trial_name": null,
|
| 760 |
+
"trial_params": null
|
| 761 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eee975e6b9a502abdd36a9eacb349577b79673f9b562bbe7296c4ce27b56e32f
|
| 3 |
+
size 5329
|