Run 3. Outer Step 12. Inner Step 0.
Browse files- config.json +305 -0
- inner_optimizer.pt +3 -0
- model.safetensors +3 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,305 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "distributed/optimized-gpt2-1b",
         | 
| 3 | 
            +
              "activation_function": "gelu_new",
         | 
| 4 | 
            +
              "all_reduce_scores": {
         | 
| 5 | 
            +
                "0": "NON_PARTICIPATING",
         | 
| 6 | 
            +
                "1": "NON_PARTICIPATING",
         | 
| 7 | 
            +
                "10": "NON_PARTICIPATING",
         | 
| 8 | 
            +
                "100": "NON_PARTICIPATING",
         | 
| 9 | 
            +
                "101": "NON_PARTICIPATING",
         | 
| 10 | 
            +
                "102": "NON_PARTICIPATING",
         | 
| 11 | 
            +
                "103": "NON_PARTICIPATING",
         | 
| 12 | 
            +
                "104": "NON_PARTICIPATING",
         | 
| 13 | 
            +
                "105": "NON_PARTICIPATING",
         | 
| 14 | 
            +
                "106": "NON_PARTICIPATING",
         | 
| 15 | 
            +
                "107": "NON_PARTICIPATING",
         | 
| 16 | 
            +
                "108": "NON_PARTICIPATING",
         | 
| 17 | 
            +
                "109": "NON_PARTICIPATING",
         | 
| 18 | 
            +
                "11": "NON_PARTICIPATING",
         | 
| 19 | 
            +
                "110": "NON_PARTICIPATING",
         | 
| 20 | 
            +
                "111": "NON_PARTICIPATING",
         | 
| 21 | 
            +
                "112": "NON_PARTICIPATING",
         | 
| 22 | 
            +
                "113": "NON_PARTICIPATING",
         | 
| 23 | 
            +
                "114": "NON_PARTICIPATING",
         | 
| 24 | 
            +
                "115": "NON_PARTICIPATING",
         | 
| 25 | 
            +
                "116": "NON_PARTICIPATING",
         | 
| 26 | 
            +
                "117": "NON_PARTICIPATING",
         | 
| 27 | 
            +
                "118": "NON_PARTICIPATING",
         | 
| 28 | 
            +
                "119": "NON_PARTICIPATING",
         | 
| 29 | 
            +
                "12": "NON_PARTICIPATING",
         | 
| 30 | 
            +
                "120": "NON_PARTICIPATING",
         | 
| 31 | 
            +
                "121": "NON_PARTICIPATING",
         | 
| 32 | 
            +
                "122": "NON_PARTICIPATING",
         | 
| 33 | 
            +
                "123": "NON_PARTICIPATING",
         | 
| 34 | 
            +
                "124": "NON_PARTICIPATING",
         | 
| 35 | 
            +
                "125": "NON_PARTICIPATING",
         | 
| 36 | 
            +
                "126": "NON_PARTICIPATING",
         | 
| 37 | 
            +
                "127": "NON_PARTICIPATING",
         | 
| 38 | 
            +
                "128": "NON_PARTICIPATING",
         | 
| 39 | 
            +
                "129": "NON_PARTICIPATING",
         | 
| 40 | 
            +
                "13": "NON_PARTICIPATING",
         | 
| 41 | 
            +
                "130": "NON_PARTICIPATING",
         | 
| 42 | 
            +
                "131": "NON_PARTICIPATING",
         | 
| 43 | 
            +
                "132": "NON_PARTICIPATING",
         | 
| 44 | 
            +
                "133": "NON_PARTICIPATING",
         | 
| 45 | 
            +
                "134": "NON_PARTICIPATING",
         | 
| 46 | 
            +
                "135": "NON_PARTICIPATING",
         | 
| 47 | 
            +
                "136": "NON_PARTICIPATING",
         | 
| 48 | 
            +
                "137": "NON_PARTICIPATING",
         | 
| 49 | 
            +
                "138": "NON_PARTICIPATING",
         | 
| 50 | 
            +
                "139": "NON_PARTICIPATING",
         | 
| 51 | 
            +
                "14": "NON_PARTICIPATING",
         | 
| 52 | 
            +
                "140": "NON_PARTICIPATING",
         | 
| 53 | 
            +
                "141": "NON_PARTICIPATING",
         | 
| 54 | 
            +
                "142": "NON_PARTICIPATING",
         | 
| 55 | 
            +
                "143": "NON_PARTICIPATING",
         | 
| 56 | 
            +
                "144": "NON_PARTICIPATING",
         | 
| 57 | 
            +
                "145": "NON_PARTICIPATING",
         | 
| 58 | 
            +
                "146": "NON_PARTICIPATING",
         | 
| 59 | 
            +
                "147": "NON_PARTICIPATING",
         | 
| 60 | 
            +
                "148": "NON_PARTICIPATING",
         | 
| 61 | 
            +
                "149": "NON_PARTICIPATING",
         | 
| 62 | 
            +
                "15": "NON_PARTICIPATING",
         | 
| 63 | 
            +
                "150": "NON_PARTICIPATING",
         | 
| 64 | 
            +
                "151": "NON_PARTICIPATING",
         | 
| 65 | 
            +
                "152": "NON_PARTICIPATING",
         | 
| 66 | 
            +
                "153": "NON_PARTICIPATING",
         | 
| 67 | 
            +
                "154": "NON_PARTICIPATING",
         | 
| 68 | 
            +
                "155": "NON_PARTICIPATING",
         | 
| 69 | 
            +
                "156": "NON_PARTICIPATING",
         | 
| 70 | 
            +
                "157": "NON_PARTICIPATING",
         | 
| 71 | 
            +
                "158": "NON_PARTICIPATING",
         | 
| 72 | 
            +
                "159": "NON_PARTICIPATING",
         | 
| 73 | 
            +
                "16": "NON_PARTICIPATING",
         | 
| 74 | 
            +
                "160": "NON_PARTICIPATING",
         | 
| 75 | 
            +
                "161": "NON_PARTICIPATING",
         | 
| 76 | 
            +
                "162": "NON_PARTICIPATING",
         | 
| 77 | 
            +
                "163": "NON_PARTICIPATING",
         | 
| 78 | 
            +
                "164": "NON_PARTICIPATING",
         | 
| 79 | 
            +
                "165": "NON_PARTICIPATING",
         | 
| 80 | 
            +
                "166": "NON_PARTICIPATING",
         | 
| 81 | 
            +
                "167": "NON_PARTICIPATING",
         | 
| 82 | 
            +
                "168": "NON_PARTICIPATING",
         | 
| 83 | 
            +
                "169": "NON_PARTICIPATING",
         | 
| 84 | 
            +
                "17": "NON_PARTICIPATING",
         | 
| 85 | 
            +
                "170": "NON_PARTICIPATING",
         | 
| 86 | 
            +
                "171": "NON_PARTICIPATING",
         | 
| 87 | 
            +
                "172": "NON_PARTICIPATING",
         | 
| 88 | 
            +
                "173": "NON_PARTICIPATING",
         | 
| 89 | 
            +
                "174": "NON_PARTICIPATING",
         | 
| 90 | 
            +
                "175": "NON_PARTICIPATING",
         | 
| 91 | 
            +
                "176": "NON_PARTICIPATING",
         | 
| 92 | 
            +
                "177": "NON_PARTICIPATING",
         | 
| 93 | 
            +
                "178": "NON_PARTICIPATING",
         | 
| 94 | 
            +
                "179": "NON_PARTICIPATING",
         | 
| 95 | 
            +
                "18": "NON_PARTICIPATING",
         | 
| 96 | 
            +
                "180": "NON_PARTICIPATING",
         | 
| 97 | 
            +
                "181": "NON_PARTICIPATING",
         | 
| 98 | 
            +
                "182": "NON_PARTICIPATING",
         | 
| 99 | 
            +
                "183": "NON_PARTICIPATING",
         | 
| 100 | 
            +
                "184": "NON_PARTICIPATING",
         | 
| 101 | 
            +
                "185": "NON_PARTICIPATING",
         | 
| 102 | 
            +
                "186": "NON_PARTICIPATING",
         | 
| 103 | 
            +
                "187": "NON_PARTICIPATING",
         | 
| 104 | 
            +
                "188": "NON_PARTICIPATING",
         | 
| 105 | 
            +
                "189": "NON_PARTICIPATING",
         | 
| 106 | 
            +
                "19": "NON_PARTICIPATING",
         | 
| 107 | 
            +
                "190": "NON_PARTICIPATING",
         | 
| 108 | 
            +
                "191": "NON_PARTICIPATING",
         | 
| 109 | 
            +
                "192": "NON_PARTICIPATING",
         | 
| 110 | 
            +
                "193": "NON_PARTICIPATING",
         | 
| 111 | 
            +
                "194": "NON_PARTICIPATING",
         | 
| 112 | 
            +
                "195": "NON_PARTICIPATING",
         | 
| 113 | 
            +
                "196": "NON_PARTICIPATING",
         | 
| 114 | 
            +
                "197": "NON_PARTICIPATING",
         | 
| 115 | 
            +
                "198": "NON_PARTICIPATING",
         | 
| 116 | 
            +
                "199": "NON_PARTICIPATING",
         | 
| 117 | 
            +
                "2": "NON_PARTICIPATING",
         | 
| 118 | 
            +
                "20": "NON_PARTICIPATING",
         | 
| 119 | 
            +
                "200": "NON_PARTICIPATING",
         | 
| 120 | 
            +
                "201": "NON_PARTICIPATING",
         | 
| 121 | 
            +
                "202": "NON_PARTICIPATING",
         | 
| 122 | 
            +
                "203": "NON_PARTICIPATING",
         | 
| 123 | 
            +
                "204": "NON_PARTICIPATING",
         | 
| 124 | 
            +
                "205": "NON_PARTICIPATING",
         | 
| 125 | 
            +
                "206": "NON_PARTICIPATING",
         | 
| 126 | 
            +
                "207": "NON_PARTICIPATING",
         | 
| 127 | 
            +
                "208": "NON_PARTICIPATING",
         | 
| 128 | 
            +
                "209": "NON_PARTICIPATING",
         | 
| 129 | 
            +
                "21": "NON_PARTICIPATING",
         | 
| 130 | 
            +
                "210": "NON_PARTICIPATING",
         | 
| 131 | 
            +
                "211": "NON_PARTICIPATING",
         | 
| 132 | 
            +
                "212": "NON_PARTICIPATING",
         | 
| 133 | 
            +
                "213": "NON_PARTICIPATING",
         | 
| 134 | 
            +
                "214": "NON_PARTICIPATING",
         | 
| 135 | 
            +
                "215": "NON_PARTICIPATING",
         | 
| 136 | 
            +
                "216": "NON_PARTICIPATING",
         | 
| 137 | 
            +
                "217": "NON_PARTICIPATING",
         | 
| 138 | 
            +
                "218": "NON_PARTICIPATING",
         | 
| 139 | 
            +
                "219": "NON_PARTICIPATING",
         | 
| 140 | 
            +
                "22": "NON_PARTICIPATING",
         | 
| 141 | 
            +
                "220": "NON_PARTICIPATING",
         | 
| 142 | 
            +
                "221": "NON_PARTICIPATING",
         | 
| 143 | 
            +
                "222": "NON_PARTICIPATING",
         | 
| 144 | 
            +
                "223": "NON_PARTICIPATING",
         | 
| 145 | 
            +
                "224": "NON_PARTICIPATING",
         | 
| 146 | 
            +
                "225": "NON_PARTICIPATING",
         | 
| 147 | 
            +
                "226": "NON_PARTICIPATING",
         | 
| 148 | 
            +
                "227": "NON_PARTICIPATING",
         | 
| 149 | 
            +
                "228": "NON_PARTICIPATING",
         | 
| 150 | 
            +
                "229": "NON_PARTICIPATING",
         | 
| 151 | 
            +
                "23": "NON_PARTICIPATING",
         | 
| 152 | 
            +
                "230": "NON_PARTICIPATING",
         | 
| 153 | 
            +
                "231": "NON_PARTICIPATING",
         | 
| 154 | 
            +
                "232": "NON_PARTICIPATING",
         | 
| 155 | 
            +
                "233": "NON_PARTICIPATING",
         | 
| 156 | 
            +
                "234": "NON_PARTICIPATING",
         | 
| 157 | 
            +
                "235": "NON_PARTICIPATING",
         | 
| 158 | 
            +
                "236": "NON_PARTICIPATING",
         | 
| 159 | 
            +
                "237": "NON_PARTICIPATING",
         | 
| 160 | 
            +
                "238": "NON_PARTICIPATING",
         | 
| 161 | 
            +
                "239": "NON_PARTICIPATING",
         | 
| 162 | 
            +
                "24": "NON_PARTICIPATING",
         | 
| 163 | 
            +
                "240": "NON_PARTICIPATING",
         | 
| 164 | 
            +
                "241": "NON_PARTICIPATING",
         | 
| 165 | 
            +
                "242": "NON_PARTICIPATING",
         | 
| 166 | 
            +
                "243": "NON_PARTICIPATING",
         | 
| 167 | 
            +
                "244": "NON_PARTICIPATING",
         | 
| 168 | 
            +
                "245": "NON_PARTICIPATING",
         | 
| 169 | 
            +
                "246": "NON_PARTICIPATING",
         | 
| 170 | 
            +
                "247": "NON_PARTICIPATING",
         | 
| 171 | 
            +
                "248": "NON_PARTICIPATING",
         | 
| 172 | 
            +
                "249": "NON_PARTICIPATING",
         | 
| 173 | 
            +
                "25": "NON_PARTICIPATING",
         | 
| 174 | 
            +
                "250": "NON_PARTICIPATING",
         | 
| 175 | 
            +
                "251": "NON_PARTICIPATING",
         | 
| 176 | 
            +
                "252": "NON_PARTICIPATING",
         | 
| 177 | 
            +
                "253": "NON_PARTICIPATING",
         | 
| 178 | 
            +
                "254": "NON_PARTICIPATING",
         | 
| 179 | 
            +
                "255": "NON_PARTICIPATING",
         | 
| 180 | 
            +
                "26": "NON_PARTICIPATING",
         | 
| 181 | 
            +
                "27": "NON_PARTICIPATING",
         | 
| 182 | 
            +
                "28": "NON_PARTICIPATING",
         | 
| 183 | 
            +
                "29": "NON_PARTICIPATING",
         | 
| 184 | 
            +
                "3": "NON_PARTICIPATING",
         | 
| 185 | 
            +
                "30": "NON_PARTICIPATING",
         | 
| 186 | 
            +
                "31": "NON_PARTICIPATING",
         | 
| 187 | 
            +
                "32": "NON_PARTICIPATING",
         | 
| 188 | 
            +
                "33": "NON_PARTICIPATING",
         | 
| 189 | 
            +
                "34": "NON_PARTICIPATING",
         | 
| 190 | 
            +
                "35": "NON_PARTICIPATING",
         | 
| 191 | 
            +
                "36": "NON_PARTICIPATING",
         | 
| 192 | 
            +
                "37": "NON_PARTICIPATING",
         | 
| 193 | 
            +
                "38": "NON_PARTICIPATING",
         | 
| 194 | 
            +
                "39": "NON_PARTICIPATING",
         | 
| 195 | 
            +
                "4": "NON_PARTICIPATING",
         | 
| 196 | 
            +
                "40": "NON_PARTICIPATING",
         | 
| 197 | 
            +
                "41": "NON_PARTICIPATING",
         | 
| 198 | 
            +
                "42": "NON_PARTICIPATING",
         | 
| 199 | 
            +
                "43": "NON_PARTICIPATING",
         | 
| 200 | 
            +
                "44": "NON_PARTICIPATING",
         | 
| 201 | 
            +
                "45": "NON_PARTICIPATING",
         | 
| 202 | 
            +
                "46": "NON_PARTICIPATING",
         | 
| 203 | 
            +
                "47": "NON_PARTICIPATING",
         | 
| 204 | 
            +
                "48": "NON_PARTICIPATING",
         | 
| 205 | 
            +
                "49": "NON_PARTICIPATING",
         | 
| 206 | 
            +
                "5": "NON_PARTICIPATING",
         | 
| 207 | 
            +
                "50": "NON_PARTICIPATING",
         | 
| 208 | 
            +
                "51": "NON_PARTICIPATING",
         | 
| 209 | 
            +
                "52": "NON_PARTICIPATING",
         | 
| 210 | 
            +
                "53": "NON_PARTICIPATING",
         | 
| 211 | 
            +
                "54": "NON_PARTICIPATING",
         | 
| 212 | 
            +
                "55": "NON_PARTICIPATING",
         | 
| 213 | 
            +
                "56": "NON_PARTICIPATING",
         | 
| 214 | 
            +
                "57": "NON_PARTICIPATING",
         | 
| 215 | 
            +
                "58": "NON_PARTICIPATING",
         | 
| 216 | 
            +
                "59": "NON_PARTICIPATING",
         | 
| 217 | 
            +
                "6": "NON_PARTICIPATING",
         | 
| 218 | 
            +
                "60": "NON_PARTICIPATING",
         | 
| 219 | 
            +
                "61": "NON_PARTICIPATING",
         | 
| 220 | 
            +
                "62": "NON_PARTICIPATING",
         | 
| 221 | 
            +
                "63": "NON_PARTICIPATING",
         | 
| 222 | 
            +
                "64": "NON_PARTICIPATING",
         | 
| 223 | 
            +
                "65": "NON_PARTICIPATING",
         | 
| 224 | 
            +
                "66": "NON_PARTICIPATING",
         | 
| 225 | 
            +
                "67": "NON_PARTICIPATING",
         | 
| 226 | 
            +
                "68": "NON_PARTICIPATING",
         | 
| 227 | 
            +
                "69": "NON_PARTICIPATING",
         | 
| 228 | 
            +
                "7": "NON_PARTICIPATING",
         | 
| 229 | 
            +
                "70": "NON_PARTICIPATING",
         | 
| 230 | 
            +
                "71": "NON_PARTICIPATING",
         | 
| 231 | 
            +
                "72": "NON_PARTICIPATING",
         | 
| 232 | 
            +
                "73": "NON_PARTICIPATING",
         | 
| 233 | 
            +
                "74": "NON_PARTICIPATING",
         | 
| 234 | 
            +
                "75": "NON_PARTICIPATING",
         | 
| 235 | 
            +
                "76": "NON_PARTICIPATING",
         | 
| 236 | 
            +
                "77": "NON_PARTICIPATING",
         | 
| 237 | 
            +
                "78": "NON_PARTICIPATING",
         | 
| 238 | 
            +
                "79": "NON_PARTICIPATING",
         | 
| 239 | 
            +
                "8": "NON_PARTICIPATING",
         | 
| 240 | 
            +
                "80": "NON_PARTICIPATING",
         | 
| 241 | 
            +
                "81": "NON_PARTICIPATING",
         | 
| 242 | 
            +
                "82": "NON_PARTICIPATING",
         | 
| 243 | 
            +
                "83": "NON_PARTICIPATING",
         | 
| 244 | 
            +
                "84": "NON_PARTICIPATING",
         | 
| 245 | 
            +
                "85": "NON_PARTICIPATING",
         | 
| 246 | 
            +
                "86": "NON_PARTICIPATING",
         | 
| 247 | 
            +
                "87": "NON_PARTICIPATING",
         | 
| 248 | 
            +
                "88": "NON_PARTICIPATING",
         | 
| 249 | 
            +
                "89": "NON_PARTICIPATING",
         | 
| 250 | 
            +
                "9": "NON_PARTICIPATING",
         | 
| 251 | 
            +
                "90": "NON_PARTICIPATING",
         | 
| 252 | 
            +
                "91": "NON_PARTICIPATING",
         | 
| 253 | 
            +
                "92": "NON_PARTICIPATING",
         | 
| 254 | 
            +
                "93": "NON_PARTICIPATING",
         | 
| 255 | 
            +
                "94": "NON_PARTICIPATING",
         | 
| 256 | 
            +
                "95": "NON_PARTICIPATING",
         | 
| 257 | 
            +
                "96": "NON_PARTICIPATING",
         | 
| 258 | 
            +
                "97": "NON_PARTICIPATING",
         | 
| 259 | 
            +
                "98": "NON_PARTICIPATING",
         | 
| 260 | 
            +
                "99": "NON_PARTICIPATING"
         | 
| 261 | 
            +
              },
         | 
| 262 | 
            +
              "architectures": [
         | 
| 263 | 
            +
                "GPTOptim"
         | 
| 264 | 
            +
              ],
         | 
| 265 | 
            +
              "attn_pdrop": 0.1,
         | 
| 266 | 
            +
              "auto_map": {
         | 
| 267 | 
            +
                "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
         | 
| 268 | 
            +
                "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
         | 
| 269 | 
            +
              },
         | 
| 270 | 
            +
              "block_list": [
         | 
| 271 | 
            +
                5466548,
         | 
| 272 | 
            +
                5466551,
         | 
| 273 | 
            +
                5466553,
         | 
| 274 | 
            +
                5466556,
         | 
| 275 | 
            +
                5466558
         | 
| 276 | 
            +
              ],
         | 
| 277 | 
            +
              "block_size": 1024,
         | 
| 278 | 
            +
              "bos_token_id": 50256,
         | 
| 279 | 
            +
              "embd_pdrop": 0.1,
         | 
| 280 | 
            +
              "eos_token_id": 50256,
         | 
| 281 | 
            +
              "initializer_range": 0.02,
         | 
| 282 | 
            +
              "inner_step": 0,
         | 
| 283 | 
            +
              "inner_steps": 0,
         | 
| 284 | 
            +
              "last_allreduce_block": 5450451,
         | 
| 285 | 
            +
              "layer_norm_epsilon": 1e-05,
         | 
| 286 | 
            +
              "model_type": "gpt_optimized",
         | 
| 287 | 
            +
              "n_embd": 1280,
         | 
| 288 | 
            +
              "n_head": 32,
         | 
| 289 | 
            +
              "n_inner": null,
         | 
| 290 | 
            +
              "n_layer": 48,
         | 
| 291 | 
            +
              "n_positions": 1024,
         | 
| 292 | 
            +
              "reorder_and_upcast_attn": false,
         | 
| 293 | 
            +
              "resid_pdrop": 0.1,
         | 
| 294 | 
            +
              "scale_attn_by_inverse_layer_idx": false,
         | 
| 295 | 
            +
              "scale_attn_weights": true,
         | 
| 296 | 
            +
              "summary_activation": null,
         | 
| 297 | 
            +
              "summary_first_dropout": 0.1,
         | 
| 298 | 
            +
              "summary_proj_to_labels": true,
         | 
| 299 | 
            +
              "summary_type": "cls_index",
         | 
| 300 | 
            +
              "summary_use_proj": true,
         | 
| 301 | 
            +
              "torch_dtype": "float32",
         | 
| 302 | 
            +
              "transformers_version": "4.39.3",
         | 
| 303 | 
            +
              "use_cache": true,
         | 
| 304 | 
            +
              "vocab_size": 50257
         | 
| 305 | 
            +
            }
         | 
    	
        inner_optimizer.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:33e565b43e3a803cc0103fbe6dbdc5b644c1a180748c66e5e50343726a6184fb
         | 
| 3 | 
            +
            size 8081782026
         | 
    	
        model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:73efb0c1068249abe2eb6b6207f5e051b4312911446a9a1d544ec2cb71610cf7
         | 
| 3 | 
            +
            size 4040701744
         | 
