Run 4. Outer Step 20. 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": "SUCCESS",
|
| 7 |
+
"10": "SUCCESS",
|
| 8 |
+
"100": "NON_PARTICIPATING",
|
| 9 |
+
"101": "SUCCESS",
|
| 10 |
+
"102": "NON_PARTICIPATING",
|
| 11 |
+
"103": "NON_PARTICIPATING",
|
| 12 |
+
"104": "NON_PARTICIPATING",
|
| 13 |
+
"105": "NON_PARTICIPATING",
|
| 14 |
+
"106": "SUCCESS",
|
| 15 |
+
"107": "SUCCESS",
|
| 16 |
+
"108": "NON_PARTICIPATING",
|
| 17 |
+
"109": "NON_PARTICIPATING",
|
| 18 |
+
"11": "NON_PARTICIPATING",
|
| 19 |
+
"110": "SUCCESS",
|
| 20 |
+
"111": "SUCCESS",
|
| 21 |
+
"112": "NON_PARTICIPATING",
|
| 22 |
+
"113": "NON_PARTICIPATING",
|
| 23 |
+
"114": "SUCCESS",
|
| 24 |
+
"115": "NON_PARTICIPATING",
|
| 25 |
+
"116": "NON_PARTICIPATING",
|
| 26 |
+
"117": "NON_PARTICIPATING",
|
| 27 |
+
"118": "SUCCESS",
|
| 28 |
+
"119": "NON_PARTICIPATING",
|
| 29 |
+
"12": "SUCCESS",
|
| 30 |
+
"120": "NON_PARTICIPATING",
|
| 31 |
+
"121": "SUCCESS",
|
| 32 |
+
"122": "SUCCESS",
|
| 33 |
+
"123": "SUCCESS",
|
| 34 |
+
"124": "NON_PARTICIPATING",
|
| 35 |
+
"125": "NON_PARTICIPATING",
|
| 36 |
+
"126": "NON_PARTICIPATING",
|
| 37 |
+
"127": "SUCCESS",
|
| 38 |
+
"128": "NON_PARTICIPATING",
|
| 39 |
+
"129": "NON_PARTICIPATING",
|
| 40 |
+
"13": "NON_PARTICIPATING",
|
| 41 |
+
"130": "NON_PARTICIPATING",
|
| 42 |
+
"131": "NON_PARTICIPATING",
|
| 43 |
+
"132": "SUCCESS",
|
| 44 |
+
"133": "NON_PARTICIPATING",
|
| 45 |
+
"134": "NON_PARTICIPATING",
|
| 46 |
+
"135": "SUCCESS",
|
| 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": "SUCCESS",
|
| 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": "SUCCESS",
|
| 62 |
+
"15": "SUCCESS",
|
| 63 |
+
"150": "NON_PARTICIPATING",
|
| 64 |
+
"151": "NON_PARTICIPATING",
|
| 65 |
+
"152": "NON_PARTICIPATING",
|
| 66 |
+
"153": "NON_PARTICIPATING",
|
| 67 |
+
"154": "SUCCESS",
|
| 68 |
+
"155": "NON_PARTICIPATING",
|
| 69 |
+
"156": "SUCCESS",
|
| 70 |
+
"157": "NON_PARTICIPATING",
|
| 71 |
+
"158": "NON_PARTICIPATING",
|
| 72 |
+
"159": "SUCCESS",
|
| 73 |
+
"16": "SUCCESS",
|
| 74 |
+
"160": "SUCCESS",
|
| 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": "SUCCESS",
|
| 82 |
+
"168": "NON_PARTICIPATING",
|
| 83 |
+
"169": "NON_PARTICIPATING",
|
| 84 |
+
"17": "SUCCESS",
|
| 85 |
+
"170": "SUCCESS",
|
| 86 |
+
"171": "NON_PARTICIPATING",
|
| 87 |
+
"172": "SUCCESS",
|
| 88 |
+
"173": "NON_PARTICIPATING",
|
| 89 |
+
"174": "NON_PARTICIPATING",
|
| 90 |
+
"175": "SUCCESS",
|
| 91 |
+
"176": "NON_PARTICIPATING",
|
| 92 |
+
"177": "NON_PARTICIPATING",
|
| 93 |
+
"178": "NON_PARTICIPATING",
|
| 94 |
+
"179": "NON_PARTICIPATING",
|
| 95 |
+
"18": "SUCCESS",
|
| 96 |
+
"180": "NON_PARTICIPATING",
|
| 97 |
+
"181": "NON_PARTICIPATING",
|
| 98 |
+
"182": "NON_PARTICIPATING",
|
| 99 |
+
"183": "NON_PARTICIPATING",
|
| 100 |
+
"184": "SUCCESS",
|
| 101 |
+
"185": "NON_PARTICIPATING",
|
| 102 |
+
"186": "SUCCESS",
|
| 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": "SUCCESS",
|
| 111 |
+
"194": "NON_PARTICIPATING",
|
| 112 |
+
"195": "SUCCESS",
|
| 113 |
+
"196": "NON_PARTICIPATING",
|
| 114 |
+
"197": "NON_PARTICIPATING",
|
| 115 |
+
"198": "NON_PARTICIPATING",
|
| 116 |
+
"199": "NON_PARTICIPATING",
|
| 117 |
+
"2": "SUCCESS",
|
| 118 |
+
"20": "SUCCESS",
|
| 119 |
+
"200": "SUCCESS",
|
| 120 |
+
"201": "SUCCESS",
|
| 121 |
+
"202": "NON_PARTICIPATING",
|
| 122 |
+
"203": "SUCCESS",
|
| 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": "SUCCESS",
|
| 130 |
+
"210": "NON_PARTICIPATING",
|
| 131 |
+
"211": "NON_PARTICIPATING",
|
| 132 |
+
"212": "NON_PARTICIPATING",
|
| 133 |
+
"213": "NON_PARTICIPATING",
|
| 134 |
+
"214": "SUCCESS",
|
| 135 |
+
"215": "SUCCESS",
|
| 136 |
+
"216": "NON_PARTICIPATING",
|
| 137 |
+
"217": "NON_PARTICIPATING",
|
| 138 |
+
"218": "SUCCESS",
|
| 139 |
+
"219": "SUCCESS",
|
| 140 |
+
"22": "SUCCESS",
|
| 141 |
+
"220": "NON_PARTICIPATING",
|
| 142 |
+
"221": "NON_PARTICIPATING",
|
| 143 |
+
"222": "NON_PARTICIPATING",
|
| 144 |
+
"223": "SUCCESS",
|
| 145 |
+
"224": "NON_PARTICIPATING",
|
| 146 |
+
"225": "SUCCESS",
|
| 147 |
+
"226": "SUCCESS",
|
| 148 |
+
"227": "NON_PARTICIPATING",
|
| 149 |
+
"228": "NON_PARTICIPATING",
|
| 150 |
+
"229": "NON_PARTICIPATING",
|
| 151 |
+
"23": "SUCCESS",
|
| 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": "SUCCESS",
|
| 163 |
+
"240": "NON_PARTICIPATING",
|
| 164 |
+
"241": "NON_PARTICIPATING",
|
| 165 |
+
"242": "NON_PARTICIPATING",
|
| 166 |
+
"243": "NON_PARTICIPATING",
|
| 167 |
+
"244": "SUCCESS",
|
| 168 |
+
"245": "NON_PARTICIPATING",
|
| 169 |
+
"246": "NON_PARTICIPATING",
|
| 170 |
+
"247": "SUCCESS",
|
| 171 |
+
"248": "NON_PARTICIPATING",
|
| 172 |
+
"249": "SUCCESS",
|
| 173 |
+
"25": "SUCCESS",
|
| 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": "SUCCESS",
|
| 181 |
+
"27": "SUCCESS",
|
| 182 |
+
"28": "SUCCESS",
|
| 183 |
+
"29": "SUCCESS",
|
| 184 |
+
"3": "NON_PARTICIPATING",
|
| 185 |
+
"30": "NON_PARTICIPATING",
|
| 186 |
+
"31": "NON_PARTICIPATING",
|
| 187 |
+
"32": "SUCCESS",
|
| 188 |
+
"33": "NON_PARTICIPATING",
|
| 189 |
+
"34": "SUCCESS",
|
| 190 |
+
"35": "NON_PARTICIPATING",
|
| 191 |
+
"36": "NON_PARTICIPATING",
|
| 192 |
+
"37": "SUCCESS",
|
| 193 |
+
"38": "NON_PARTICIPATING",
|
| 194 |
+
"39": "NON_PARTICIPATING",
|
| 195 |
+
"4": "NON_PARTICIPATING",
|
| 196 |
+
"40": "SUCCESS",
|
| 197 |
+
"41": "SUCCESS",
|
| 198 |
+
"42": "NON_PARTICIPATING",
|
| 199 |
+
"43": "SUCCESS",
|
| 200 |
+
"44": "SUCCESS",
|
| 201 |
+
"45": "SUCCESS",
|
| 202 |
+
"46": "SUCCESS",
|
| 203 |
+
"47": "SUCCESS",
|
| 204 |
+
"48": "NON_PARTICIPATING",
|
| 205 |
+
"49": "SUCCESS",
|
| 206 |
+
"5": "NON_PARTICIPATING",
|
| 207 |
+
"50": "SUCCESS",
|
| 208 |
+
"51": "SUCCESS",
|
| 209 |
+
"52": "NON_PARTICIPATING",
|
| 210 |
+
"53": "NON_PARTICIPATING",
|
| 211 |
+
"54": "SUCCESS",
|
| 212 |
+
"55": "SUCCESS",
|
| 213 |
+
"56": "SUCCESS",
|
| 214 |
+
"57": "SUCCESS",
|
| 215 |
+
"58": "NON_PARTICIPATING",
|
| 216 |
+
"59": "NON_PARTICIPATING",
|
| 217 |
+
"6": "NON_PARTICIPATING",
|
| 218 |
+
"60": "SUCCESS",
|
| 219 |
+
"61": "NON_PARTICIPATING",
|
| 220 |
+
"62": "SUCCESS",
|
| 221 |
+
"63": "SUCCESS",
|
| 222 |
+
"64": "NON_PARTICIPATING",
|
| 223 |
+
"65": "NON_PARTICIPATING",
|
| 224 |
+
"66": "NON_PARTICIPATING",
|
| 225 |
+
"67": "SUCCESS",
|
| 226 |
+
"68": "SUCCESS",
|
| 227 |
+
"69": "NON_PARTICIPATING",
|
| 228 |
+
"7": "SUCCESS",
|
| 229 |
+
"70": "NON_PARTICIPATING",
|
| 230 |
+
"71": "NON_PARTICIPATING",
|
| 231 |
+
"72": "NON_PARTICIPATING",
|
| 232 |
+
"73": "NON_PARTICIPATING",
|
| 233 |
+
"74": "NON_PARTICIPATING",
|
| 234 |
+
"75": "SUCCESS",
|
| 235 |
+
"76": "NON_PARTICIPATING",
|
| 236 |
+
"77": "NON_PARTICIPATING",
|
| 237 |
+
"78": "NON_PARTICIPATING",
|
| 238 |
+
"79": "NON_PARTICIPATING",
|
| 239 |
+
"8": "SUCCESS",
|
| 240 |
+
"80": "SUCCESS",
|
| 241 |
+
"81": "NON_PARTICIPATING",
|
| 242 |
+
"82": "SUCCESS",
|
| 243 |
+
"83": "NON_PARTICIPATING",
|
| 244 |
+
"84": "SUCCESS",
|
| 245 |
+
"85": "NON_PARTICIPATING",
|
| 246 |
+
"86": "NON_PARTICIPATING",
|
| 247 |
+
"87": "SUCCESS",
|
| 248 |
+
"88": "SUCCESS",
|
| 249 |
+
"89": "SUCCESS",
|
| 250 |
+
"9": "NON_PARTICIPATING",
|
| 251 |
+
"90": "NON_PARTICIPATING",
|
| 252 |
+
"91": "SUCCESS",
|
| 253 |
+
"92": "NON_PARTICIPATING",
|
| 254 |
+
"93": "NON_PARTICIPATING",
|
| 255 |
+
"94": "SUCCESS",
|
| 256 |
+
"95": "SUCCESS",
|
| 257 |
+
"96": "SUCCESS",
|
| 258 |
+
"97": "NON_PARTICIPATING",
|
| 259 |
+
"98": "SUCCESS",
|
| 260 |
+
"99": "SUCCESS"
|
| 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 |
+
5524865,
|
| 272 |
+
5524867,
|
| 273 |
+
5524868,
|
| 274 |
+
5524870,
|
| 275 |
+
5524873
|
| 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": 5523943,
|
| 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:e94fa6ac5551a36f60d15da29d09afdb270881cc81e1d5d124c11fbb9f83f935
|
| 3 |
+
size 8081782026
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22d2815d35e5139d8f03b0869a4072819f099cc8f8fcf4e0be28d232526efd42
|
| 3 |
+
size 4040701744
|