CoolFace
Modelpublic

kaijames1231423/DistributedTraining

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes2downloads
config.json294 linesDownload Raw Back to root
1{2  "_name_or_path": "kaijames1231423/DistributedTraining",3  "all_reduce_scores": {4    "0": "NOT_ALIVE",5    "1": "NON_PARTICIPATING",6    "10": "NOT_ALIVE",7    "100": "NOT_ALIVE",8    "101": "NOT_ALIVE",9    "102": "NOT_ALIVE",10    "103": "NON_PARTICIPATING",11    "104": "NON_PARTICIPATING",12    "105": "FAIL",13    "106": "NOT_ALIVE",14    "107": "FAIL",15    "108": "NOT_ALIVE",16    "109": "NON_PARTICIPATING",17    "11": "NON_PARTICIPATING",18    "110": "FAIL",19    "111": "NON_PARTICIPATING",20    "112": "NON_PARTICIPATING",21    "113": "NON_PARTICIPATING",22    "114": "NON_PARTICIPATING",23    "115": "NON_PARTICIPATING",24    "116": "NON_PARTICIPATING",25    "117": "FAIL",26    "118": "FAIL",27    "119": "NON_PARTICIPATING",28    "12": "NOT_ALIVE",29    "120": "NON_PARTICIPATING",30    "121": "NOT_ALIVE",31    "122": "NON_PARTICIPATING",32    "123": "FAIL",33    "124": "NON_PARTICIPATING",34    "125": "FAIL",35    "126": "NOT_ALIVE",36    "127": "NON_PARTICIPATING",37    "128": "NON_PARTICIPATING",38    "129": "NON_PARTICIPATING",39    "13": "NON_PARTICIPATING",40    "130": "NON_PARTICIPATING",41    "131": "NOT_ALIVE",42    "132": "NOT_ALIVE",43    "133": "NON_PARTICIPATING",44    "134": "NON_PARTICIPATING",45    "135": "NON_PARTICIPATING",46    "136": "NOT_ALIVE",47    "137": "NOT_ALIVE",48    "138": "NON_PARTICIPATING",49    "139": "NOT_ALIVE",50    "14": "NOT_ALIVE",51    "140": "NOT_ALIVE",52    "141": "NON_PARTICIPATING",53    "142": "NOT_ALIVE",54    "143": "FAIL",55    "144": "NON_PARTICIPATING",56    "145": "NON_PARTICIPATING",57    "146": "FAIL",58    "147": "FAIL",59    "148": "NON_PARTICIPATING",60    "149": "NOT_ALIVE",61    "15": "NON_PARTICIPATING",62    "150": "NON_PARTICIPATING",63    "151": "NOT_ALIVE",64    "152": "NOT_ALIVE",65    "153": "NOT_ALIVE",66    "154": "NON_PARTICIPATING",67    "155": "NON_PARTICIPATING",68    "156": "NON_PARTICIPATING",69    "157": "NOT_ALIVE",70    "158": "NON_PARTICIPATING",71    "159": "FAIL",72    "16": "NOT_ALIVE",73    "160": "NOT_ALIVE",74    "161": "NOT_ALIVE",75    "162": "NON_PARTICIPATING",76    "163": "NOT_ALIVE",77    "164": "NOT_ALIVE",78    "165": "FAIL",79    "166": "NON_PARTICIPATING",80    "167": "NON_PARTICIPATING",81    "168": "FAIL",82    "169": "NON_PARTICIPATING",83    "17": "NON_PARTICIPATING",84    "170": "FAIL",85    "171": "NON_PARTICIPATING",86    "172": "NOT_ALIVE",87    "173": "FAIL",88    "174": "NOT_ALIVE",89    "175": "FAIL",90    "176": "NOT_ALIVE",91    "177": "NOT_ALIVE",92    "178": "NOT_ALIVE",93    "179": "NOT_ALIVE",94    "18": "NON_PARTICIPATING",95    "180": "FAIL",96    "181": "FAIL",97    "182": "FAIL",98    "183": "FAIL",99    "184": "NON_PARTICIPATING",100    "185": "FAIL",101    "186": "NON_PARTICIPATING",102    "187": "NOT_ALIVE",103    "188": "NON_PARTICIPATING",104    "189": "NON_PARTICIPATING",105    "19": "NON_PARTICIPATING",106    "190": "NON_PARTICIPATING",107    "191": "NOT_ALIVE",108    "192": "NON_PARTICIPATING",109    "193": "NOT_ALIVE",110    "194": "NON_PARTICIPATING",111    "195": "NON_PARTICIPATING",112    "196": "NOT_ALIVE",113    "197": "FAIL",114    "198": "NON_PARTICIPATING",115    "199": "NON_PARTICIPATING",116    "2": "NON_PARTICIPATING",117    "20": "FAIL",118    "200": "NON_PARTICIPATING",119    "201": "NOT_ALIVE",120    "202": "NON_PARTICIPATING",121    "203": "FAIL",122    "204": "NOT_ALIVE",123    "205": "FAIL",124    "206": "FAIL",125    "207": "NOT_ALIVE",126    "208": "NON_PARTICIPATING",127    "209": "FAIL",128    "21": "NOT_ALIVE",129    "210": "NON_PARTICIPATING",130    "211": "FAIL",131    "212": "NON_PARTICIPATING",132    "213": "NON_PARTICIPATING",133    "214": "FAIL",134    "215": "NON_PARTICIPATING",135    "216": "FAIL",136    "217": "FAIL",137    "218": "NON_PARTICIPATING",138    "219": "NOT_ALIVE",139    "22": "NOT_ALIVE",140    "220": "NON_PARTICIPATING",141    "221": "NON_PARTICIPATING",142    "222": "FAIL",143    "223": "FAIL",144    "224": "NOT_ALIVE",145    "225": "FAIL",146    "226": "NON_PARTICIPATING",147    "227": "NOT_ALIVE",148    "228": "FAIL",149    "229": "NOT_ALIVE",150    "23": "NON_PARTICIPATING",151    "230": "NOT_ALIVE",152    "231": "NOT_ALIVE",153    "232": "FAIL",154    "233": "NON_PARTICIPATING",155    "234": "NON_PARTICIPATING",156    "235": "NON_PARTICIPATING",157    "236": "NOT_ALIVE",158    "237": "NON_PARTICIPATING",159    "238": "FAIL",160    "239": "NON_PARTICIPATING",161    "24": "FAIL",162    "240": "NON_PARTICIPATING",163    "241": "FAIL",164    "242": "NOT_ALIVE",165    "243": "NON_PARTICIPATING",166    "244": "NOT_ALIVE",167    "245": "NON_PARTICIPATING",168    "246": "NON_PARTICIPATING",169    "247": "NOT_ALIVE",170    "248": "NOT_ALIVE",171    "249": "NON_PARTICIPATING",172    "25": "SUCCESS",173    "250": "NON_PARTICIPATING",174    "251": "NON_PARTICIPATING",175    "252": "NON_PARTICIPATING",176    "253": "NON_PARTICIPATING",177    "254": "NON_PARTICIPATING",178    "255": "FAIL",179    "26": "NOT_ALIVE",180    "27": "FAIL",181    "28": "NON_PARTICIPATING",182    "29": "NON_PARTICIPATING",183    "3": "NON_PARTICIPATING",184    "30": "NON_PARTICIPATING",185    "31": "NON_PARTICIPATING",186    "32": "NOT_ALIVE",187    "33": "NOT_ALIVE",188    "34": "NON_PARTICIPATING",189    "35": "FAIL",190    "36": "NON_PARTICIPATING",191    "37": "NOT_ALIVE",192    "38": "FAIL",193    "39": "FAIL",194    "4": "FAIL",195    "40": "FAIL",196    "41": "NOT_ALIVE",197    "42": "FAIL",198    "43": "NOT_ALIVE",199    "44": "NON_PARTICIPATING",200    "45": "NOT_ALIVE",201    "46": "FAIL",202    "47": "NON_PARTICIPATING",203    "48": "NON_PARTICIPATING",204    "49": "NON_PARTICIPATING",205    "5": "NOT_ALIVE",206    "50": "NON_PARTICIPATING",207    "51": "FAIL",208    "52": "NON_PARTICIPATING",209    "53": "NON_PARTICIPATING",210    "54": "NOT_ALIVE",211    "55": "FAIL",212    "56": "NON_PARTICIPATING",213    "57": "NON_PARTICIPATING",214    "58": "NOT_ALIVE",215    "59": "NON_PARTICIPATING",216    "6": "NON_PARTICIPATING",217    "60": "NOT_ALIVE",218    "61": "FAIL",219    "62": "NON_PARTICIPATING",220    "63": "NOT_ALIVE",221    "64": "NON_PARTICIPATING",222    "65": "NOT_ALIVE",223    "66": "NON_PARTICIPATING",224    "67": "NON_PARTICIPATING",225    "68": "NON_PARTICIPATING",226    "69": "NOT_ALIVE",227    "7": "NON_PARTICIPATING",228    "70": "NON_PARTICIPATING",229    "71": "NOT_ALIVE",230    "72": "NON_PARTICIPATING",231    "73": "FAIL",232    "74": "FAIL",233    "75": "NON_PARTICIPATING",234    "76": "NON_PARTICIPATING",235    "77": "NOT_ALIVE",236    "78": "NON_PARTICIPATING",237    "79": "NON_PARTICIPATING",238    "8": "NOT_ALIVE",239    "80": "NOT_ALIVE",240    "81": "NOT_ALIVE",241    "82": "NON_PARTICIPATING",242    "83": "NON_PARTICIPATING",243    "84": "NON_PARTICIPATING",244    "85": "NON_PARTICIPATING",245    "86": "NON_PARTICIPATING",246    "87": "FAIL",247    "88": "NON_PARTICIPATING",248    "89": "NOT_ALIVE",249    "9": "NON_PARTICIPATING",250    "90": "NON_PARTICIPATING",251    "91": "NON_PARTICIPATING",252    "92": "FAIL",253    "93": "NON_PARTICIPATING",254    "94": "NON_PARTICIPATING",255    "95": "NOT_ALIVE",256    "96": "NON_PARTICIPATING",257    "97": "FAIL",258    "98": "FAIL",259    "99": "NON_PARTICIPATING"260  },261  "architectures": [262    "LlamaForCausalLM"263  ],264  "attention_bias": false,265  "attention_dropout": 0.0,266  "block_list": [267    6453963,268    6453989269  ],270  "bos_token_id": 1,271  "eos_token_id": 2,272  "hidden_act": "silu",273  "hidden_size": 2048,274  "initializer_range": 0.02,275  "inner_step": 159,276  "intermediate_size": 5632,277  "last_allreduce_block": 6453451,278  "max_position_embeddings": 2048,279  "mlp_bias": false,280  "model_type": "llama",281  "num_attention_heads": 32,282  "num_hidden_layers": 22,283  "num_key_value_heads": 4,284  "pretraining_tp": 1,285  "rms_norm_eps": 1e-05,286  "rope_scaling": null,287  "rope_theta": 10000.0,288  "tie_word_embeddings": false,289  "torch_dtype": "float32",290  "transformers_version": "4.39.3",291  "use_cache": false,292  "vocab_size": 32000293}294