{ "_name_or_path": "distributed/llama-1b", "all_reduce_scores": { "0": "NOT_ALIVE", "1": "FAIL", "10": "NON_PARTICIPATING", "100": "NOT_ALIVE", "101": "NOT_ALIVE", "102": "NOT_ALIVE", "103": "FAIL", "104": "NON_PARTICIPATING", "105": "FAIL", "106": "FAIL", "107": "NON_PARTICIPATING", "108": "NOT_ALIVE", "109": "FAIL", "11": "FAIL", "110": "NOT_ALIVE", "111": "FAIL", "112": "NOT_ALIVE", "113": "NON_PARTICIPATING", "114": "FAIL", "115": "NOT_ALIVE", "116": "FAIL", "117": "NOT_ALIVE", "118": "NON_PARTICIPATING", "119": "FAIL", "12": "NOT_ALIVE", "120": "NOT_ALIVE", "121": "NOT_ALIVE", "122": "NON_PARTICIPATING", "123": "NON_PARTICIPATING", "124": "NON_PARTICIPATING", "125": "NON_PARTICIPATING", "126": "NON_PARTICIPATING", "127": "FAIL", "128": "FAIL", "129": "NOT_ALIVE", "13": "NON_PARTICIPATING", "130": "NON_PARTICIPATING", "131": "NOT_ALIVE", "132": "NON_PARTICIPATING", "133": "NOT_ALIVE", "134": "NON_PARTICIPATING", "135": "NON_PARTICIPATING", "136": "NOT_ALIVE", "137": "NOT_ALIVE", "138": "NOT_ALIVE", "139": "NOT_ALIVE", "14": "NOT_ALIVE", "140": "NOT_ALIVE", "141": "NOT_ALIVE", "142": "NOT_ALIVE", "143": "FAIL", "144": "NOT_ALIVE", "145": "NOT_ALIVE", "146": "FAIL", "147": "NON_PARTICIPATING", "148": "NON_PARTICIPATING", "149": "NON_PARTICIPATING", "15": "NOT_ALIVE", "150": "FAIL", "151": "NOT_ALIVE", "152": "NOT_ALIVE", "153": "NON_PARTICIPATING", "154": "NOT_ALIVE", "155": "NOT_ALIVE", "156": "FAIL", "157": "FAIL", "158": "NON_PARTICIPATING", "159": "NOT_ALIVE", "16": "FAIL", "160": "NOT_ALIVE", "161": "NOT_ALIVE", "162": "NON_PARTICIPATING", "163": "FAIL", "164": "NOT_ALIVE", "165": "NON_PARTICIPATING", "166": "FAIL", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "FAIL", "17": "NON_PARTICIPATING", "170": "NON_PARTICIPATING", "171": "NOT_ALIVE", "172": "NON_PARTICIPATING", "173": "FAIL", "174": "NOT_ALIVE", "175": "FAIL", "176": "NOT_ALIVE", "177": "NON_PARTICIPATING", "178": "NOT_ALIVE", "179": "NOT_ALIVE", "18": "NOT_ALIVE", "180": "NON_PARTICIPATING", "181": "NON_PARTICIPATING", "182": "FAIL", "183": "NOT_ALIVE", "184": "NON_PARTICIPATING", "185": "NOT_ALIVE", "186": "NON_PARTICIPATING", "187": "NOT_ALIVE", "188": "FAIL", "189": "NON_PARTICIPATING", "19": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NON_PARTICIPATING", "192": "NON_PARTICIPATING", "193": "NON_PARTICIPATING", "194": "NOT_ALIVE", "195": "FAIL", "196": "NON_PARTICIPATING", "197": "NOT_ALIVE", "198": "NOT_ALIVE", "199": "NOT_ALIVE", "2": "NON_PARTICIPATING", "20": "NON_PARTICIPATING", "200": "NON_PARTICIPATING", "201": "NON_PARTICIPATING", "202": "NON_PARTICIPATING", "203": "NOT_ALIVE", "204": "NOT_ALIVE", "205": "FAIL", "206": "NOT_ALIVE", "207": "NOT_ALIVE", "208": "NOT_ALIVE", "209": "FAIL", "21": "NON_PARTICIPATING", "210": "NOT_ALIVE", "211": "FAIL", "212": "FAIL", "213": "NOT_ALIVE", "214": "NON_PARTICIPATING", "215": "NOT_ALIVE", "216": "NON_PARTICIPATING", "217": "NON_PARTICIPATING", "218": "NOT_ALIVE", "219": "FAIL", "22": "NOT_ALIVE", "220": "NON_PARTICIPATING", "221": "FAIL", "222": "NON_PARTICIPATING", "223": "NON_PARTICIPATING", "224": "NOT_ALIVE", "225": "NON_PARTICIPATING", "226": "NON_PARTICIPATING", "227": "NON_PARTICIPATING", "228": "NON_PARTICIPATING", "229": "NOT_ALIVE", "23": "NON_PARTICIPATING", "230": "NOT_ALIVE", "231": "NOT_ALIVE", "232": "NON_PARTICIPATING", "233": "NON_PARTICIPATING", "234": "NON_PARTICIPATING", "235": "FAIL", "236": "NOT_ALIVE", "237": "NOT_ALIVE", "238": "FAIL", "239": "NON_PARTICIPATING", "24": "NOT_ALIVE", "240": "NOT_ALIVE", "241": "FAIL", "242": "NOT_ALIVE", "243": "NOT_ALIVE", "244": "NOT_ALIVE", "245": "NON_PARTICIPATING", "246": "NON_PARTICIPATING", "247": "NON_PARTICIPATING", "248": "NOT_ALIVE", "249": "NOT_ALIVE", "25": "SUCCESS", "250": "NON_PARTICIPATING", "251": "NOT_ALIVE", "252": "FAIL", "253": "FAIL", "254": "NON_PARTICIPATING", "255": "NOT_ALIVE", "26": "FAIL", "27": "NOT_ALIVE", "28": "FAIL", "29": "FAIL", "3": "NON_PARTICIPATING", "30": "NOT_ALIVE", "31": "FAIL", "32": "NOT_ALIVE", "33": "NOT_ALIVE", "34": "NOT_ALIVE", "35": "NON_PARTICIPATING", "36": "NOT_ALIVE", "37": "NOT_ALIVE", "38": "NON_PARTICIPATING", "39": "NON_PARTICIPATING", "4": "FAIL", "40": "FAIL", "41": "NOT_ALIVE", "42": "NON_PARTICIPATING", "43": "NON_PARTICIPATING", "44": "NON_PARTICIPATING", "45": "NOT_ALIVE", "46": "NOT_ALIVE", "47": "FAIL", "48": "NON_PARTICIPATING", "49": "NOT_ALIVE", "5": "NON_PARTICIPATING", "50": "NON_PARTICIPATING", "51": "FAIL", "52": "NON_PARTICIPATING", "53": "NON_PARTICIPATING", "54": "NOT_ALIVE", "55": "NOT_ALIVE", "56": "NOT_ALIVE", "57": "FAIL", "58": "NON_PARTICIPATING", "59": "NOT_ALIVE", "6": "NOT_ALIVE", "60": "NON_PARTICIPATING", "61": "NOT_ALIVE", "62": "NON_PARTICIPATING", "63": "NON_PARTICIPATING", "64": "NOT_ALIVE", "65": "NOT_ALIVE", "66": "NON_PARTICIPATING", "67": "NON_PARTICIPATING", "68": "NOT_ALIVE", "69": "FAIL", "7": "NON_PARTICIPATING", "70": "FAIL", "71": "NOT_ALIVE", "72": "NON_PARTICIPATING", "73": "NOT_ALIVE", "74": "FAIL", "75": "NOT_ALIVE", "76": "NON_PARTICIPATING", "77": "NOT_ALIVE", "78": "FAIL", "79": "NON_PARTICIPATING", "8": "NON_PARTICIPATING", "80": "FAIL", "81": "NOT_ALIVE", "82": "NOT_ALIVE", "83": "NON_PARTICIPATING", "84": "NOT_ALIVE", "85": "FAIL", "86": "NON_PARTICIPATING", "87": "NOT_ALIVE", "88": "NON_PARTICIPATING", "89": "FAIL", "9": "FAIL", "90": "FAIL", "91": "FAIL", "92": "NON_PARTICIPATING", "93": "NOT_ALIVE", "94": "NON_PARTICIPATING", "95": "NOT_ALIVE", "96": "NOT_ALIVE", "97": "NON_PARTICIPATING", "98": "FAIL", "99": "NOT_ALIVE" }, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "block_list": [ 6462470, 6462489 ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "inner_step": 82, "intermediate_size": 5632, "last_allreduce_block": 6462120, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.39.3", "use_cache": false, "vocab_size": 32000 }