{ "_name_or_path": "distributed/llama-1b", "all_reduce_scores": { "0": "NON_PARTICIPATING", "1": "SUCCESS", "10": "NON_PARTICIPATING", "100": "NON_PARTICIPATING", "101": "NON_PARTICIPATING", "102": "NON_PARTICIPATING", "103": "NON_PARTICIPATING", "104": "NON_PARTICIPATING", "105": "NON_PARTICIPATING", "106": "NON_PARTICIPATING", "107": "NON_PARTICIPATING", "108": "NON_PARTICIPATING", "109": "NON_PARTICIPATING", "11": "SUCCESS", "110": "NON_PARTICIPATING", "111": "SUCCESS", "112": "NON_PARTICIPATING", "113": "NON_PARTICIPATING", "114": "NON_PARTICIPATING", "115": "NON_PARTICIPATING", "116": "NON_PARTICIPATING", "117": "SUCCESS", "118": "NON_PARTICIPATING", "119": "NON_PARTICIPATING", "12": "SUCCESS", "120": "NON_PARTICIPATING", "121": "NON_PARTICIPATING", "122": "NON_PARTICIPATING", "123": "NON_PARTICIPATING", "124": "NON_PARTICIPATING", "125": "NON_PARTICIPATING", "126": "NON_PARTICIPATING", "127": "NON_PARTICIPATING", "128": "NON_PARTICIPATING", "129": "NON_PARTICIPATING", "13": "SUCCESS", "130": "NON_PARTICIPATING", "131": "NON_PARTICIPATING", "132": "NON_PARTICIPATING", "133": "NON_PARTICIPATING", "134": "NON_PARTICIPATING", "135": "NON_PARTICIPATING", "136": "NON_PARTICIPATING", "137": "NON_PARTICIPATING", "138": "NON_PARTICIPATING", "139": "NON_PARTICIPATING", "14": "SUCCESS", "140": "NON_PARTICIPATING", "141": "NON_PARTICIPATING", "142": "NON_PARTICIPATING", "143": "NON_PARTICIPATING", "144": "NON_PARTICIPATING", "145": "NON_PARTICIPATING", "146": "NON_PARTICIPATING", "147": "NON_PARTICIPATING", "148": "NON_PARTICIPATING", "149": "NON_PARTICIPATING", "15": "SUCCESS", "150": "NON_PARTICIPATING", "151": "NON_PARTICIPATING", "152": "NON_PARTICIPATING", "153": "NON_PARTICIPATING", "154": "NON_PARTICIPATING", "155": "NON_PARTICIPATING", "156": "NON_PARTICIPATING", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "SUCCESS", "160": "NON_PARTICIPATING", "161": "SUCCESS", "162": "NON_PARTICIPATING", "163": "NON_PARTICIPATING", "164": "NON_PARTICIPATING", "165": "NON_PARTICIPATING", "166": "NON_PARTICIPATING", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "NON_PARTICIPATING", "17": "SUCCESS", "170": "NON_PARTICIPATING", "171": "NON_PARTICIPATING", "172": "NON_PARTICIPATING", "173": "NON_PARTICIPATING", "174": "NON_PARTICIPATING", "175": "NON_PARTICIPATING", "176": "NON_PARTICIPATING", "177": "NON_PARTICIPATING", "178": "NON_PARTICIPATING", "179": "NON_PARTICIPATING", "18": "SUCCESS", "180": "NON_PARTICIPATING", "181": "SUCCESS", "182": "NON_PARTICIPATING", "183": "NON_PARTICIPATING", "184": "NON_PARTICIPATING", "185": "NON_PARTICIPATING", "186": "NON_PARTICIPATING", "187": "NON_PARTICIPATING", "188": "NON_PARTICIPATING", "189": "NON_PARTICIPATING", "19": "SUCCESS", "190": "NON_PARTICIPATING", "191": "SUCCESS", "192": "NON_PARTICIPATING", "193": "NON_PARTICIPATING", "194": "NON_PARTICIPATING", "195": "NON_PARTICIPATING", "196": "NON_PARTICIPATING", "197": "NON_PARTICIPATING", "198": "NON_PARTICIPATING", "199": "NON_PARTICIPATING", "2": "SUCCESS", "20": "SUCCESS", "200": "NON_PARTICIPATING", "201": "NON_PARTICIPATING", "202": "NON_PARTICIPATING", "203": "NON_PARTICIPATING", "204": "NON_PARTICIPATING", "205": "NON_PARTICIPATING", "206": "NON_PARTICIPATING", "207": "NON_PARTICIPATING", "208": "NON_PARTICIPATING", "209": "NON_PARTICIPATING", "21": "SUCCESS", "210": "NON_PARTICIPATING", "211": "NON_PARTICIPATING", "212": "SUCCESS", "213": "NON_PARTICIPATING", "214": "NON_PARTICIPATING", "215": "NON_PARTICIPATING", "216": "NON_PARTICIPATING", "217": "NON_PARTICIPATING", "218": "NON_PARTICIPATING", "219": "SUCCESS", "22": "SUCCESS", "220": "NON_PARTICIPATING", "221": "NON_PARTICIPATING", "222": "NON_PARTICIPATING", "223": "NON_PARTICIPATING", "224": "NON_PARTICIPATING", "225": "NON_PARTICIPATING", "226": "NON_PARTICIPATING", "227": "NON_PARTICIPATING", "228": "NON_PARTICIPATING", "229": "NON_PARTICIPATING", "23": "SUCCESS", "230": "NON_PARTICIPATING", "231": "NON_PARTICIPATING", "232": "NON_PARTICIPATING", "233": "NON_PARTICIPATING", "234": "NON_PARTICIPATING", "235": "NON_PARTICIPATING", "236": "NON_PARTICIPATING", "237": "NON_PARTICIPATING", "238": "NON_PARTICIPATING", "239": "NON_PARTICIPATING", "24": "SUCCESS", "240": "NON_PARTICIPATING", "241": "NON_PARTICIPATING", "242": "NON_PARTICIPATING", "243": "NON_PARTICIPATING", "244": "NON_PARTICIPATING", "245": "NON_PARTICIPATING", "246": "NON_PARTICIPATING", "247": "NON_PARTICIPATING", "248": "NON_PARTICIPATING", "249": "SUCCESS", "25": "SUCCESS", "250": "NON_PARTICIPATING", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "NON_PARTICIPATING", "255": "NON_PARTICIPATING", "26": "NON_PARTICIPATING", "27": "SUCCESS", "28": "SUCCESS", "29": "SUCCESS", "3": "SUCCESS", "30": "SUCCESS", "31": "SUCCESS", "32": "SUCCESS", "33": "NON_PARTICIPATING", "34": "SUCCESS", "35": "SUCCESS", "36": "SUCCESS", "37": "SUCCESS", "38": "SUCCESS", "39": "SUCCESS", "4": "SUCCESS", "40": "SUCCESS", "41": "SUCCESS", "42": "SUCCESS", "43": "SUCCESS", "44": "SUCCESS", "45": "SUCCESS", "46": "SUCCESS", "47": "SUCCESS", "48": "NON_PARTICIPATING", "49": "SUCCESS", "5": "SUCCESS", "50": "SUCCESS", "51": "SUCCESS", "52": "NON_PARTICIPATING", "53": "SUCCESS", "54": "SUCCESS", "55": "SUCCESS", "56": "SUCCESS", "57": "SUCCESS", "58": "NON_PARTICIPATING", "59": "SUCCESS", "6": "SUCCESS", "60": "SUCCESS", "61": "SUCCESS", "62": "SUCCESS", "63": "SUCCESS", "64": "SUCCESS", "65": "SUCCESS", "66": "SUCCESS", "67": "SUCCESS", "68": "SUCCESS", "69": "SUCCESS", "7": "SUCCESS", "70": "SUCCESS", "71": "SUCCESS", "72": "SUCCESS", "73": "SUCCESS", "74": "SUCCESS", "75": "SUCCESS", "76": "SUCCESS", "77": "SUCCESS", "78": "SUCCESS", "79": "SUCCESS", "8": "SUCCESS", "80": "SUCCESS", "81": "SUCCESS", "82": "SUCCESS", "83": "SUCCESS", "84": "SUCCESS", "85": "SUCCESS", "86": "SUCCESS", "87": "SUCCESS", "88": "SUCCESS", "89": "SUCCESS", "9": "NON_PARTICIPATING", "90": "SUCCESS", "91": "SUCCESS", "92": "SUCCESS", "93": "SUCCESS", "94": "SUCCESS", "95": "SUCCESS", "96": "SUCCESS", "97": "SUCCESS", "98": "SUCCESS", "99": "SUCCESS" }, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "block_list": [ 5720437, 5720569 ], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "inner_step": 14, "intermediate_size": 5632, "last_allreduce_block": 5718662, "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 }