{ "_name_or_path": "distributed/optimized-gpt2-1b-vtestnet-v1", "activation_function": "gelu_new", "all_reduce_scores": { "0": "NON_PARTICIPATING", "1": "NON_PARTICIPATING", "10": "NON_PARTICIPATING", "100": "NON_PARTICIPATING", "101": "NON_PARTICIPATING", "102": "NON_PARTICIPATING", "103": "NON_PARTICIPATING", "104": "NON_PARTICIPATING", "105": "SUCCESS", "106": "NON_PARTICIPATING", "107": "NON_PARTICIPATING", "108": "NON_PARTICIPATING", "109": "NON_PARTICIPATING", "11": "NON_PARTICIPATING", "110": "NON_PARTICIPATING", "111": "NON_PARTICIPATING", "112": "NON_PARTICIPATING", "113": "NON_PARTICIPATING", "114": "NON_PARTICIPATING", "115": "SUCCESS", "116": "NON_PARTICIPATING", "117": "NON_PARTICIPATING", "118": "NON_PARTICIPATING", "119": "NON_PARTICIPATING", "12": "NON_PARTICIPATING", "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": "NON_PARTICIPATING", "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": "SUCCESS", "14": "NON_PARTICIPATING", "140": "NON_PARTICIPATING", "141": "NON_PARTICIPATING", "142": "NON_PARTICIPATING", "143": "NON_PARTICIPATING", "144": "NON_PARTICIPATING", "145": "NON_PARTICIPATING", "146": "SUCCESS", "147": "NON_PARTICIPATING", "148": "NON_PARTICIPATING", "149": "NON_PARTICIPATING", "15": "SUCCESS", "150": "NON_PARTICIPATING", "151": "NON_PARTICIPATING", "152": "NON_PARTICIPATING", "153": "SUCCESS", "154": "NON_PARTICIPATING", "155": "SUCCESS", "156": "NON_PARTICIPATING", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "SUCCESS", "160": "NON_PARTICIPATING", "161": "NON_PARTICIPATING", "162": "NON_PARTICIPATING", "163": "NON_PARTICIPATING", "164": "NON_PARTICIPATING", "165": "NON_PARTICIPATING", "166": "SUCCESS", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "SUCCESS", "17": "NON_PARTICIPATING", "170": "NON_PARTICIPATING", "171": "SUCCESS", "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": "NON_PARTICIPATING", "180": "NON_PARTICIPATING", "181": "NON_PARTICIPATING", "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": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NON_PARTICIPATING", "192": "NON_PARTICIPATING", "193": "NON_PARTICIPATING", "194": "NON_PARTICIPATING", "195": "NON_PARTICIPATING", "196": "NON_PARTICIPATING", "197": "SUCCESS", "198": "NON_PARTICIPATING", "199": "NON_PARTICIPATING", "2": "NON_PARTICIPATING", "20": "NON_PARTICIPATING", "200": "NON_PARTICIPATING", "201": "NON_PARTICIPATING", "202": "NON_PARTICIPATING", "203": "SUCCESS", "204": "NON_PARTICIPATING", "205": "NON_PARTICIPATING", "206": "NON_PARTICIPATING", "207": "NON_PARTICIPATING", "208": "NON_PARTICIPATING", "209": "NON_PARTICIPATING", "21": "NON_PARTICIPATING", "210": "NON_PARTICIPATING", "211": "NON_PARTICIPATING", "212": "NON_PARTICIPATING", "213": "NON_PARTICIPATING", "214": "NON_PARTICIPATING", "215": "NON_PARTICIPATING", "216": "NON_PARTICIPATING", "217": "NON_PARTICIPATING", "218": "SUCCESS", "219": "NON_PARTICIPATING", "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": "NON_PARTICIPATING", "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": "NON_PARTICIPATING", "240": "NON_PARTICIPATING", "241": "SUCCESS", "242": "NON_PARTICIPATING", "243": "NON_PARTICIPATING", "244": "NON_PARTICIPATING", "245": "NON_PARTICIPATING", "246": "NON_PARTICIPATING", "247": "NON_PARTICIPATING", "248": "NON_PARTICIPATING", "249": "NON_PARTICIPATING", "25": "SUCCESS", "250": "NON_PARTICIPATING", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "NON_PARTICIPATING", "255": "NON_PARTICIPATING", "26": "NON_PARTICIPATING", "27": "NON_PARTICIPATING", "28": "NON_PARTICIPATING", "29": "NON_PARTICIPATING", "3": "NON_PARTICIPATING", "30": "NON_PARTICIPATING", "31": "NON_PARTICIPATING", "32": "NON_PARTICIPATING", "33": "NON_PARTICIPATING", "34": "NON_PARTICIPATING", "35": "NON_PARTICIPATING", "36": "NON_PARTICIPATING", "37": "SUCCESS", "38": "NON_PARTICIPATING", "39": "SUCCESS", "4": "SUCCESS", "40": "NON_PARTICIPATING", "41": "NON_PARTICIPATING", "42": "NON_PARTICIPATING", "43": "NON_PARTICIPATING", "44": "NON_PARTICIPATING", "45": "NON_PARTICIPATING", "46": "NON_PARTICIPATING", "47": "NON_PARTICIPATING", "48": "NON_PARTICIPATING", "49": "NON_PARTICIPATING", "5": "NON_PARTICIPATING", "50": "SUCCESS", "51": "NON_PARTICIPATING", "52": "NON_PARTICIPATING", "53": "NON_PARTICIPATING", "54": "NON_PARTICIPATING", "55": "NON_PARTICIPATING", "56": "NON_PARTICIPATING", "57": "SUCCESS", "58": "NON_PARTICIPATING", "59": "NON_PARTICIPATING", "6": "NON_PARTICIPATING", "60": "NON_PARTICIPATING", "61": "NON_PARTICIPATING", "62": "NON_PARTICIPATING", "63": "NON_PARTICIPATING", "64": "NON_PARTICIPATING", "65": "SUCCESS", "66": "NON_PARTICIPATING", "67": "NON_PARTICIPATING", "68": "SUCCESS", "69": "NON_PARTICIPATING", "7": "NON_PARTICIPATING", "70": "NON_PARTICIPATING", "71": "NON_PARTICIPATING", "72": "SUCCESS", "73": "SUCCESS", "74": "NON_PARTICIPATING", "75": "NON_PARTICIPATING", "76": "SUCCESS", "77": "NON_PARTICIPATING", "78": "NON_PARTICIPATING", "79": "NON_PARTICIPATING", "8": "NON_PARTICIPATING", "80": "SUCCESS", "81": "NON_PARTICIPATING", "82": "NON_PARTICIPATING", "83": "NON_PARTICIPATING", "84": "NON_PARTICIPATING", "85": "NON_PARTICIPATING", "86": "NON_PARTICIPATING", "87": "NON_PARTICIPATING", "88": "NON_PARTICIPATING", "89": "NON_PARTICIPATING", "9": "NON_PARTICIPATING", "90": "NON_PARTICIPATING", "91": "SUCCESS", "92": "NON_PARTICIPATING", "93": "NON_PARTICIPATING", "94": "NON_PARTICIPATING", "95": "NON_PARTICIPATING", "96": "NON_PARTICIPATING", "97": "NON_PARTICIPATING", "98": "NON_PARTICIPATING", "99": "SUCCESS" }, "architectures": [ "GPTOptim" ], "attn_pdrop": 0.1, "auto_map": { "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig", "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim" }, "block_list": [ 3850188, 3850196, 3850203, 3850220, 3850227, 3850241, 3850248, 3850259, 3850265, 3850272, 3850283, 3850289, 3850299, 3850312, 3850320, 3850326, 3850333, 3850341, 3850346, 3850352, 3850356, 3850369, 3850375, 3850383, 3850389, 3850397, 3850404, 3850410, 3850416, 3850423, 3850429, 3850435, 3850442, 3850451, 3850459, 3850466, 3850472, 3850483, 3850490, 3850497, 3850503, 3850509, 3850515, 3850525, 3850528, 3850537, 3850544, 3850552, 3850557, 3850563, 3850573, 3850584, 3850593, 3850599, 3850606, 3850613, 3850622, 3850629, 3850636, 3850644, 3850662, 3850669, 3850676, 3850682, 3850687, 3850698, 3850705, 3850711, 3850716, 3850722, 3850728, 3850735, 3850740, 3850747, 3850762, 3850768, 3850780, 3850784, 3850792, 3850799, 3850807, 3850825, 3850839, 3850844, 3850850, 3850858, 3850863, 3850868, 3850873, 3850878, 3850884, 3850894, 3850902, 3850908, 3850915, 3850919, 3850924, 3850931, 3850938, 3850946, 3850952, 3850961, 3850967, 3850976, 3850982, 3850988, 3850997, 3851003, 3851009, 3851017, 3851021, 3851027, 3851033, 3851047, 3851053, 3851059, 3851064, 3851071, 3851076, 3851083, 3851094, 3851118, 3851127, 3851133, 3851139, 3851148, 3851154, 3851159, 3851167, 3851172, 3851179, 3851186, 3851194, 3851201, 3851207, 3851212, 3851220, 3851231, 3851239, 3851245, 3851259, 3851265, 3851275, 3851281, 3851288, 3851294, 3851300, 3851307, 3851318, 3851322, 3851328, 3851332, 3851338, 3851343, 3851348, 3851356, 3851361, 3851367, 3851374, 3851389, 3851403, 3851409, 3851417, 3851423, 3851432, 3851438, 3851444, 3851450, 3851466, 3851471, 3851478, 3851483, 3851488, 3851493, 3851499, 3851506, 3851512, 3851519, 3851545, 3851552, 3851557, 3851562, 3851569, 3851575, 3851580, 3851585, 3851596, 3851613, 3851617, 3851623, 3851630, 3851634, 3851640, 3851644, 3851654, 3851659, 3851667, 3851674, 3851681, 3851686, 3851697, 3851704, 3851710, 3851715, 3851721, 3851727, 3851733, 3851739 ], "block_size": 1024, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt_optimized", "n_embd": 1280, "n_head": 32, "n_inner": null, "n_layer": 48, "n_positions": 1024, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "torch_dtype": "float32", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 50257 }