{ "_name_or_path": "distributed/optimized-gpt2-1b", "activation_function": "gelu_new", "all_reduce_scores": { "0": "NON_PARTICIPATING", "1": "SUCCESS", "10": "SUCCESS", "100": "NON_PARTICIPATING", "101": "SUCCESS", "102": "NON_PARTICIPATING", "103": "NON_PARTICIPATING", "104": "SUCCESS", "105": "NON_PARTICIPATING", "106": "NON_PARTICIPATING", "107": "SUCCESS", "108": "NON_PARTICIPATING", "109": "SUCCESS", "11": "SUCCESS", "110": "SUCCESS", "111": "NON_PARTICIPATING", "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": "SUCCESS", "123": "NON_PARTICIPATING", "124": "NON_PARTICIPATING", "125": "SUCCESS", "126": "NON_PARTICIPATING", "127": "NON_PARTICIPATING", "128": "NON_PARTICIPATING", "129": "NON_PARTICIPATING", "13": "NON_PARTICIPATING", "130": "NON_PARTICIPATING", "131": "NON_PARTICIPATING", "132": "SUCCESS", "133": "NON_PARTICIPATING", "134": "SUCCESS", "135": "SUCCESS", "136": "NON_PARTICIPATING", "137": "NON_PARTICIPATING", "138": "NON_PARTICIPATING", "139": "NON_PARTICIPATING", "14": "NON_PARTICIPATING", "140": "NON_PARTICIPATING", "141": "NON_PARTICIPATING", "142": "SUCCESS", "143": "NON_PARTICIPATING", "144": "NON_PARTICIPATING", "145": "NON_PARTICIPATING", "146": "NON_PARTICIPATING", "147": "NON_PARTICIPATING", "148": "SUCCESS", "149": "SUCCESS", "15": "SUCCESS", "150": "NON_PARTICIPATING", "151": "NON_PARTICIPATING", "152": "NON_PARTICIPATING", "153": "NON_PARTICIPATING", "154": "SUCCESS", "155": "NON_PARTICIPATING", "156": "SUCCESS", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "NON_PARTICIPATING", "160": "SUCCESS", "161": "NON_PARTICIPATING", "162": "NON_PARTICIPATING", "163": "NON_PARTICIPATING", "164": "NON_PARTICIPATING", "165": "NON_PARTICIPATING", "166": "NON_PARTICIPATING", "167": "SUCCESS", "168": "NON_PARTICIPATING", "169": "NON_PARTICIPATING", "17": "SUCCESS", "170": "NON_PARTICIPATING", "171": "NON_PARTICIPATING", "172": "SUCCESS", "173": "NON_PARTICIPATING", "174": "NON_PARTICIPATING", "175": "SUCCESS", "176": "NON_PARTICIPATING", "177": "SUCCESS", "178": "SUCCESS", "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": "SUCCESS", "187": "NON_PARTICIPATING", "188": "NON_PARTICIPATING", "189": "NON_PARTICIPATING", "19": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NON_PARTICIPATING", "192": "SUCCESS", "193": "NON_PARTICIPATING", "194": "NON_PARTICIPATING", "195": "SUCCESS", "196": "NON_PARTICIPATING", "197": "NON_PARTICIPATING", "198": "NON_PARTICIPATING", "199": "NON_PARTICIPATING", "2": "SUCCESS", "20": "SUCCESS", "200": "SUCCESS", "201": "NON_PARTICIPATING", "202": "NON_PARTICIPATING", "203": "SUCCESS", "204": "NON_PARTICIPATING", "205": "NON_PARTICIPATING", "206": "SUCCESS", "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": "SUCCESS", "217": "NON_PARTICIPATING", "218": "SUCCESS", "219": "NON_PARTICIPATING", "22": "SUCCESS", "220": "NON_PARTICIPATING", "221": "NON_PARTICIPATING", "222": "SUCCESS", "223": "SUCCESS", "224": "NON_PARTICIPATING", "225": "SUCCESS", "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": "NON_PARTICIPATING", "240": "NON_PARTICIPATING", "241": "NON_PARTICIPATING", "242": "NON_PARTICIPATING", "243": "NON_PARTICIPATING", "244": "NON_PARTICIPATING", "245": "NON_PARTICIPATING", "246": "NON_PARTICIPATING", "247": "SUCCESS", "248": "NON_PARTICIPATING", "249": "SUCCESS", "25": "SUCCESS", "250": "SUCCESS", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "NON_PARTICIPATING", "255": "SUCCESS", "26": "SUCCESS", "27": "SUCCESS", "28": "NON_PARTICIPATING", "29": "NON_PARTICIPATING", "3": "NON_PARTICIPATING", "30": "SUCCESS", "31": "NON_PARTICIPATING", "32": "NON_PARTICIPATING", "33": "NON_PARTICIPATING", "34": "SUCCESS", "35": "NON_PARTICIPATING", "36": "NON_PARTICIPATING", "37": "SUCCESS", "38": "NON_PARTICIPATING", "39": "SUCCESS", "4": "SUCCESS", "40": "SUCCESS", "41": "SUCCESS", "42": "NON_PARTICIPATING", "43": "SUCCESS", "44": "SUCCESS", "45": "SUCCESS", "46": "NON_PARTICIPATING", "47": "NON_PARTICIPATING", "48": "NON_PARTICIPATING", "49": "SUCCESS", "5": "NON_PARTICIPATING", "50": "SUCCESS", "51": "SUCCESS", "52": "NON_PARTICIPATING", "53": "SUCCESS", "54": "NON_PARTICIPATING", "55": "SUCCESS", "56": "SUCCESS", "57": "NON_PARTICIPATING", "58": "SUCCESS", "59": "NON_PARTICIPATING", "6": "SUCCESS", "60": "SUCCESS", "61": "NON_PARTICIPATING", "62": "SUCCESS", "63": "SUCCESS", "64": "NON_PARTICIPATING", "65": "NON_PARTICIPATING", "66": "NON_PARTICIPATING", "67": "SUCCESS", "68": "NON_PARTICIPATING", "69": "NON_PARTICIPATING", "7": "NON_PARTICIPATING", "70": "SUCCESS", "71": "NON_PARTICIPATING", "72": "NON_PARTICIPATING", "73": "NON_PARTICIPATING", "74": "NON_PARTICIPATING", "75": "SUCCESS", "76": "NON_PARTICIPATING", "77": "NON_PARTICIPATING", "78": "SUCCESS", "79": "NON_PARTICIPATING", "8": "NON_PARTICIPATING", "80": "SUCCESS", "81": "NON_PARTICIPATING", "82": "SUCCESS", "83": "NON_PARTICIPATING", "84": "SUCCESS", "85": "SUCCESS", "86": "NON_PARTICIPATING", "87": "SUCCESS", "88": "SUCCESS", "89": "SUCCESS", "9": "NON_PARTICIPATING", "90": "NON_PARTICIPATING", "91": "NON_PARTICIPATING", "92": "NON_PARTICIPATING", "93": "NON_PARTICIPATING", "94": "NON_PARTICIPATING", "95": "SUCCESS", "96": "SUCCESS", "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": [ 5499183, 5499186, 5499188, 5499191, 5499193, 5499196, 5499198, 5499199 ], "block_size": 1024, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "inner_step": 157, "inner_steps": 0, "last_allreduce_block": 5492224, "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 }