config.json

{
  "_name_or_path": "distributed/optimized-gpt2-1b",
  "activation_function": "gelu_new",
  "all_reduce_scores": {
    "0": "NON_PARTICIPATING",
    "1": "NON_PARTICIPATING",
    "10": "NON_PARTICIPATING",
    "100": "NON_PARTICIPATING",
    "101": "SUCCESS",
    "102": "NON_PARTICIPATING",
    "103": "NON_PARTICIPATING",
    "104": "NON_PARTICIPATING",
    "105": "NON_PARTICIPATING",
    "106": "NON_PARTICIPATING",
    "107": "SUCCESS",
    "108": "NON_PARTICIPATING",
    "109": "NON_PARTICIPATING",
    "11": "NON_PARTICIPATING",
    "110": "NON_PARTICIPATING",
    "111": "SUCCESS",
    "112": "NON_PARTICIPATING",
    "113": "NON_PARTICIPATING",
    "114": "NON_PARTICIPATING",
    "115": "NON_PARTICIPATING",
    "116": "SUCCESS",
    "117": "NON_PARTICIPATING",
    "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": "NON_PARTICIPATING",
    "130": "NON_PARTICIPATING",
    "131": "NON_PARTICIPATING",
    "132": "NON_PARTICIPATING",
    "133": "NON_PARTICIPATING",
    "134": "NON_PARTICIPATING",
    "135": "NON_PARTICIPATING",
    "136": "NON_PARTICIPATING",
    "137": "SUCCESS",
    "138": "NON_PARTICIPATING",
    "139": "NON_PARTICIPATING",
    "14": "NON_PARTICIPATING",
    "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": "NON_PARTICIPATING",
    "150": "SUCCESS",
    "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": "NON_PARTICIPATING",
    "160": "NON_PARTICIPATING",
    "161": "NON_PARTICIPATING",
    "162": "NON_PARTICIPATING",
    "163": "SUCCESS",
    "164": "NON_PARTICIPATING",
    "165": "NON_PARTICIPATING",
    "166": "NON_PARTICIPATING",
    "167": "SUCCESS",
    "168": "NON_PARTICIPATING",
    "169": "NON_PARTICIPATING",
    "17": "NON_PARTICIPATING",
    "170": "NON_PARTICIPATING",
    "171": "NON_PARTICIPATING",
    "172": "NON_PARTICIPATING",
    "173": "NON_PARTICIPATING",
    "174": "SUCCESS",
    "175": "SUCCESS",
    "176": "SUCCESS",
    "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": "SUCCESS",
    "185": "NON_PARTICIPATING",
    "186": "SUCCESS",
    "187": "NON_PARTICIPATING",
    "188": "NON_PARTICIPATING",
    "189": "NON_PARTICIPATING",
    "19": "NON_PARTICIPATING",
    "190": "NON_PARTICIPATING",
    "191": "NON_PARTICIPATING",
    "192": "NON_PARTICIPATING",
    "193": "SUCCESS",
    "194": "NON_PARTICIPATING",
    "195": "NON_PARTICIPATING",
    "196": "SUCCESS",
    "197": "NON_PARTICIPATING",
    "198": "NON_PARTICIPATING",
    "199": "NON_PARTICIPATING",
    "2": "NON_PARTICIPATING",
    "20": "NON_PARTICIPATING",
    "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": "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": "NON_PARTICIPATING",
    "219": "NON_PARTICIPATING",
    "22": "NON_PARTICIPATING",
    "220": "NON_PARTICIPATING",
    "221": "SUCCESS",
    "222": "NON_PARTICIPATING",
    "223": "NON_PARTICIPATING",
    "224": "NON_PARTICIPATING",
    "225": "NON_PARTICIPATING",
    "226": "SUCCESS",
    "227": "NON_PARTICIPATING",
    "228": "NON_PARTICIPATING",
    "229": "NON_PARTICIPATING",
    "23": "SUCCESS",
    "230": "SUCCESS",
    "231": "NON_PARTICIPATING",
    "232": "NON_PARTICIPATING",
    "233": "NON_PARTICIPATING",
    "234": "NON_PARTICIPATING",
    "235": "NON_PARTICIPATING",
    "236": "SUCCESS",
    "237": "NON_PARTICIPATING",
    "238": "SUCCESS",
    "239": "NON_PARTICIPATING",
    "24": "NON_PARTICIPATING",
    "240": "NON_PARTICIPATING",
    "241": "NON_PARTICIPATING",
    "242": "SUCCESS",
    "243": "NON_PARTICIPATING",
    "244": "SUCCESS",
    "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": "SUCCESS",
    "32": "SUCCESS",
    "33": "NON_PARTICIPATING",
    "34": "SUCCESS",
    "35": "NON_PARTICIPATING",
    "36": "NON_PARTICIPATING",
    "37": "NON_PARTICIPATING",
    "38": "NON_PARTICIPATING",
    "39": "SUCCESS",
    "4": "NON_PARTICIPATING",
    "40": "NON_PARTICIPATING",
    "41": "NON_PARTICIPATING",
    "42": "NON_PARTICIPATING",
    "43": "NON_PARTICIPATING",
    "44": "SUCCESS",
    "45": "NON_PARTICIPATING",
    "46": "NON_PARTICIPATING",
    "47": "NON_PARTICIPATING",
    "48": "NON_PARTICIPATING",
    "49": "NON_PARTICIPATING",
    "5": "NON_PARTICIPATING",
    "50": "NON_PARTICIPATING",
    "51": "NON_PARTICIPATING",
    "52": "NON_PARTICIPATING",
    "53": "NON_PARTICIPATING",
    "54": "NON_PARTICIPATING",
    "55": "SUCCESS",
    "56": "NON_PARTICIPATING",
    "57": "NON_PARTICIPATING",
    "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": "NON_PARTICIPATING",
    "66": "NON_PARTICIPATING",
    "67": "NON_PARTICIPATING",
    "68": "NON_PARTICIPATING",
    "69": "NON_PARTICIPATING",
    "7": "NON_PARTICIPATING",
    "70": "NON_PARTICIPATING",
    "71": "NON_PARTICIPATING",
    "72": "NON_PARTICIPATING",
    "73": "SUCCESS",
    "74": "NON_PARTICIPATING",
    "75": "NON_PARTICIPATING",
    "76": "NON_PARTICIPATING",
    "77": "NON_PARTICIPATING",
    "78": "NON_PARTICIPATING",
    "79": "SUCCESS",
    "8": "NON_PARTICIPATING",
    "80": "NON_PARTICIPATING",
    "81": "NON_PARTICIPATING",
    "82": "NON_PARTICIPATING",
    "83": "SUCCESS",
    "84": "NON_PARTICIPATING",
    "85": "NON_PARTICIPATING",
    "86": "NON_PARTICIPATING",
    "87": "NON_PARTICIPATING",
    "88": "NON_PARTICIPATING",
    "89": "NON_PARTICIPATING",
    "9": "NON_PARTICIPATING",
    "90": "SUCCESS",
    "91": "NON_PARTICIPATING",
    "92": "NON_PARTICIPATING",
    "93": "SUCCESS",
    "94": "NON_PARTICIPATING",
    "95": "NON_PARTICIPATING",
    "96": "NON_PARTICIPATING",
    "97": "NON_PARTICIPATING",
    "98": "NON_PARTICIPATING",
    "99": "NON_PARTICIPATING"
  },
  "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_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
}