{ "_name_or_path": "/tmp/models/tmp__hd8huf/tmper3sy7w0", "activation_function": "gelu_new", "all_reduce_scores": { "0": "NON_PARTICIPATING", "1": "NON_PARTICIPATING", "10": "NON_PARTICIPATING", "100": "NON_PARTICIPATING", "101": "NON_PARTICIPATING", "102": "SUCCESS", "103": "SUCCESS", "104": "NON_PARTICIPATING", "105": "NON_PARTICIPATING", "106": "NON_PARTICIPATING", "107": "NON_PARTICIPATING", "108": "SUCCESS", "109": "NON_PARTICIPATING", "11": "NON_PARTICIPATING", "110": "NON_PARTICIPATING", "111": "SUCCESS", "112": "SUCCESS", "113": "SUCCESS", "114": "SUCCESS", "115": "SUCCESS", "116": "NON_PARTICIPATING", "117": "NON_PARTICIPATING", "118": "SUCCESS", "119": "SUCCESS", "12": "NON_PARTICIPATING", "120": "SUCCESS", "121": "SUCCESS", "122": "NON_PARTICIPATING", "123": "SUCCESS", "124": "NON_PARTICIPATING", "125": "SUCCESS", "126": "SUCCESS", "127": "NON_PARTICIPATING", "128": "SUCCESS", "129": "SUCCESS", "13": "NON_PARTICIPATING", "130": "SUCCESS", "131": "NON_PARTICIPATING", "132": "SUCCESS", "133": "NON_PARTICIPATING", "134": "SUCCESS", "135": "SUCCESS", "136": "NON_PARTICIPATING", "137": "SUCCESS", "138": "NON_PARTICIPATING", "139": "NON_PARTICIPATING", "14": "NON_PARTICIPATING", "140": "NON_PARTICIPATING", "141": "NON_PARTICIPATING", "142": "SUCCESS", "143": "SUCCESS", "144": "SUCCESS", "145": "NON_PARTICIPATING", "146": "NON_PARTICIPATING", "147": "SUCCESS", "148": "NON_PARTICIPATING", "149": "SUCCESS", "15": "NON_PARTICIPATING", "150": "SUCCESS", "151": "SUCCESS", "152": "NON_PARTICIPATING", "153": "SUCCESS", "154": "SUCCESS", "155": "SUCCESS", "156": "NON_PARTICIPATING", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "SUCCESS", "16": "SUCCESS", "160": "NON_PARTICIPATING", "161": "NON_PARTICIPATING", "162": "SUCCESS", "163": "SUCCESS", "164": "SUCCESS", "165": "SUCCESS", "166": "NON_PARTICIPATING", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "NON_PARTICIPATING", "17": "SUCCESS", "170": "SUCCESS", "171": "SUCCESS", "172": "NON_PARTICIPATING", "173": "NON_PARTICIPATING", "174": "SUCCESS", "175": "NON_PARTICIPATING", "176": "NON_PARTICIPATING", "177": "NON_PARTICIPATING", "178": "SUCCESS", "179": "NON_PARTICIPATING", "18": "SUCCESS", "180": "NON_PARTICIPATING", "181": "NON_PARTICIPATING", "182": "NON_PARTICIPATING", "183": "SUCCESS", "184": "NON_PARTICIPATING", "185": "NON_PARTICIPATING", "186": "NON_PARTICIPATING", "187": "SUCCESS", "188": "NON_PARTICIPATING", "189": "NON_PARTICIPATING", "19": "NON_PARTICIPATING", "190": "SUCCESS", "191": "NON_PARTICIPATING", "192": "NON_PARTICIPATING", "193": "SUCCESS", "194": "SUCCESS", "195": "NON_PARTICIPATING", "196": "NON_PARTICIPATING", "197": "SUCCESS", "198": "NON_PARTICIPATING", "199": "NON_PARTICIPATING", "2": "NON_PARTICIPATING", "20": "NON_PARTICIPATING", "200": "SUCCESS", "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": "SUCCESS", "211": "SUCCESS", "212": "SUCCESS", "213": "NON_PARTICIPATING", "214": "NON_PARTICIPATING", "215": "NON_PARTICIPATING", "216": "SUCCESS", "217": "SUCCESS", "218": "SUCCESS", "219": "SUCCESS", "22": "NON_PARTICIPATING", "220": "NON_PARTICIPATING", "221": "NON_PARTICIPATING", "222": "NON_PARTICIPATING", "223": "NON_PARTICIPATING", "224": "NON_PARTICIPATING", "225": "SUCCESS", "226": "NON_PARTICIPATING", "227": "SUCCESS", "228": "NON_PARTICIPATING", "229": "NON_PARTICIPATING", "23": "NON_PARTICIPATING", "230": "SUCCESS", "231": "NON_PARTICIPATING", "232": "NON_PARTICIPATING", "233": "NON_PARTICIPATING", "234": "SUCCESS", "235": "NON_PARTICIPATING", "236": "NON_PARTICIPATING", "237": "NON_PARTICIPATING", "238": "SUCCESS", "239": "NON_PARTICIPATING", "24": "SUCCESS", "240": "NON_PARTICIPATING", "241": "SUCCESS", "242": "NON_PARTICIPATING", "243": "SUCCESS", "244": "SUCCESS", "245": "SUCCESS", "246": "NON_PARTICIPATING", "247": "SUCCESS", "248": "NON_PARTICIPATING", "249": "SUCCESS", "25": "NON_PARTICIPATING", "250": "NON_PARTICIPATING", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "SUCCESS", "255": "NON_PARTICIPATING", "26": "NON_PARTICIPATING", "27": "SUCCESS", "28": "NON_PARTICIPATING", "29": "NON_PARTICIPATING", "3": "NON_PARTICIPATING", "30": "NON_PARTICIPATING", "31": "NON_PARTICIPATING", "32": "SUCCESS", "33": "NON_PARTICIPATING", "34": "NON_PARTICIPATING", "35": "NON_PARTICIPATING", "36": "SUCCESS", "37": "NON_PARTICIPATING", "38": "NON_PARTICIPATING", "39": "NON_PARTICIPATING", "4": "NON_PARTICIPATING", "40": "SUCCESS", "41": "NON_PARTICIPATING", "42": "NON_PARTICIPATING", "43": "NON_PARTICIPATING", "44": "NON_PARTICIPATING", "45": "NON_PARTICIPATING", "46": "NON_PARTICIPATING", "47": "NON_PARTICIPATING", "48": "SUCCESS", "49": "NON_PARTICIPATING", "5": "SUCCESS", "50": "NON_PARTICIPATING", "51": "SUCCESS", "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": "SUCCESS", "61": "SUCCESS", "62": "SUCCESS", "63": "SUCCESS", "64": "SUCCESS", "65": "NON_PARTICIPATING", "66": "NON_PARTICIPATING", "67": "NON_PARTICIPATING", "68": "NON_PARTICIPATING", "69": "NON_PARTICIPATING", "7": "NON_PARTICIPATING", "70": "NON_PARTICIPATING", "71": "SUCCESS", "72": "NON_PARTICIPATING", "73": "NON_PARTICIPATING", "74": "NON_PARTICIPATING", "75": "SUCCESS", "76": "NON_PARTICIPATING", "77": "NON_PARTICIPATING", "78": "SUCCESS", "79": "SUCCESS", "8": "SUCCESS", "80": "SUCCESS", "81": "NON_PARTICIPATING", "82": "NON_PARTICIPATING", "83": "NON_PARTICIPATING", "84": "NON_PARTICIPATING", "85": "NON_PARTICIPATING", "86": "SUCCESS", "87": "NON_PARTICIPATING", "88": "SUCCESS", "89": "NON_PARTICIPATING", "9": "NON_PARTICIPATING", "90": "NON_PARTICIPATING", "91": "SUCCESS", "92": "SUCCESS", "93": "SUCCESS", "94": "SUCCESS", "95": "NON_PARTICIPATING", "96": "NON_PARTICIPATING", "97": "SUCCESS", "98": "NON_PARTICIPATING", "99": "NON_PARTICIPATING" }, "architectures": [ "GPTOptim" ], "attn_pdrop": 0.1, "auto_map": { "AutoConfig": "configuration_gpt_optimized.GPTOptimConfig", "AutoModelForCausalLM": "distributed/optimized-gpt2-2b--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": 1904, "n_head": 34, "n_inner": null, "n_layer": 44, "n_positions": 1024, "quantization_config": { "transformer.h.attn.c_attn": { "offload_meta": false, "scale_quant_params": null, "weight_quant_params": { "axis": 0, "channel_wise": true, "group_size": 64, "nbits": 4, "optimize": true, "round_zero": true, "view_as_float": false }, "zero_quant_params": { "channel_wise": false, "group_size": null, "nbits": 8, "optimize": false } }, "transformer.h.attn.c_proj": { "offload_meta": false, "scale_quant_params": null, "weight_quant_params": { "axis": 0, "channel_wise": true, "group_size": 64, "nbits": 4, "optimize": true, "round_zero": true, "view_as_float": false }, "zero_quant_params": { "channel_wise": false, "group_size": null, "nbits": 8, "optimize": false } }, "transformer.h.mlp.c_fc": { "offload_meta": false, "scale_quant_params": null, "weight_quant_params": { "axis": 0, "channel_wise": true, "group_size": 64, "nbits": 4, "optimize": true, "round_zero": true, "view_as_float": false }, "zero_quant_params": { "channel_wise": false, "group_size": null, "nbits": 8, "optimize": false } }, "transformer.h.mlp.c_proj": { "offload_meta": false, "scale_quant_params": null, "weight_quant_params": { "axis": 0, "channel_wise": true, "group_size": 64, "nbits": 4, "optimize": true, "round_zero": true, "view_as_float": false }, "zero_quant_params": { "channel_wise": false, "group_size": null, "nbits": 8, "optimize": false } } }, "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": "4.44.0", "use_cache": true, "vocab_size": 50257 }