Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-100/added_tokens.json

@@ -0,0 +1,1437 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|)_py -> _ter |>": 152154,
+  "<|]_py -> _ter |>": 151928,
+  "<|alias_py -> as_pattern_target_py |>": 151965,
+  "<|alias_py -> attribute_py |>": 152944,
+  "<|alias_py -> identifier_py |>": 152294,
+  "<|alias_py -> identifier_ter |>": 152952,
+  "<|alias_py -> parenthesized_expression_py |>": 153027,
+  "<|alias_py -> tuple_py |>": 152094,
+  "<|aliased_import_py -> name_py as_ter alias_py |>": 152207,
+  "<|alternative_py -> case_clause_py |>": 152250,
+  "<|alternative_py -> elif_clause_py |>": 152512,
+  "<|alternative_py -> else_clause_py |>": 151845,
+  "<|argument_list_py -> (_ter|>": 152060,
+  "<|argument_list_py -> )_py|>": 152113,
+  "<|argument_list_py -> )_ter|>": 152142,
+  "<|argument_list_py -> ,_ter|>": 152868,
+  "<|argument_list_py -> End |>": 152717,
+  "<|argument_list_py -> attribute_py|>": 152605,
+  "<|argument_list_py -> await_py|>": 152073,
+  "<|argument_list_py -> binary_operator_py|>": 152462,
+  "<|argument_list_py -> boolean_operator_py|>": 152307,
+  "<|argument_list_py -> call_py|>": 151960,
+  "<|argument_list_py -> comparison_operator_py|>": 152138,
+  "<|argument_list_py -> conditional_expression_py|>": 152062,
+  "<|argument_list_py -> dictionary_comprehension_py|>": 152422,
+  "<|argument_list_py -> dictionary_py|>": 152758,
+  "<|argument_list_py -> dictionary_splat_py|>": 152713,
+  "<|argument_list_py -> ellipsis_py|>": 151808,
+  "<|argument_list_py -> false_py|>": 152390,
+  "<|argument_list_py -> float_py|>": 151912,
+  "<|argument_list_py -> generator_expression_py|>": 152148,
+  "<|argument_list_py -> identifier_py|>": 152263,
+  "<|argument_list_py -> identifier_ter|>": 151953,
+  "<|argument_list_py -> integer_py|>": 152419,
+  "<|argument_list_py -> keyword_argument_py|>": 152323,
+  "<|argument_list_py -> lambda_py|>": 151950,
+  "<|argument_list_py -> list_comprehension_py|>": 152208,
+  "<|argument_list_py -> list_py|>": 152591,
+  "<|argument_list_py -> list_splat_py|>": 152272,
+  "<|argument_list_py -> named_expression_py|>": 151831,
+  "<|argument_list_py -> none_py|>": 152695,
+  "<|argument_list_py -> not_operator_py|>": 151828,
+  "<|argument_list_py -> parenthesized_expression_py|>": 151765,
+  "<|argument_list_py -> set_comprehension_py|>": 152125,
+  "<|argument_list_py -> set_py|>": 152091,
+  "<|argument_list_py -> string_literal_py|>": 152314,
+  "<|argument_list_py -> subscript_py|>": 152749,
+  "<|argument_list_py -> true_py|>": 152473,
+  "<|argument_list_py -> tuple_py|>": 152820,
+  "<|argument_list_py -> unary_operator_py|>": 152506,
+  "<|argument_py -> attribute_py |>": 152734,
+  "<|argument_py -> await_py |>": 152313,
+  "<|argument_py -> binary_operator_py |>": 151931,
+  "<|argument_py -> boolean_operator_py |>": 152839,
+  "<|argument_py -> call_py |>": 152705,
+  "<|argument_py -> comparison_operator_py |>": 152580,
+  "<|argument_py -> conditional_expression_py |>": 151888,
+  "<|argument_py -> dictionary_comprehension_py |>": 152439,
+  "<|argument_py -> dictionary_py |>": 152429,
+  "<|argument_py -> false_py |>": 151992,
+  "<|argument_py -> float_py |>": 151958,
+  "<|argument_py -> generator_expression_py |>": 151683,
+  "<|argument_py -> identifier_py |>": 152831,
+  "<|argument_py -> identifier_ter |>": 152624,
+  "<|argument_py -> integer_py |>": 152884,
+  "<|argument_py -> list_comprehension_py |>": 152164,
+  "<|argument_py -> list_py |>": 152477,
+  "<|argument_py -> none_py |>": 151722,
+  "<|argument_py -> not_operator_py |>": 152640,
+  "<|argument_py -> parenthesized_expression_py |>": 152034,
+  "<|argument_py -> set_comprehension_py |>": 152991,
+  "<|argument_py -> set_py |>": 153037,
+  "<|argument_py -> string_literal_py |>": 151902,
+  "<|argument_py -> subscript_py |>": 151967,
+  "<|argument_py -> true_py |>": 151713,
+  "<|argument_py -> tuple_py |>": 152793,
+  "<|argument_py -> unary_operator_py |>": 152188,
+  "<|arguments_py -> argument_list_py |>": 152318,
+  "<|arguments_py -> generator_expression_py |>": 152536,
+  "<|as_pattern_py -> attribute_py as_ter alias_py |>": 152598,
+  "<|as_pattern_py -> await_py as_ter alias_py |>": 152190,
+  "<|as_pattern_py -> binary_operator_py as_ter alias_py |>": 152110,
+  "<|as_pattern_py -> boolean_operator_py as_ter alias_py |>": 151801,
+  "<|as_pattern_py -> call_py as_ter alias_py |>": 151889,
+  "<|as_pattern_py -> case_pattern_py as_ter identifier_py |>": 151753,
+  "<|as_pattern_py -> comparison_operator_py as_ter alias_py |>": 152956,
+  "<|as_pattern_py -> ellipsis_py as_ter alias_py |>": 152928,
+  "<|as_pattern_py -> identifier_py as_ter alias_py |>": 152725,
+  "<|as_pattern_py -> list_py as_ter alias_py |>": 152964,
+  "<|as_pattern_py -> none_py as_ter alias_py |>": 152815,
+  "<|as_pattern_py -> not_operator_py as_ter alias_py |>": 152915,
+  "<|as_pattern_py -> parenthesized_expression_py as_ter alias_py |>": 152458,
+  "<|as_pattern_py -> set_py as_ter alias_py |>": 153057,
+  "<|as_pattern_py -> string_literal_py as_ter alias_py |>": 152911,
+  "<|as_pattern_py -> subscript_py as_ter alias_py |>": 152256,
+  "<|as_pattern_py -> tuple_py as_ter alias_py |>": 152162,
+  "<|as_pattern_py -> unary_operator_py as_ter alias_py |>": 152344,
+  "<|as_pattern_target_py -> attribute_py |>": 152804,
+  "<|as_pattern_target_py -> call_py |>": 153034,
+  "<|as_pattern_target_py -> identifier_py |>": 152821,
+  "<|as_pattern_target_py -> identifier_ter |>": 152980,
+  "<|as_pattern_target_py -> list_py |>": 152416,
+  "<|as_pattern_target_py -> parenthesized_expression_py |>": 153060,
+  "<|as_pattern_target_py -> subscript_py |>": 153014,
+  "<|as_pattern_target_py -> tuple_py |>": 151838,
+  "<|assert_statement_py -> ,_ter|>": 151913,
+  "<|assert_statement_py -> End |>": 151749,
+  "<|assert_statement_py -> assert_ter|>": 152151,
+  "<|assert_statement_py -> attribute_py|>": 152310,
+  "<|assert_statement_py -> await_py|>": 151815,
+  "<|assert_statement_py -> binary_operator_py|>": 151769,
+  "<|assert_statement_py -> boolean_operator_py|>": 152597,
+  "<|assert_statement_py -> call_py|>": 152834,
+  "<|assert_statement_py -> comparison_operator_py|>": 152563,
+  "<|assert_statement_py -> conditional_expression_py|>": 152632,
+  "<|assert_statement_py -> dictionary_comprehension_py|>": 152930,
+  "<|assert_statement_py -> dictionary_py|>": 152958,
+  "<|assert_statement_py -> false_py|>": 151694,
+  "<|assert_statement_py -> float_py|>": 152949,
+  "<|assert_statement_py -> generator_expression_py|>": 152008,
+  "<|assert_statement_py -> identifier_py|>": 152771,
+  "<|assert_statement_py -> identifier_ter|>": 152908,
+  "<|assert_statement_py -> integer_py|>": 152127,
+  "<|assert_statement_py -> list_comprehension_py|>": 151942,
+  "<|assert_statement_py -> list_py|>": 152128,
+  "<|assert_statement_py -> none_py|>": 152938,
+  "<|assert_statement_py -> not_operator_py|>": 152774,
+  "<|assert_statement_py -> parenthesized_expression_py|>": 151907,
+  "<|assert_statement_py -> set_py|>": 152381,
+  "<|assert_statement_py -> string_literal_py|>": 152842,
+  "<|assert_statement_py -> subscript_py|>": 152108,
+  "<|assert_statement_py -> true_py|>": 151871,
+  "<|assert_statement_py -> tuple_py|>": 152050,
+  "<|assert_statement_py -> unary_operator_py|>": 152005,
+  "<|assignment_py -> left_py :_ter type_py =_ter right_py |>": 152667,
+  "<|assignment_py -> left_py :_ter type_py |>": 151991,
+  "<|assignment_py -> left_py =_ter right_py |>": 152628,
+  "<|attribute_py -> identifier_py |>": 151821,
+  "<|attribute_py -> identifier_ter |>": 152838,
+  "<|attribute_py -> object_py ._ter attribute_py |>": 152631,
+  "<|augmented_assignment_py -> left_py operator_py right_py |>": 152708,
+  "<|await_py -> await_ter attribute_py |>": 151731,
+  "<|await_py -> await_ter call_py |>": 151670,
+  "<|await_py -> await_ter identifier_py |>": 152402,
+  "<|await_py -> await_ter integer_py |>": 152989,
+  "<|await_py -> await_ter parenthesized_expression_py |>": 151798,
+  "<|await_py -> await_ter string_literal_py |>": 152777,
+  "<|await_py -> await_ter subscript_py |>": 152727,
+  "<|await_py -> await_ter tuple_py |>": 151877,
+  "<|binary_operator_py -> left_py operator_py right_py |>": 151707,
+  "<|block_py -> ;_ter|>": 151899,
+  "<|block_py -> End |>": 152617,
+  "<|block_py -> alternative_py|>": 151734,
+  "<|block_py -> assert_statement_py|>": 152359,
+  "<|block_py -> break_statement_py|>": 152103,
+  "<|block_py -> class_definition_py|>": 151827,
+  "<|block_py -> continue_statement_py|>": 151852,
+  "<|block_py -> decorated_definition_py|>": 152155,
+  "<|block_py -> delete_statement_py|>": 151674,
+  "<|block_py -> exec_statement_py|>": 151952,
+  "<|block_py -> expression_statement_py|>": 152405,
+  "<|block_py -> for_statement_py|>": 152029,
+  "<|block_py -> function_definition_py|>": 152704,
+  "<|block_py -> future_import_statement_py|>": 152014,
+  "<|block_py -> global_statement_py|>": 152576,
+  "<|block_py -> if_statement_py|>": 152529,
+  "<|block_py -> import_from_statement_py|>": 152854,
+  "<|block_py -> import_statement_py|>": 152889,
+  "<|block_py -> match_statement_py|>": 152650,
+  "<|block_py -> nonlocal_statement_py|>": 152279,
+  "<|block_py -> pass_statement_py|>": 152736,
+  "<|block_py -> print_statement_py|>": 152370,
+  "<|block_py -> raise_statement_py|>": 152460,
+  "<|block_py -> return_statement_py|>": 152627,
+  "<|block_py -> try_statement_py|>": 151816,
+  "<|block_py -> type_alias_statement_py|>": 152683,
+  "<|block_py -> while_statement_py|>": 152038,
+  "<|block_py -> with_statement_py|>": 152847,
+  "<|body_py -> End |>": 151924,
+  "<|body_py -> attribute_py|>": 152772,
+  "<|body_py -> await_py|>": 151995,
+  "<|body_py -> binary_operator_py|>": 152466,
+  "<|body_py -> block_py|>": 152414,
+  "<|body_py -> boolean_operator_py|>": 152562,
+  "<|body_py -> call_py|>": 152143,
+  "<|body_py -> comment_py|>": 152276,
+  "<|body_py -> comparison_operator_py|>": 151904,
+  "<|body_py -> conditional_expression_py|>": 151717,
+  "<|body_py -> dictionary_comprehension_py|>": 152358,
+  "<|body_py -> dictionary_py|>": 151814,
+  "<|body_py -> ellipsis_py|>": 151963,
+  "<|body_py -> false_py|>": 152805,
+  "<|body_py -> float_py|>": 152813,
+  "<|body_py -> generator_expression_py|>": 152561,
+  "<|body_py -> identifier_py|>": 152732,
+  "<|body_py -> identifier_ter|>": 152120,
+  "<|body_py -> integer_py|>": 152645,
+  "<|body_py -> lambda_py|>": 152566,
+  "<|body_py -> list_comprehension_py|>": 152691,
+  "<|body_py -> list_py|>": 151738,
+  "<|body_py -> named_expression_py|>": 152573,
+  "<|body_py -> none_py|>": 151847,
+  "<|body_py -> not_operator_py|>": 152218,
+  "<|body_py -> pair_py|>": 152178,
+  "<|body_py -> parenthesized_expression_py|>": 151850,
+  "<|body_py -> set_comprehension_py|>": 151706,
+  "<|body_py -> set_py|>": 152296,
+  "<|body_py -> string_literal_py|>": 152449,
+  "<|body_py -> subscript_py|>": 152609,
+  "<|body_py -> true_py|>": 152879,
+  "<|body_py -> tuple_py|>": 152396,
+  "<|body_py -> unary_operator_py|>": 152474,
+  "<|boolean_operator_py -> left_py operator_py right_py |>": 152408,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|break_statement_py -> break_ter |>": 152720,
+  "<|call_py -> function_py arguments_py |>": 151817,
+  "<|case_clause_py -> ,_ter|>": 152923,
+  "<|case_clause_py -> :_ter|>": 152716,
+  "<|case_clause_py -> End |>": 151890,
+  "<|case_clause_py -> case_pattern_py|>": 152227,
+  "<|case_clause_py -> case_ter|>": 151823,
+  "<|case_clause_py -> consequence_py|>": 152662,
+  "<|case_clause_py -> guard_py|>": 151737,
+  "<|case_pattern_py -> -_ter float_py |>": 153032,
+  "<|case_pattern_py -> -_ter integer_py |>": 153018,
+  "<|case_pattern_py -> __ter |>": 152840,
+  "<|case_pattern_py -> as_pattern_py |>": 152377,
+  "<|case_pattern_py -> class_pattern_py |>": 152626,
+  "<|case_pattern_py -> dict_pattern_py |>": 151894,
+  "<|case_pattern_py -> dotted_name_py |>": 152699,
+  "<|case_pattern_py -> false_py |>": 152931,
+  "<|case_pattern_py -> float_py |>": 152116,
+  "<|case_pattern_py -> integer_py |>": 152663,
+  "<|case_pattern_py -> keyword_pattern_py |>": 152328,
+  "<|case_pattern_py -> list_pattern_py |>": 152851,
+  "<|case_pattern_py -> none_py |>": 152028,
+  "<|case_pattern_py -> splat_pattern_py |>": 152364,
+  "<|case_pattern_py -> string_literal_py |>": 151688,
+  "<|case_pattern_py -> true_py |>": 153022,
+  "<|case_pattern_py -> tuple_pattern_py |>": 151751,
+  "<|case_pattern_py -> union_pattern_py |>": 152768,
+  "<|cause_py -> attribute_py |>": 151678,
+  "<|cause_py -> boolean_operator_py |>": 153062,
+  "<|cause_py -> call_py |>": 152380,
+  "<|cause_py -> identifier_py |>": 152211,
+  "<|cause_py -> none_py |>": 152467,
+  "<|cause_py -> subscript_py |>": 152417,
+  "<|chevron_py -> >>_ter attribute_py |>": 152145,
+  "<|chevron_py -> >>_ter call_py |>": 151841,
+  "<|chevron_py -> >>_ter identifier_py |>": 152052,
+  "<|chevron_py -> >>_ter none_py |>": 152996,
+  "<|chevron_py -> >>_ter string_literal_py |>": 153059,
+  "<|chevron_py -> >>_ter subscript_py |>": 153033,
+  "<|class_definition_py -> class_ter name_py :_ter body_py |>": 152530,
+  "<|class_definition_py -> class_ter name_py superclasses_py :_ter body_py |>": 151676,
+  "<|class_definition_py -> class_ter name_py type_parameters_py :_ter body_py |>": 152192,
+  "<|class_definition_py -> class_ter name_py type_parameters_py superclasses_py :_ter body_py |>": 153020,
+  "<|class_pattern_py -> (_ter|>": 152139,
+  "<|class_pattern_py -> )_ter|>": 152011,
+  "<|class_pattern_py -> ,_ter|>": 151959,
+  "<|class_pattern_py -> End |>": 152000,
+  "<|class_pattern_py -> case_pattern_py|>": 152054,
+  "<|class_pattern_py -> dotted_name_py|>": 152084,
+  "<|code_py -> identifier_py |>": 152484,
+  "<|code_py -> string_literal_py |>": 151897,
+  "<|comment_py -> End|>": 152767,
+  "<|comparison_operator_py -> End |>": 151836,
+  "<|comparison_operator_py -> attribute_py|>": 151957,
+  "<|comparison_operator_py -> await_py|>": 151700,
+  "<|comparison_operator_py -> binary_operator_py|>": 152595,
+  "<|comparison_operator_py -> call_py|>": 151719,
+  "<|comparison_operator_py -> dictionary_comprehension_py|>": 152107,
+  "<|comparison_operator_py -> dictionary_py|>": 151718,
+  "<|comparison_operator_py -> ellipsis_py|>": 152114,
+  "<|comparison_operator_py -> false_py|>": 151846,
+  "<|comparison_operator_py -> float_py|>": 151792,
+  "<|comparison_operator_py -> generator_expression_py|>": 152773,
+  "<|comparison_operator_py -> identifier_py|>": 152015,
+  "<|comparison_operator_py -> identifier_ter|>": 152363,
+  "<|comparison_operator_py -> integer_py|>": 152592,
+  "<|comparison_operator_py -> list_comprehension_py|>": 152105,
+  "<|comparison_operator_py -> list_py|>": 152877,
+  "<|comparison_operator_py -> list_splat_py|>": 152032,
+  "<|comparison_operator_py -> none_py|>": 152684,
+  "<|comparison_operator_py -> operators_py|>": 152448,
+  "<|comparison_operator_py -> parenthesized_expression_py|>": 152174,
+  "<|comparison_operator_py -> set_comprehension_py|>": 152135,
+  "<|comparison_operator_py -> set_py|>": 152456,
+  "<|comparison_operator_py -> string_literal_py|>": 152435,
+  "<|comparison_operator_py -> subscript_py|>": 152635,
+  "<|comparison_operator_py -> true_py|>": 152230,
+  "<|comparison_operator_py -> tuple_py|>": 152368,
+  "<|comparison_operator_py -> unary_operator_py|>": 152735,
+  "<|condition_py -> as_pattern_py |>": 153023,
+  "<|condition_py -> attribute_py |>": 151921,
+  "<|condition_py -> await_py |>": 152887,
+  "<|condition_py -> binary_operator_py |>": 151810,
+  "<|condition_py -> boolean_operator_py |>": 152283,
+  "<|condition_py -> call_py |>": 152100,
+  "<|condition_py -> comparison_operator_py |>": 151743,
+  "<|condition_py -> conditional_expression_py |>": 152500,
+  "<|condition_py -> dictionary_py |>": 152757,
+  "<|condition_py -> ellipsis_py |>": 152527,
+  "<|condition_py -> false_py |>": 151929,
+  "<|condition_py -> float_py |>": 152973,
+  "<|condition_py -> generator_expression_py |>": 153069,
+  "<|condition_py -> identifier_py |>": 152437,
+  "<|condition_py -> identifier_ter |>": 152025,
+  "<|condition_py -> integer_py |>": 151679,
+  "<|condition_py -> lambda_py |>": 152891,
+  "<|condition_py -> list_comprehension_py |>": 152288,
+  "<|condition_py -> list_py |>": 152172,
+  "<|condition_py -> named_expression_py |>": 151716,
+  "<|condition_py -> none_py |>": 152985,
+  "<|condition_py -> not_operator_py |>": 151789,
+  "<|condition_py -> parenthesized_expression_py |>": 152213,
+  "<|condition_py -> set_comprehension_py |>": 153016,
+  "<|condition_py -> set_py |>": 152900,
+  "<|condition_py -> string_literal_py |>": 152542,
+  "<|condition_py -> subscript_py |>": 152588,
+  "<|condition_py -> true_py |>": 152243,
+  "<|condition_py -> tuple_py |>": 152885,
+  "<|condition_py -> unary_operator_py |>": 152003,
+  "<|conditional_expression_py -> End |>": 152119,
+  "<|conditional_expression_py -> as_pattern_py|>": 151720,
+  "<|conditional_expression_py -> attribute_py|>": 152315,
+  "<|conditional_expression_py -> await_py|>": 152600,
+  "<|conditional_expression_py -> binary_operator_py|>": 152690,
+  "<|conditional_expression_py -> boolean_operator_py|>": 152266,
+  "<|conditional_expression_py -> call_py|>": 151936,
+  "<|conditional_expression_py -> comparison_operator_py|>": 152242,
+  "<|conditional_expression_py -> conditional_expression_py|>": 152643,
+  "<|conditional_expression_py -> dictionary_comprehension_py|>": 152537,
+  "<|conditional_expression_py -> dictionary_py|>": 152569,
+  "<|conditional_expression_py -> ellipsis_py|>": 152525,
+  "<|conditional_expression_py -> else_ter|>": 152883,
+  "<|conditional_expression_py -> false_py|>": 152181,
+  "<|conditional_expression_py -> float_py|>": 151775,
+  "<|conditional_expression_py -> generator_expression_py|>": 152608,
+  "<|conditional_expression_py -> identifier_py|>": 151712,
+  "<|conditional_expression_py -> identifier_ter|>": 151773,
+  "<|conditional_expression_py -> if_ter|>": 152867,
+  "<|conditional_expression_py -> integer_py|>": 152541,
+  "<|conditional_expression_py -> lambda_py|>": 152491,
+  "<|conditional_expression_py -> list_comprehension_py|>": 152202,
+  "<|conditional_expression_py -> list_py|>": 152540,
+  "<|conditional_expression_py -> named_expression_py|>": 152016,
+  "<|conditional_expression_py -> none_py|>": 152123,
+  "<|conditional_expression_py -> not_operator_py|>": 152577,
+  "<|conditional_expression_py -> parenthesized_expression_py|>": 152394,
+  "<|conditional_expression_py -> set_comprehension_py|>": 152567,
+  "<|conditional_expression_py -> set_py|>": 152476,
+  "<|conditional_expression_py -> string_literal_py|>": 151800,
+  "<|conditional_expression_py -> subscript_py|>": 152865,
+  "<|conditional_expression_py -> true_py|>": 152718,
+  "<|conditional_expression_py -> tuple_py|>": 152360,
+  "<|conditional_expression_py -> unary_operator_py|>": 152048,
+  "<|consequence_py -> block_py |>": 152191,
+  "<|consequence_py -> comment_py |>": 152367,
+  "<|constrained_type_py -> type_py :_ter type_py |>": 152403,
+  "<|continue_statement_py -> continue_ter |>": 151981,
+  "<|decorated_definition_py -> End |>": 151793,
+  "<|decorated_definition_py -> decorator_py|>": 152878,
+  "<|decorated_definition_py -> definition_py|>": 152775,
+  "<|decorator_py -> @_ter attribute_py |>": 152350,
+  "<|decorator_py -> @_ter binary_operator_py |>": 153015,
+  "<|decorator_py -> @_ter call_py |>": 151774,
+  "<|decorator_py -> @_ter identifier_py |>": 152682,
+  "<|decorator_py -> @_ter lambda_py |>": 152982,
+  "<|decorator_py -> @_ter parenthesized_expression_py |>": 153024,
+  "<|decorator_py -> @_ter subscript_py |>": 152452,
+  "<|default_parameter_py -> name_py =_ter value_py |>": 151919,
+  "<|definition_py -> class_definition_py |>": 152549,
+  "<|definition_py -> function_definition_py |>": 152615,
+  "<|delete_statement_py -> del_ter attribute_py |>": 152309,
+  "<|delete_statement_py -> del_ter call_py |>": 152518,
+  "<|delete_statement_py -> del_ter comparison_operator_py |>": 152999,
+  "<|delete_statement_py -> del_ter expression_list_py |>": 152501,
+  "<|delete_statement_py -> del_ter identifier_py |>": 152379,
+  "<|delete_statement_py -> del_ter integer_py |>": 153055,
+  "<|delete_statement_py -> del_ter list_py |>": 152986,
+  "<|delete_statement_py -> del_ter parenthesized_expression_py |>": 152352,
+  "<|delete_statement_py -> del_ter subscript_py |>": 151740,
+  "<|delete_statement_py -> del_ter tuple_py |>": 152806,
+  "<|dict_pattern_py -> ,_ter|>": 151973,
+  "<|dict_pattern_py -> :_ter|>": 152677,
+  "<|dict_pattern_py -> End |>": 152347,
+  "<|dict_pattern_py -> key_py|>": 151997,
+  "<|dict_pattern_py -> splat_pattern_py|>": 153005,
+  "<|dict_pattern_py -> value_py|>": 152552,
+  "<|dict_pattern_py -> {_ter|>": 151914,
+  "<|dict_pattern_py -> }_ter|>": 152791,
+  "<|dictionary_comprehension_py -> End |>": 151741,
+  "<|dictionary_comprehension_py -> body_py|>": 151768,
+  "<|dictionary_comprehension_py -> for_in_clause_py|>": 151990,
+  "<|dictionary_comprehension_py -> if_clause_py|>": 152578,
+  "<|dictionary_comprehension_py -> {_ter|>": 152832,
+  "<|dictionary_comprehension_py -> }_ter|>": 152472,
+  "<|dictionary_py -> ,_ter|>": 151879,
+  "<|dictionary_py -> End |>": 152361,
+  "<|dictionary_py -> dictionary_splat_py|>": 151863,
+  "<|dictionary_py -> pair_py|>": 152746,
+  "<|dictionary_py -> {_ter|>": 152245,
+  "<|dictionary_py -> }_py|>": 152241,
+  "<|dictionary_py -> }_ter|>": 152293,
+  "<|dictionary_splat_pattern_py -> **_ter identifier_py |>": 152864,
+  "<|dictionary_splat_py -> **_ter attribute_py |>": 152828,
+  "<|dictionary_splat_py -> **_ter await_py |>": 152092,
+  "<|dictionary_splat_py -> **_ter binary_operator_py |>": 152468,
+  "<|dictionary_splat_py -> **_ter boolean_operator_py |>": 151855,
+  "<|dictionary_splat_py -> **_ter call_py |>": 152652,
+  "<|dictionary_splat_py -> **_ter conditional_expression_py |>": 151685,
+  "<|dictionary_splat_py -> **_ter dictionary_comprehension_py |>": 151839,
+  "<|dictionary_splat_py -> **_ter dictionary_py |>": 151667,
+  "<|dictionary_splat_py -> **_ter identifier_py |>": 152743,
+  "<|dictionary_splat_py -> **_ter identifier_ter |>": 153065,
+  "<|dictionary_splat_py -> **_ter integer_py |>": 152903,
+  "<|dictionary_splat_py -> **_ter list_py |>": 153029,
+  "<|dictionary_splat_py -> **_ter list_splat_py |>": 152978,
+  "<|dictionary_splat_py -> **_ter none_py |>": 153047,
+  "<|dictionary_splat_py -> **_ter parenthesized_expression_py |>": 152343,
+  "<|dictionary_splat_py -> **_ter set_py |>": 152902,
+  "<|dictionary_splat_py -> **_ter string_literal_py |>": 153042,
+  "<|dictionary_splat_py -> **_ter subscript_py |>": 152816,
+  "<|dictionary_splat_py -> **_ter tuple_py |>": 153021,
+  "<|dotted_name_py -> ._ter|>": 152862,
+  "<|dotted_name_py -> End |>": 152259,
+  "<|dotted_name_py -> identifier_py|>": 151880,
+  "<|dotted_name_py -> identifier_ter|>": 152317,
+  "<|elif_clause_py -> elif_ter condition_py :_ter consequence_py |>": 152002,
+  "<|ellipsis_py -> ..._ter |>": 151999,
+  "<|else_clause_py -> else_ter :_ter body_py |>": 152083,
+  "<|endoftext|>": 151643,
+  "<|except_clause_py -> except_ter :_ter block_py |>": 152795,
+  "<|except_clause_py -> except_ter :_ter |>": 151681,
+  "<|except_clause_py -> except_ter value_py ,_ter alias_py :_ter block_py |>": 151748,
+  "<|except_clause_py -> except_ter value_py ,_ter alias_py :_ter |>": 152401,
+  "<|except_clause_py -> except_ter value_py :_ter block_py |>": 151756,
+  "<|except_clause_py -> except_ter value_py :_ter |>": 151869,
+  "<|except_group_clause_py -> except*_ter as_pattern_py :_ter block_py |>": 152893,
+  "<|except_group_clause_py -> except*_ter identifier_py :_ter block_py |>": 152790,
+  "<|exec_statement_py -> exec_ter code_py in_ter attribute_py |>": 152934,
+  "<|exec_statement_py -> exec_ter code_py in_ter call_py ,_ter attribute_py |>": 152972,
+  "<|exec_statement_py -> exec_ter code_py in_ter call_py ,_ter call_py |>": 152744,
+  "<|exec_statement_py -> exec_ter code_py in_ter call_py ,_ter identifier_py |>": 152897,
+  "<|exec_statement_py -> exec_ter code_py in_ter call_py |>": 152953,
+  "<|exec_statement_py -> exec_ter code_py in_ter dictionary_py ,_ter dictionary_py |>": 152981,
+  "<|exec_statement_py -> exec_ter code_py in_ter dictionary_py ,_ter identifier_py |>": 153071,
+  "<|exec_statement_py -> exec_ter code_py in_ter dictionary_py |>": 152731,
+  "<|exec_statement_py -> exec_ter code_py in_ter identifier_py ,_ter identifier_py |>": 151868,
+  "<|exec_statement_py -> exec_ter code_py in_ter identifier_py |>": 152496,
+  "<|exec_statement_py -> exec_ter code_py in_ter subscript_py |>": 152994,
+  "<|exec_statement_py -> exec_ter code_py |>": 152495,
+  "<|expression_list_py -> ,_ter|>": 152393,
+  "<|expression_list_py -> End |>": 152871,
+  "<|expression_list_py -> attribute_py|>": 152535,
+  "<|expression_list_py -> await_py|>": 151818,
+  "<|expression_list_py -> binary_operator_py|>": 151834,
+  "<|expression_list_py -> boolean_operator_py|>": 152355,
+  "<|expression_list_py -> call_py|>": 152291,
+  "<|expression_list_py -> comparison_operator_py|>": 152649,
+  "<|expression_list_py -> conditional_expression_py|>": 151853,
+  "<|expression_list_py -> dictionary_comprehension_py|>": 152488,
+  "<|expression_list_py -> dictionary_py|>": 151677,
+  "<|expression_list_py -> ellipsis_py|>": 152613,
+  "<|expression_list_py -> false_py|>": 151940,
+  "<|expression_list_py -> float_py|>": 151934,
+  "<|expression_list_py -> generator_expression_py|>": 152198,
+  "<|expression_list_py -> identifier_py|>": 152764,
+  "<|expression_list_py -> identifier_ter|>": 151915,
+  "<|expression_list_py -> integer_py|>": 152876,
+  "<|expression_list_py -> lambda_py|>": 152434,
+  "<|expression_list_py -> list_comprehension_py|>": 152194,
+  "<|expression_list_py -> list_py|>": 152366,
+  "<|expression_list_py -> list_splat_py|>": 152168,
+  "<|expression_list_py -> none_py|>": 152515,
+  "<|expression_list_py -> not_operator_py|>": 152009,
+  "<|expression_list_py -> parenthesized_expression_py|>": 152045,
+  "<|expression_list_py -> set_comprehension_py|>": 152446,
+  "<|expression_list_py -> set_py|>": 152144,
+  "<|expression_list_py -> string_literal_py|>": 152001,
+  "<|expression_list_py -> subscript_py|>": 151782,
+  "<|expression_list_py -> true_py|>": 152195,
+  "<|expression_list_py -> tuple_py|>": 152106,
+  "<|expression_list_py -> unary_operator_py|>": 152669,
+  "<|expression_statement_py -> ,_ter|>": 152622,
+  "<|expression_statement_py -> End |>": 152035,
+  "<|expression_statement_py -> as_pattern_py|>": 152030,
+  "<|expression_statement_py -> assignment_py|>": 152869,
+  "<|expression_statement_py -> attribute_py|>": 152822,
+  "<|expression_statement_py -> augmented_assignment_py|>": 151975,
+  "<|expression_statement_py -> await_py|>": 151771,
+  "<|expression_statement_py -> binary_operator_py|>": 152471,
+  "<|expression_statement_py -> boolean_operator_py|>": 152096,
+  "<|expression_statement_py -> call_py|>": 152234,
+  "<|expression_statement_py -> comparison_operator_py|>": 151842,
+  "<|expression_statement_py -> conditional_expression_py|>": 152338,
+  "<|expression_statement_py -> dictionary_comprehension_py|>": 152785,
+  "<|expression_statement_py -> dictionary_py|>": 151941,
+  "<|expression_statement_py -> ellipsis_py|>": 151709,
+  "<|expression_statement_py -> false_py|>": 152794,
+  "<|expression_statement_py -> float_py|>": 151689,
+  "<|expression_statement_py -> generator_expression_py|>": 151820,
+  "<|expression_statement_py -> identifier_py|>": 152826,
+  "<|expression_statement_py -> identifier_ter|>": 152942,
+  "<|expression_statement_py -> integer_py|>": 151687,
+  "<|expression_statement_py -> lambda_py|>": 152286,
+  "<|expression_statement_py -> list_comprehension_py|>": 152534,
+  "<|expression_statement_py -> list_py|>": 151864,
+  "<|expression_statement_py -> list_splat_py|>": 152917,
+  "<|expression_statement_py -> none_py|>": 152432,
+  "<|expression_statement_py -> not_operator_py|>": 152261,
+  "<|expression_statement_py -> parenthesized_expression_py|>": 152075,
+  "<|expression_statement_py -> set_comprehension_py|>": 152810,
+  "<|expression_statement_py -> set_py|>": 152513,
+  "<|expression_statement_py -> string_literal_py|>": 152244,
+  "<|expression_statement_py -> subscript_py|>": 152057,
+  "<|expression_statement_py -> true_py|>": 152146,
+  "<|expression_statement_py -> tuple_py|>": 152546,
+  "<|expression_statement_py -> unary_operator_py|>": 152007,
+  "<|expression_statement_py -> yield_py|>": 152762,
+  "<|false_py -> False_ter |>": 151862,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|finally_clause_py -> finally_ter :_ter block_py |>": 151772,
+  "<|finally_clause_py -> finally_ter :_ter |>": 152742,
+  "<|for_in_clause_py -> ,_ter|>": 152992,
+  "<|for_in_clause_py -> End |>": 151757,
+  "<|for_in_clause_py -> async_ter|>": 152335,
+  "<|for_in_clause_py -> for_ter|>": 152409,
+  "<|for_in_clause_py -> in_ter|>": 151916,
+  "<|for_in_clause_py -> left_py|>": 152856,
+  "<|for_in_clause_py -> right_py|>": 152063,
+  "<|for_statement_py -> async_ter for_ter left_py in_ter right_py :_ter body_py alternative_py |>": 152819,
+  "<|for_statement_py -> async_ter for_ter left_py in_ter right_py :_ter body_py |>": 151732,
+  "<|for_statement_py -> for_ter left_py in_ter right_py :_ter body_py alternative_py |>": 151885,
+  "<|for_statement_py -> for_ter left_py in_ter right_py :_ter body_py |>": 152325,
+  "<|function_definition_py -> async_ter def_ter name_py parameters_py ->_ter return_type_py :_ter body_py |>": 152097,
+  "<|function_definition_py -> async_ter def_ter name_py parameters_py :_ter body_py |>": 151806,
+  "<|function_definition_py -> def_ter name_py parameters_py ->_ter return_type_py :_ter body_py |>": 151930,
+  "<|function_definition_py -> def_ter name_py parameters_py :_ter body_py |>": 152679,
+  "<|function_definition_py -> def_ter name_py type_parameters_py parameters_py ->_ter return_type_py :_ter body_py |>": 152912,
+  "<|function_definition_py -> def_ter name_py type_parameters_py parameters_py :_ter body_py |>": 152739,
+  "<|function_py -> attribute_py |>": 152463,
+  "<|function_py -> call_py |>": 152859,
+  "<|function_py -> ellipsis_py |>": 152657,
+  "<|function_py -> false_py |>": 152378,
+  "<|function_py -> float_py |>": 152969,
+  "<|function_py -> identifier_py |>": 152082,
+  "<|function_py -> identifier_ter |>": 152159,
+  "<|function_py -> integer_py |>": 152200,
+  "<|function_py -> list_py |>": 153013,
+  "<|function_py -> list_splat_py |>": 151896,
+  "<|function_py -> none_py |>": 152710,
+  "<|function_py -> parenthesized_expression_py |>": 151686,
+  "<|function_py -> string_literal_py |>": 152223,
+  "<|function_py -> subscript_py |>": 152548,
+  "<|function_py -> true_py |>": 151761,
+  "<|function_py -> tuple_py |>": 151725,
+  "<|future_import_statement_py -> (_ter|>": 152023,
+  "<|future_import_statement_py -> )_ter|>": 151785,
+  "<|future_import_statement_py -> ,_ter|>": 151760,
+  "<|future_import_statement_py -> End |>": 152140,
+  "<|future_import_statement_py -> __future___ter|>": 151859,
+  "<|future_import_statement_py -> from_ter|>": 152689,
+  "<|future_import_statement_py -> import_ter|>": 152225,
+  "<|future_import_statement_py -> name_py|>": 152769,
+  "<|generator_expression_py -> (_ter|>": 152067,
+  "<|generator_expression_py -> )_py|>": 152913,
+  "<|generator_expression_py -> )_ter|>": 152078,
+  "<|generator_expression_py -> End |>": 152236,
+  "<|generator_expression_py -> body_py|>": 151955,
+  "<|generator_expression_py -> for_in_clause_py|>": 152465,
+  "<|generator_expression_py -> if_clause_py|>": 152214,
+  "<|generic_type_py -> identifier_py type_parameter_py |>": 151759,
+  "<|global_statement_py -> ,_ter|>": 151750,
+  "<|global_statement_py -> End |>": 151906,
+  "<|global_statement_py -> global_ter|>": 152058,
+  "<|global_statement_py -> identifier_py|>": 152412,
+  "<|global_statement_py -> identifier_ter|>": 152894,
+  "<|guard_py -> if_clause_py |>": 152086,
+  "<|if_clause_py -> if_ter attribute_py |>": 152589,
+  "<|if_clause_py -> if_ter await_py |>": 152424,
+  "<|if_clause_py -> if_ter binary_operator_py |>": 152487,
+  "<|if_clause_py -> if_ter boolean_operator_py |>": 152022,
+  "<|if_clause_py -> if_ter call_py |>": 152348,
+  "<|if_clause_py -> if_ter comparison_operator_py |>": 152099,
+  "<|if_clause_py -> if_ter dictionary_comprehension_py |>": 152896,
+  "<|if_clause_py -> if_ter false_py |>": 152671,
+  "<|if_clause_py -> if_ter identifier_py |>": 152571,
+  "<|if_clause_py -> if_ter integer_py |>": 153077,
+  "<|if_clause_py -> if_ter lambda_py |>": 152983,
+  "<|if_clause_py -> if_ter list_comprehension_py |>": 152761,
+  "<|if_clause_py -> if_ter list_py |>": 152984,
+  "<|if_clause_py -> if_ter named_expression_py |>": 153045,
+  "<|if_clause_py -> if_ter not_operator_py |>": 152709,
+  "<|if_clause_py -> if_ter parenthesized_expression_py |>": 152478,
+  "<|if_clause_py -> if_ter string_literal_py |>": 153070,
+  "<|if_clause_py -> if_ter subscript_py |>": 152586,
+  "<|if_clause_py -> if_ter true_py |>": 153025,
+  "<|if_clause_py -> if_ter tuple_py |>": 152122,
+  "<|if_clause_py -> if_ter unary_operator_py |>": 152910,
+  "<|if_statement_py -> :_ter|>": 152575,
+  "<|if_statement_py -> End |>": 152284,
+  "<|if_statement_py -> alternative_py|>": 152668,
+  "<|if_statement_py -> condition_py|>": 152647,
+  "<|if_statement_py -> consequence_py|>": 152544,
+  "<|if_statement_py -> if_ter|>": 152340,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|import_from_statement_py -> (_ter|>": 152093,
+  "<|import_from_statement_py -> )_ter|>": 151856,
+  "<|import_from_statement_py -> ,_ter|>": 152197,
+  "<|import_from_statement_py -> End |>": 152297,
+  "<|import_from_statement_py -> from_ter|>": 151680,
+  "<|import_from_statement_py -> import_ter|>": 152024,
+  "<|import_from_statement_py -> module_name_py|>": 151822,
+  "<|import_from_statement_py -> name_py|>": 152013,
+  "<|import_from_statement_py -> wildcard_import_py|>": 152788,
+  "<|import_prefix_py -> ._ter|>": 152407,
+  "<|import_prefix_py -> End |>": 152464,
+  "<|import_statement_py -> ,_ter|>": 151989,
+  "<|import_statement_py -> End |>": 152611,
+  "<|import_statement_py -> import_ter|>": 152719,
+  "<|import_statement_py -> name_py|>": 151956,
+  "<|in_py -> _ter |>": 152216,
+  "<|is_not_py -> is_ter not_ter |>": 152386,
+  "<|key_py -> attribute_py |>": 152346,
+  "<|key_py -> await_py |>": 153064,
+  "<|key_py -> binary_operator_py |>": 152306,
+  "<|key_py -> boolean_operator_py |>": 152320,
+  "<|key_py -> call_py |>": 152582,
+  "<|key_py -> comparison_operator_py |>": 152825,
+  "<|key_py -> conditional_expression_py |>": 152397,
+  "<|key_py -> dictionary_py |>": 152700,
+  "<|key_py -> dotted_name_py |>": 152988,
+  "<|key_py -> ellipsis_py |>": 153003,
+  "<|key_py -> false_py |>": 151843,
+  "<|key_py -> float_py |>": 151917,
+  "<|key_py -> identifier_py |>": 152733,
+  "<|key_py -> identifier_ter |>": 152383,
+  "<|key_py -> integer_py |>": 152282,
+  "<|key_py -> lambda_py |>": 152866,
+  "<|key_py -> list_py |>": 152251,
+  "<|key_py -> none_py |>": 152319,
+  "<|key_py -> not_operator_py |>": 152203,
+  "<|key_py -> parenthesized_expression_py |>": 152714,
+  "<|key_py -> string_literal_py |>": 151870,
+  "<|key_py -> subscript_py |>": 152163,
+  "<|key_py -> true_py |>": 152853,
+  "<|key_py -> tuple_py |>": 152565,
+  "<|key_py -> unary_operator_py |>": 151874,
+  "<|keyword_argument_py -> name_py =_ter value_py |>": 152817,
+  "<|keyword_pattern_py -> identifier_py =_ter -_ter integer_py |>": 153054,
+  "<|keyword_pattern_py -> identifier_py =_ter __ter |>": 152987,
+  "<|keyword_pattern_py -> identifier_py =_ter class_pattern_py |>": 152933,
+  "<|keyword_pattern_py -> identifier_py =_ter dict_pattern_py |>": 153052,
+  "<|keyword_pattern_py -> identifier_py =_ter dotted_name_py |>": 152729,
+  "<|keyword_pattern_py -> identifier_py =_ter false_py |>": 153030,
+  "<|keyword_pattern_py -> identifier_py =_ter integer_py |>": 153056,
+  "<|keyword_pattern_py -> identifier_py =_ter list_pattern_py |>": 152907,
+  "<|keyword_pattern_py -> identifier_py =_ter none_py |>": 153035,
+  "<|keyword_pattern_py -> identifier_py =_ter string_literal_py |>": 152799,
+  "<|keyword_pattern_py -> identifier_py =_ter true_py |>": 153040,
+  "<|keyword_pattern_py -> identifier_py =_ter tuple_pattern_py |>": 152961,
+  "<|keyword_pattern_py -> identifier_py =_ter union_pattern_py |>": 152971,
+  "<|keyword_separator_py -> *_ter |>": 152090,
+  "<|lambda_parameters_py -> ,_ter|>": 152797,
+  "<|lambda_parameters_py -> End |>": 151939,
+  "<|lambda_parameters_py -> default_parameter_py|>": 151755,
+  "<|lambda_parameters_py -> dictionary_splat_pattern_py|>": 152812,
+  "<|lambda_parameters_py -> identifier_py|>": 152226,
+  "<|lambda_parameters_py -> identifier_ter|>": 152556,
+  "<|lambda_parameters_py -> keyword_separator_py|>": 153075,
+  "<|lambda_parameters_py -> list_splat_pattern_py|>": 152231,
+  "<|lambda_parameters_py -> positional_separator_py|>": 152947,
+  "<|lambda_parameters_py -> tuple_pattern_py|>": 152547,
+  "<|lambda_py -> lambda_ter :_ter body_py |>": 151903,
+  "<|lambda_py -> lambda_ter parameters_py :_ter body_py |>": 152176,
+  "<|left_py -> attribute_py |>": 151943,
+  "<|left_py -> await_py |>": 152331,
+  "<|left_py -> binary_operator_py |>": 152497,
+  "<|left_py -> boolean_operator_py |>": 151696,
+  "<|left_py -> call_py |>": 152861,
+  "<|left_py -> comparison_operator_py |>": 151781,
+  "<|left_py -> dictionary_comprehension_py |>": 152674,
+  "<|left_py -> dictionary_py |>": 152169,
+  "<|left_py -> ellipsis_py |>": 153008,
+  "<|left_py -> false_py |>": 152376,
+  "<|left_py -> float_py |>": 151964,
+  "<|left_py -> generator_expression_py |>": 152004,
+  "<|left_py -> identifier_py |>": 152292,
+  "<|left_py -> identifier_ter |>": 152829,
+  "<|left_py -> integer_py |>": 151908,
+  "<|left_py -> list_comprehension_py |>": 151987,
+  "<|left_py -> list_pattern_py |>": 152781,
+  "<|left_py -> list_py |>": 152043,
+  "<|left_py -> list_splat_pattern_py |>": 152406,
+  "<|left_py -> list_splat_py |>": 153036,
+  "<|left_py -> none_py |>": 152055,
+  "<|left_py -> not_operator_py |>": 151837,
+  "<|left_py -> parenthesized_expression_py |>": 152387,
+  "<|left_py -> pattern_list_py |>": 152274,
+  "<|left_py -> set_comprehension_py |>": 151833,
+  "<|left_py -> set_py |>": 152670,
+  "<|left_py -> string_literal_py |>": 152594,
+  "<|left_py -> subscript_py |>": 151726,
+  "<|left_py -> true_py |>": 152715,
+  "<|left_py -> tuple_pattern_py |>": 152427,
+  "<|left_py -> tuple_py |>": 151745,
+  "<|left_py -> type_py |>": 152085,
+  "<|left_py -> unary_operator_py |>": 151673,
+  "<|list_comprehension_py -> End |>": 151813,
+  "<|list_comprehension_py -> [_ter|>": 152836,
+  "<|list_comprehension_py -> ]_py|>": 152136,
+  "<|list_comprehension_py -> ]_ter|>": 152264,
+  "<|list_comprehension_py -> body_py|>": 151796,
+  "<|list_comprehension_py -> for_in_clause_py|>": 152888,
+  "<|list_comprehension_py -> if_clause_py|>": 152072,
+  "<|list_pattern_py -> ,_ter|>": 152765,
+  "<|list_pattern_py -> End |>": 152026,
+  "<|list_pattern_py -> [_ter|>": 151742,
+  "<|list_pattern_py -> ]_ter|>": 152581,
+  "<|list_pattern_py -> attribute_py|>": 152158,
+  "<|list_pattern_py -> case_pattern_py|>": 151884,
+  "<|list_pattern_py -> identifier_py|>": 152301,
+  "<|list_pattern_py -> identifier_ter|>": 152914,
+  "<|list_pattern_py -> list_pattern_py|>": 152620,
+  "<|list_pattern_py -> list_splat_pattern_py|>": 152354,
+  "<|list_pattern_py -> subscript_py|>": 152882,
+  "<|list_pattern_py -> tuple_pattern_py|>": 152874,
+  "<|list_py -> ,_ter|>": 152269,
+  "<|list_py -> End |>": 152173,
+  "<|list_py -> [_ter|>": 152835,
+  "<|list_py -> ]_py|>": 151691,
+  "<|list_py -> ]_ter|>": 152502,
+  "<|list_py -> attribute_py|>": 152415,
+  "<|list_py -> await_py|>": 152658,
+  "<|list_py -> binary_operator_py|>": 152509,
+  "<|list_py -> boolean_operator_py|>": 151920,
+  "<|list_py -> call_py|>": 152088,
+  "<|list_py -> comparison_operator_py|>": 151804,
+  "<|list_py -> conditional_expression_py|>": 152041,
+  "<|list_py -> dictionary_comprehension_py|>": 152217,
+  "<|list_py -> dictionary_py|>": 152392,
+  "<|list_py -> ellipsis_py|>": 151882,
+  "<|list_py -> false_py|>": 151898,
+  "<|list_py -> float_py|>": 152837,
+  "<|list_py -> generator_expression_py|>": 152076,
+  "<|list_py -> identifier_py|>": 152814,
+  "<|list_py -> identifier_ter|>": 151671,
+  "<|list_py -> integer_py|>": 152763,
+  "<|list_py -> lambda_py|>": 151988,
+  "<|list_py -> list_comprehension_py|>": 152311,
+  "<|list_py -> list_py|>": 152612,
+  "<|list_py -> list_splat_py|>": 152171,
+  "<|list_py -> named_expression_py|>": 152395,
+  "<|list_py -> none_py|>": 152596,
+  "<|list_py -> not_operator_py|>": 152455,
+  "<|list_py -> parenthesized_expression_py|>": 152555,
+  "<|list_py -> parenthesized_list_splat_py|>": 153009,
+  "<|list_py -> set_comprehension_py|>": 152235,
+  "<|list_py -> set_py|>": 152257,
+  "<|list_py -> string_literal_py|>": 152564,
+  "<|list_py -> subscript_py|>": 152421,
+  "<|list_py -> true_py|>": 152784,
+  "<|list_py -> tuple_py|>": 152532,
+  "<|list_py -> unary_operator_py|>": 152115,
+  "<|list_splat_pattern_py -> *_ter attribute_py |>": 152623,
+  "<|list_splat_pattern_py -> *_ter identifier_py |>": 151835,
+  "<|list_splat_pattern_py -> *_ter subscript_py |>": 152901,
+  "<|list_splat_py -> *_ter attribute_py |>": 152490,
+  "<|list_splat_py -> *_ter await_py |>": 152503,
+  "<|list_splat_py -> *_ter binary_operator_py |>": 152655,
+  "<|list_splat_py -> *_ter boolean_operator_py |>": 151966,
+  "<|list_splat_py -> *_ter call_py |>": 152431,
+  "<|list_splat_py -> *_ter comparison_operator_py |>": 152959,
+  "<|list_splat_py -> *_ter conditional_expression_py |>": 152267,
+  "<|list_splat_py -> *_ter dictionary_py |>": 153043,
+  "<|list_splat_py -> *_ter float_py |>": 152927,
+  "<|list_splat_py -> *_ter generator_expression_py |>": 151705,
+  "<|list_splat_py -> *_ter identifier_py |>": 152701,
+  "<|list_splat_py -> *_ter identifier_ter |>": 152932,
+  "<|list_splat_py -> *_ter integer_py |>": 153017,
+  "<|list_splat_py -> *_ter list_comprehension_py |>": 152751,
+  "<|list_splat_py -> *_ter list_py |>": 152844,
+  "<|list_splat_py -> *_ter list_splat_py |>": 152943,
+  "<|list_splat_py -> *_ter parenthesized_expression_py |>": 152848,
+  "<|list_splat_py -> *_ter set_comprehension_py |>": 153058,
+  "<|list_splat_py -> *_ter set_py |>": 152012,
+  "<|list_splat_py -> *_ter string_literal_py |>": 152252,
+  "<|list_splat_py -> *_ter subscript_py |>": 152504,
+  "<|list_splat_py -> *_ter tuple_py |>": 151766,
+  "<|list_splat_py -> *_ter unary_operator_py |>": 152621,
+  "<|match_statement_py -> match_ter subject_py ,_ter subject_py ,_ter subject_py :_ter body_py |>": 152922,
+  "<|match_statement_py -> match_ter subject_py ,_ter subject_py :_ter body_py |>": 153048,
+  "<|match_statement_py -> match_ter subject_py :_ter body_py |>": 151901,
+  "<|member_type_py -> type_py ._ter identifier_py |>": 152858,
+  "<|module_name_py -> dotted_name_py |>": 151977,
+  "<|module_name_py -> relative_import_py |>": 152750,
+  "<|module_py -> ;_ter|>": 152872,
+  "<|module_py -> End |>": 152539,
+  "<|module_py -> _ter|>": 152327,
+  "<|module_py -> assert_statement_py|>": 152639,
+  "<|module_py -> break_statement_py|>": 152680,
+  "<|module_py -> class_definition_py|>": 152521,
+  "<|module_py -> continue_statement_py|>": 153007,
+  "<|module_py -> decorated_definition_py|>": 152644,
+  "<|module_py -> delete_statement_py|>": 152738,
+  "<|module_py -> exec_statement_py|>": 152543,
+  "<|module_py -> expression_statement_py|>": 152382,
+  "<|module_py -> for_statement_py|>": 152061,
+  "<|module_py -> function_definition_py|>": 152802,
+  "<|module_py -> future_import_statement_py|>": 152280,
+  "<|module_py -> global_statement_py|>": 152065,
+  "<|module_py -> if_statement_py|>": 151947,
+  "<|module_py -> import_from_statement_py|>": 151788,
+  "<|module_py -> import_statement_py|>": 151932,
+  "<|module_py -> match_statement_py|>": 152553,
+  "<|module_py -> pass_statement_py|>": 151893,
+  "<|module_py -> print_statement_py|>": 152165,
+  "<|module_py -> raise_statement_py|>": 152587,
+  "<|module_py -> return_statement_py|>": 152659,
+  "<|module_py -> try_statement_py|>": 152755,
+  "<|module_py -> type_alias_statement_py|>": 152249,
+  "<|module_py -> while_statement_py|>": 152278,
+  "<|module_py -> with_statement_py|>": 152603,
+  "<|name_py -> aliased_import_py |>": 152724,
+  "<|name_py -> dotted_name_py |>": 152316,
+  "<|name_py -> identifier_py |>": 152610,
+  "<|name_py -> identifier_ter |>": 151693,
+  "<|name_py -> tuple_pattern_py |>": 153053,
+  "<|named_expression_py -> name_py :=_ter value_py |>": 151770,
+  "<|none_py -> None_ter |>": 151805,
+  "<|nonlocal_statement_py -> ,_ter|>": 152538,
+  "<|nonlocal_statement_py -> End |>": 152349,
+  "<|nonlocal_statement_py -> identifier_py|>": 152254,
+  "<|nonlocal_statement_py -> identifier_ter|>": 151976,
+  "<|nonlocal_statement_py -> nonlocal_ter|>": 152721,
+  "<|not_in_py -> not_ter in_py |>": 152221,
+  "<|not_in_py -> not_ter in_ter |>": 152706,
+  "<|not_operator_py -> not_ter argument_py |>": 152440,
+  "<|object_py -> attribute_py |>": 152248,
+  "<|object_py -> call_py |>": 152425,
+  "<|object_py -> dictionary_comprehension_py |>": 152420,
+  "<|object_py -> dictionary_py |>": 152875,
+  "<|object_py -> ellipsis_py |>": 152454,
+  "<|object_py -> false_py |>": 152324,
+  "<|object_py -> float_py |>": 152299,
+  "<|object_py -> generator_expression_py |>": 151777,
+  "<|object_py -> identifier_py |>": 152304,
+  "<|object_py -> identifier_ter |>": 151970,
+  "<|object_py -> integer_py |>": 152780,
+  "<|object_py -> list_comprehension_py |>": 152047,
+  "<|object_py -> list_py |>": 151985,
+  "<|object_py -> list_splat_py |>": 151979,
+  "<|object_py -> none_py |>": 152779,
+  "<|object_py -> parenthesized_expression_py |>": 152037,
+  "<|object_py -> set_comprehension_py |>": 151851,
+  "<|object_py -> set_py |>": 152147,
+  "<|object_py -> string_literal_py |>": 152362,
+  "<|object_py -> subscript_py |>": 152602,
+  "<|object_py -> true_py |>": 152593,
+  "<|object_py -> tuple_py |>": 152656,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|operator_py -> %=_ter |>": 151704,
+  "<|operator_py -> %_ter |>": 152071,
+  "<|operator_py -> &=_ter |>": 151978,
+  "<|operator_py -> &_ter |>": 152183,
+  "<|operator_py -> **=_ter |>": 152056,
+  "<|operator_py -> **_ter |>": 152430,
+  "<|operator_py -> *=_ter |>": 152798,
+  "<|operator_py -> *_ter |>": 152461,
+  "<|operator_py -> +=_ter |>": 152204,
+  "<|operator_py -> +_ter |>": 152389,
+  "<|operator_py -> -=_ter |>": 151776,
+  "<|operator_py -> -_ter |>": 152189,
+  "<|operator_py -> //=_ter |>": 152890,
+  "<|operator_py -> //_ter |>": 152365,
+  "<|operator_py -> /=_ter |>": 152728,
+  "<|operator_py -> /_ter |>": 152271,
+  "<|operator_py -> <<=_ter |>": 152583,
+  "<|operator_py -> <<_ter |>": 152134,
+  "<|operator_py -> >>=_ter |>": 152132,
+  "<|operator_py -> >>_ter |>": 152444,
+  "<|operator_py -> @=_ter |>": 151795,
+  "<|operator_py -> @_ter |>": 152246,
+  "<|operator_py -> ^=_ter |>": 152433,
+  "<|operator_py -> ^_ter |>": 151923,
+  "<|operator_py -> and_ter |>": 152664,
+  "<|operator_py -> or_ter |>": 151829,
+  "<|operator_py -> |=_ter |>": 152808,
+  "<|operator_py -> |_ter |>": 152184,
+  "<|operator_py -> ~_ter |>": 151980,
+  "<|operators_py -> !=_ter |>": 152800,
+  "<|operators_py -> <=_ter |>": 152150,
+  "<|operators_py -> <>_ter |>": 152177,
+  "<|operators_py -> <_ter |>": 152130,
+  "<|operators_py -> ==_ter |>": 152079,
+  "<|operators_py -> >=_ter |>": 151695,
+  "<|operators_py -> >_ter |>": 152441,
+  "<|operators_py -> in_ter |>": 152843,
+  "<|operators_py -> is_not_py |>": 152258,
+  "<|operators_py -> is_ter |>": 151708,
+  "<|operators_py -> not_in_py |>": 152745,
+  "<|pair_py -> key_py :_ter value_py |>": 152240,
+  "<|parameters_py -> (_ter|>": 151984,
+  "<|parameters_py -> )_py|>": 152968,
+  "<|parameters_py -> )_ter|>": 151819,
+  "<|parameters_py -> ,_ter|>": 152675,
+  "<|parameters_py -> End |>": 152687,
+  "<|parameters_py -> default_parameter_py|>": 152388,
+  "<|parameters_py -> dictionary_splat_pattern_py|>": 151948,
+  "<|parameters_py -> identifier_py|>": 152673,
+  "<|parameters_py -> identifier_ter|>": 151858,
+  "<|parameters_py -> keyword_separator_py|>": 152807,
+  "<|parameters_py -> lambda_parameters_py|>": 152322,
+  "<|parameters_py -> list_splat_pattern_py|>": 152759,
+  "<|parameters_py -> parameters_py|>": 152044,
+  "<|parameters_py -> positional_separator_py|>": 151905,
+  "<|parameters_py -> tuple_pattern_py|>": 152526,
+  "<|parameters_py -> typed_default_parameter_py|>": 151807,
+  "<|parameters_py -> typed_parameter_py|>": 151666,
+  "<|parenthesized_expression_py -> (_ter as_pattern_py )_ter |>": 152754,
+  "<|parenthesized_expression_py -> (_ter attribute_py )_ter |>": 152342,
+  "<|parenthesized_expression_py -> (_ter await_py )_ter |>": 152730,
+  "<|parenthesized_expression_py -> (_ter binary_operator_py )_py |>": 152326,
+  "<|parenthesized_expression_py -> (_ter binary_operator_py )_ter |>": 152069,
+  "<|parenthesized_expression_py -> (_ter boolean_operator_py )_py |>": 152508,
+  "<|parenthesized_expression_py -> (_ter boolean_operator_py )_ter |>": 151886,
+  "<|parenthesized_expression_py -> (_ter call_py )_py |>": 153072,
+  "<|parenthesized_expression_py -> (_ter call_py )_ter |>": 152528,
+  "<|parenthesized_expression_py -> (_ter comparison_operator_py )_py |>": 152629,
+  "<|parenthesized_expression_py -> (_ter comparison_operator_py )_ter |>": 152436,
+  "<|parenthesized_expression_py -> (_ter conditional_expression_py )_ter |>": 152040,
+  "<|parenthesized_expression_py -> (_ter dictionary_comprehension_py )_ter |>": 152619,
+  "<|parenthesized_expression_py -> (_ter dictionary_py )_ter |>": 152818,
+  "<|parenthesized_expression_py -> (_ter ellipsis_py )_ter |>": 152493,
+  "<|parenthesized_expression_py -> (_ter false_py )_ter |>": 152855,
+  "<|parenthesized_expression_py -> (_ter float_py )_ter |>": 152625,
+  "<|parenthesized_expression_py -> (_ter generator_expression_py )_ter |>": 152215,
+  "<|parenthesized_expression_py -> (_ter identifier_py )_ter |>": 152634,
+  "<|parenthesized_expression_py -> (_ter identifier_ter )_ter |>": 153044,
+  "<|parenthesized_expression_py -> (_ter integer_py )_ter |>": 152187,
+  "<|parenthesized_expression_py -> (_ter lambda_py )_ter |>": 152637,
+  "<|parenthesized_expression_py -> (_ter list_comprehension_py )_ter |>": 152166,
+  "<|parenthesized_expression_py -> (_ter list_py )_ter |>": 152102,
+  "<|parenthesized_expression_py -> (_ter list_splat_py )_ter |>": 153076,
+  "<|parenthesized_expression_py -> (_ter named_expression_py )_ter |>": 151672,
+  "<|parenthesized_expression_py -> (_ter none_py )_ter |>": 152519,
+  "<|parenthesized_expression_py -> (_ter not_operator_py )_py |>": 152993,
+  "<|parenthesized_expression_py -> (_ter not_operator_py )_ter |>": 152156,
+  "<|parenthesized_expression_py -> (_ter parenthesized_expression_py )_py |>": 153046,
+  "<|parenthesized_expression_py -> (_ter parenthesized_expression_py )_ter |>": 152636,
+  "<|parenthesized_expression_py -> (_ter set_comprehension_py )_ter |>": 153050,
+  "<|parenthesized_expression_py -> (_ter set_py )_ter |>": 152723,
+  "<|parenthesized_expression_py -> (_ter string_literal_py )_ter |>": 152068,
+  "<|parenthesized_expression_py -> (_ter subscript_py )_ter |>": 151778,
+  "<|parenthesized_expression_py -> (_ter true_py )_ter |>": 151763,
+  "<|parenthesized_expression_py -> (_ter tuple_py )_ter |>": 152517,
+  "<|parenthesized_expression_py -> (_ter unary_operator_py )_ter |>": 152618,
+  "<|parenthesized_expression_py -> (_ter yield_py )_ter |>": 152232,
+  "<|parenthesized_list_splat_py -> (_ter list_splat_py )_ter |>": 153001,
+  "<|pass_statement_py -> pass_ter |>": 152137,
+  "<|pattern_list_py -> ,_ter|>": 152741,
+  "<|pattern_list_py -> End |>": 151849,
+  "<|pattern_list_py -> attribute_py|>": 152489,
+  "<|pattern_list_py -> identifier_py|>": 151951,
+  "<|pattern_list_py -> identifier_ter|>": 152153,
+  "<|pattern_list_py -> list_pattern_py|>": 151811,
+  "<|pattern_list_py -> list_splat_pattern_py|>": 152064,
+  "<|pattern_list_py -> subscript_py|>": 152692,
+  "<|pattern_list_py -> tuple_pattern_py|>": 151974,
+  "<|positional_separator_py -> /_ter |>": 151881,
+  "<|print_statement_py -> ,_ter|>": 152193,
+  "<|print_statement_py -> End |>": 152131,
+  "<|print_statement_py -> argument_py|>": 152514,
+  "<|print_statement_py -> chevron_py|>": 152483,
+  "<|print_statement_py -> print_ter|>": 151736,
+  "<|python -> module_py |>": 152585,
+  "<|python -> module_ter |>": 152760,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|raise_statement_py -> raise_ter attribute_py from_ter cause_py |>": 152411,
+  "<|raise_statement_py -> raise_ter attribute_py |>": 152182,
+  "<|raise_statement_py -> raise_ter await_py from_ter cause_py |>": 153063,
+  "<|raise_statement_py -> raise_ter await_py |>": 153002,
+  "<|raise_statement_py -> raise_ter binary_operator_py |>": 152281,
+  "<|raise_statement_py -> raise_ter boolean_operator_py from_ter cause_py |>": 152975,
+  "<|raise_statement_py -> raise_ter boolean_operator_py |>": 151983,
+  "<|raise_statement_py -> raise_ter call_py from_ter cause_py |>": 151996,
+  "<|raise_statement_py -> raise_ter call_py |>": 152852,
+  "<|raise_statement_py -> raise_ter comparison_operator_py |>": 152792,
+  "<|raise_statement_py -> raise_ter conditional_expression_py from_ter cause_py |>": 152945,
+  "<|raise_statement_py -> raise_ter conditional_expression_py |>": 152475,
+  "<|raise_statement_py -> raise_ter dictionary_py |>": 152726,
+  "<|raise_statement_py -> raise_ter ellipsis_py |>": 152998,
+  "<|raise_statement_py -> raise_ter expression_list_py |>": 152118,
+  "<|raise_statement_py -> raise_ter false_py |>": 152990,
+  "<|raise_statement_py -> raise_ter identifier_py from_ter cause_py |>": 152524,
+  "<|raise_statement_py -> raise_ter identifier_py |>": 152648,
+  "<|raise_statement_py -> raise_ter identifier_ter |>": 153039,
+  "<|raise_statement_py -> raise_ter integer_py |>": 152976,
+  "<|raise_statement_py -> raise_ter list_py |>": 153028,
+  "<|raise_statement_py -> raise_ter none_py |>": 152919,
+  "<|raise_statement_py -> raise_ter not_operator_py |>": 152929,
+  "<|raise_statement_py -> raise_ter parenthesized_expression_py from_ter cause_py |>": 152899,
+  "<|raise_statement_py -> raise_ter parenthesized_expression_py |>": 152485,
+  "<|raise_statement_py -> raise_ter set_py |>": 152957,
+  "<|raise_statement_py -> raise_ter string_literal_py |>": 151900,
+  "<|raise_statement_py -> raise_ter subscript_py from_ter cause_py |>": 152599,
+  "<|raise_statement_py -> raise_ter subscript_py |>": 152020,
+  "<|raise_statement_py -> raise_ter tuple_py from_ter cause_py |>": 152920,
+  "<|raise_statement_py -> raise_ter tuple_py |>": 152507,
+  "<|raise_statement_py -> raise_ter unary_operator_py |>": 152967,
+  "<|raise_statement_py -> raise_ter |>": 152212,
+  "<|relative_import_py -> import_prefix_py dotted_name_py |>": 151968,
+  "<|relative_import_py -> import_prefix_py |>": 152312,
+  "<|repo_name|>": 151663,
+  "<|return_statement_py -> return_ter attribute_py |>": 152642,
+  "<|return_statement_py -> return_ter await_py |>": 151799,
+  "<|return_statement_py -> return_ter binary_operator_py |>": 151824,
+  "<|return_statement_py -> return_ter boolean_operator_py |>": 152373,
+  "<|return_statement_py -> return_ter call_py |>": 152081,
+  "<|return_statement_py -> return_ter comparison_operator_py |>": 152006,
+  "<|return_statement_py -> return_ter conditional_expression_py |>": 152666,
+  "<|return_statement_py -> return_ter dictionary_comprehension_py |>": 152646,
+  "<|return_statement_py -> return_ter dictionary_py |>": 152522,
+  "<|return_statement_py -> return_ter ellipsis_py |>": 152520,
+  "<|return_statement_py -> return_ter expression_list_py |>": 152737,
+  "<|return_statement_py -> return_ter false_py |>": 151715,
+  "<|return_statement_py -> return_ter float_py |>": 151724,
+  "<|return_statement_py -> return_ter generator_expression_py |>": 151860,
+  "<|return_statement_py -> return_ter identifier_py |>": 152447,
+  "<|return_statement_py -> return_ter identifier_ter |>": 152285,
+  "<|return_statement_py -> return_ter integer_py |>": 151844,
+  "<|return_statement_py -> return_ter lambda_py |>": 152480,
+  "<|return_statement_py -> return_ter list_comprehension_py |>": 152459,
+  "<|return_statement_py -> return_ter list_py |>": 152289,
+  "<|return_statement_py -> return_ter named_expression_py |>": 153004,
+  "<|return_statement_py -> return_ter none_py |>": 152863,
+  "<|return_statement_py -> return_ter not_operator_py |>": 151684,
+  "<|return_statement_py -> return_ter parenthesized_expression_py |>": 152300,
+  "<|return_statement_py -> return_ter set_comprehension_py |>": 151937,
+  "<|return_statement_py -> return_ter set_py |>": 152712,
+  "<|return_statement_py -> return_ter string_literal_py |>": 152329,
+  "<|return_statement_py -> return_ter subscript_py |>": 152559,
+  "<|return_statement_py -> return_ter true_py |>": 152229,
+  "<|return_statement_py -> return_ter tuple_py |>": 152584,
+  "<|return_statement_py -> return_ter unary_operator_py |>": 152482,
+  "<|return_statement_py -> return_ter |>": 152017,
+  "<|return_type_py -> type_py |>": 151762,
+  "<|right_py -> ,_ter |>": 152413,
+  "<|right_py -> as_pattern_py |>": 152033,
+  "<|right_py -> assignment_py |>": 151832,
+  "<|right_py -> attribute_py |>": 152846,
+  "<|right_py -> augmented_assignment_py |>": 152372,
+  "<|right_py -> await_py |>": 152698,
+  "<|right_py -> binary_operator_py |>": 152199,
+  "<|right_py -> boolean_operator_py |>": 152638,
+  "<|right_py -> call_py |>": 151887,
+  "<|right_py -> comparison_operator_py |>": 152209,
+  "<|right_py -> conditional_expression_py |>": 152210,
+  "<|right_py -> dictionary_comprehension_py |>": 151783,
+  "<|right_py -> dictionary_py |>": 152827,
+  "<|right_py -> ellipsis_py |>": 152220,
+  "<|right_py -> expression_list_py |>": 152019,
+  "<|right_py -> false_py |>": 152533,
+  "<|right_py -> float_py |>": 152423,
+  "<|right_py -> generator_expression_py |>": 151872,
+  "<|right_py -> identifier_py |>": 152560,
+  "<|right_py -> identifier_ter |>": 151812,
+  "<|right_py -> integer_py |>": 152676,
+  "<|right_py -> lambda_py |>": 152551,
+  "<|right_py -> list_comprehension_py |>": 152295,
+  "<|right_py -> list_py |>": 152262,
+  "<|right_py -> list_splat_py |>": 152438,
+  "<|right_py -> none_py |>": 152786,
+  "<|right_py -> not_operator_py |>": 151703,
+  "<|right_py -> parenthesized_expression_py |>": 151998,
+  "<|right_py -> pattern_list_py |>": 151779,
+  "<|right_py -> set_comprehension_py |>": 151865,
+  "<|right_py -> set_py |>": 152287,
+  "<|right_py -> string_literal_py |>": 151787,
+  "<|right_py -> subscript_py |>": 152205,
+  "<|right_py -> true_py |>": 152470,
+  "<|right_py -> tuple_py |>": 152237,
+  "<|right_py -> type_py |>": 152873,
+  "<|right_py -> unary_operator_py |>": 151721,
+  "<|right_py -> yield_py |>": 152445,
+  "<|set_comprehension_py -> End |>": 151933,
+  "<|set_comprehension_py -> body_py|>": 152748,
+  "<|set_comprehension_py -> for_in_clause_py|>": 151791,
+  "<|set_comprehension_py -> if_clause_py|>": 152222,
+  "<|set_comprehension_py -> {_ter|>": 152133,
+  "<|set_comprehension_py -> }_ter|>": 151944,
+  "<|set_py -> ,_ter|>": 152152,
+  "<|set_py -> End |>": 151866,
+  "<|set_py -> attribute_py|>": 151802,
+  "<|set_py -> await_py|>": 152962,
+  "<|set_py -> binary_operator_py|>": 152334,
+  "<|set_py -> boolean_operator_py|>": 152124,
+  "<|set_py -> call_py|>": 152572,
+  "<|set_py -> comparison_operator_py|>": 151994,
+  "<|set_py -> conditional_expression_py|>": 151764,
+  "<|set_py -> dictionary_py|>": 152196,
+  "<|set_py -> ellipsis_py|>": 152157,
+  "<|set_py -> false_py|>": 152809,
+  "<|set_py -> float_py|>": 152499,
+  "<|set_py -> identifier_py|>": 152696,
+  "<|set_py -> identifier_ter|>": 152290,
+  "<|set_py -> integer_py|>": 152686,
+  "<|set_py -> lambda_py|>": 151891,
+  "<|set_py -> list_comprehension_py|>": 152979,
+  "<|set_py -> list_py|>": 151711,
+  "<|set_py -> list_splat_py|>": 152641,
+  "<|set_py -> named_expression_py|>": 153073,
+  "<|set_py -> none_py|>": 151873,
+  "<|set_py -> not_operator_py|>": 152925,
+  "<|set_py -> parenthesized_expression_py|>": 152161,
+  "<|set_py -> set_py|>": 151701,
+  "<|set_py -> string_literal_py|>": 152703,
+  "<|set_py -> subscript_py|>": 152849,
+  "<|set_py -> true_py|>": 152783,
+  "<|set_py -> tuple_py|>": 152457,
+  "<|set_py -> unary_operator_py|>": 151892,
+  "<|set_py -> {_ter|>": 151668,
+  "<|set_py -> }_py|>": 152801,
+  "<|set_py -> }_ter|>": 152051,
+  "<|slice_py -> :_ter|>": 152186,
+  "<|slice_py -> End |>": 151702,
+  "<|slice_py -> attribute_py|>": 152523,
+  "<|slice_py -> binary_operator_py|>": 152398,
+  "<|slice_py -> boolean_operator_py|>": 152042,
+  "<|slice_py -> call_py|>": 151675,
+  "<|slice_py -> comparison_operator_py|>": 152126,
+  "<|slice_py -> conditional_expression_py|>": 152451,
+  "<|slice_py -> ellipsis_py|>": 152918,
+  "<|slice_py -> false_py|>": 153000,
+  "<|slice_py -> float_py|>": 152330,
+  "<|slice_py -> identifier_py|>": 152550,
+  "<|slice_py -> identifier_ter|>": 153006,
+  "<|slice_py -> integer_py|>": 151735,
+  "<|slice_py -> list_py|>": 152955,
+  "<|slice_py -> none_py|>": 152385,
+  "<|slice_py -> not_operator_py|>": 153011,
+  "<|slice_py -> parenthesized_expression_py|>": 152356,
+  "<|slice_py -> string_literal_py|>": 152046,
+  "<|slice_py -> subscript_py|>": 152179,
+  "<|slice_py -> true_py|>": 152066,
+  "<|slice_py -> tuple_py|>": 152963,
+  "<|slice_py -> unary_operator_py|>": 151825,
+  "<|splat_pattern_py -> **_ter identifier_py |>": 152936,
+  "<|splat_pattern_py -> *_ter __ter |>": 152965,
+  "<|splat_pattern_py -> *_ter identifier_py |>": 151925,
+  "<|splat_type_py -> **_ter identifier_py |>": 152946,
+  "<|splat_type_py -> *_ter identifier_py |>": 152898,
+  "<|start -> python|>": 151867,
+  "<|string_literal_py -> End|>": 152766,
+  "<|subject_py -> attribute_py |>": 151692,
+  "<|subject_py -> await_py |>": 152995,
+  "<|subject_py -> binary_operator_py |>": 152939,
+  "<|subject_py -> boolean_operator_py |>": 153067,
+  "<|subject_py -> call_py |>": 151954,
+  "<|subject_py -> comparison_operator_py |>": 153026,
+  "<|subject_py -> conditional_expression_py |>": 152892,
+  "<|subject_py -> identifier_py |>": 152850,
+  "<|subject_py -> identifier_ter |>": 153041,
+  "<|subject_py -> integer_py |>": 152905,
+  "<|subject_py -> list_comprehension_py |>": 153019,
+  "<|subject_py -> list_py |>": 152895,
+  "<|subject_py -> named_expression_py |>": 153010,
+  "<|subject_py -> parenthesized_expression_py |>": 153012,
+  "<|subject_py -> subscript_py |>": 151790,
+  "<|subject_py -> true_py |>": 153074,
+  "<|subject_py -> tuple_py |>": 151794,
+  "<|subscript_py -> ,_ter|>": 152545,
+  "<|subscript_py -> End |>": 152653,
+  "<|subscript_py -> [_ter|>": 152614,
+  "<|subscript_py -> ]_py|>": 151730,
+  "<|subscript_py -> ]_ter|>": 152747,
+  "<|subscript_py -> attribute_py|>": 152384,
+  "<|subscript_py -> await_py|>": 151972,
+  "<|subscript_py -> binary_operator_py|>": 151797,
+  "<|subscript_py -> boolean_operator_py|>": 151945,
+  "<|subscript_py -> call_py|>": 151895,
+  "<|subscript_py -> comparison_operator_py|>": 152753,
+  "<|subscript_py -> conditional_expression_py|>": 152660,
+  "<|subscript_py -> dictionary_comprehension_py|>": 153038,
+  "<|subscript_py -> dictionary_py|>": 151758,
+  "<|subscript_py -> ellipsis_py|>": 152428,
+  "<|subscript_py -> false_py|>": 152277,
+  "<|subscript_py -> float_py|>": 152219,
+  "<|subscript_py -> generator_expression_py|>": 152308,
+  "<|subscript_py -> identifier_py|>": 152803,
+  "<|subscript_py -> identifier_ter|>": 152298,
+  "<|subscript_py -> integer_py|>": 151840,
+  "<|subscript_py -> lambda_py|>": 152333,
+  "<|subscript_py -> list_comprehension_py|>": 152604,
+  "<|subscript_py -> list_py|>": 152453,
+  "<|subscript_py -> list_splat_py|>": 152070,
+  "<|subscript_py -> named_expression_py|>": 152950,
+  "<|subscript_py -> none_py|>": 152752,
+  "<|subscript_py -> not_operator_py|>": 152833,
+  "<|subscript_py -> parenthesized_expression_py|>": 152049,
+  "<|subscript_py -> set_py|>": 151848,
+  "<|subscript_py -> slice_py|>": 152112,
+  "<|subscript_py -> string_literal_py|>": 152450,
+  "<|subscript_py -> subscript_py|>": 152268,
+  "<|subscript_py -> true_py|>": 151857,
+  "<|subscript_py -> tuple_py|>": 152260,
+  "<|subscript_py -> unary_operator_py|>": 152369,
+  "<|subscript_py -> value_py|>": 152010,
+  "<|superclasses_py -> argument_list_py |>": 152479,
+  "<|true_py -> True_ter |>": 151993,
+  "<|try_statement_py -> :_ter|>": 152404,
+  "<|try_statement_py -> End |>": 152233,
+  "<|try_statement_py -> body_py|>": 152778,
+  "<|try_statement_py -> else_clause_py|>": 151669,
+  "<|try_statement_py -> except_clause_py|>": 152707,
+  "<|try_statement_py -> except_group_clause_py|>": 152886,
+  "<|try_statement_py -> finally_clause_py|>": 151780,
+  "<|try_statement_py -> try_ter|>": 152702,
+  "<|tuple_pattern_py -> (_ter|>": 152031,
+  "<|tuple_pattern_py -> )_py|>": 152904,
+  "<|tuple_pattern_py -> )_ter|>": 151746,
+  "<|tuple_pattern_py -> ,_ter|>": 152787,
+  "<|tuple_pattern_py -> End |>": 151784,
+  "<|tuple_pattern_py -> attribute_py|>": 151961,
+  "<|tuple_pattern_py -> case_pattern_py|>": 151714,
+  "<|tuple_pattern_py -> identifier_py|>": 152341,
+  "<|tuple_pattern_py -> identifier_ter|>": 152111,
+  "<|tuple_pattern_py -> list_pattern_py|>": 152336,
+  "<|tuple_pattern_py -> list_splat_pattern_py|>": 152511,
+  "<|tuple_pattern_py -> subscript_py|>": 151697,
+  "<|tuple_pattern_py -> tuple_pattern_py|>": 152711,
+  "<|tuple_py -> (_ter|>": 152170,
+  "<|tuple_py -> )_py|>": 152516,
+  "<|tuple_py -> )_ter|>": 152303,
+  "<|tuple_py -> ,_ter|>": 152039,
+  "<|tuple_py -> End |>": 152018,
+  "<|tuple_py -> as_pattern_py|>": 151723,
+  "<|tuple_py -> attribute_py|>": 152410,
+  "<|tuple_py -> await_py|>": 152167,
+  "<|tuple_py -> binary_operator_py|>": 152481,
+  "<|tuple_py -> boolean_operator_py|>": 152101,
+  "<|tuple_py -> call_py|>": 152443,
+  "<|tuple_py -> comparison_operator_py|>": 152247,
+  "<|tuple_py -> conditional_expression_py|>": 152697,
+  "<|tuple_py -> dictionary_comprehension_py|>": 151767,
+  "<|tuple_py -> dictionary_py|>": 152391,
+  "<|tuple_py -> ellipsis_py|>": 151883,
+  "<|tuple_py -> false_py|>": 151698,
+  "<|tuple_py -> float_py|>": 151949,
+  "<|tuple_py -> generator_expression_py|>": 152796,
+  "<|tuple_py -> identifier_py|>": 151911,
+  "<|tuple_py -> identifier_ter|>": 151878,
+  "<|tuple_py -> integer_py|>": 152665,
+  "<|tuple_py -> lambda_py|>": 152579,
+  "<|tuple_py -> list_comprehension_py|>": 152109,
+  "<|tuple_py -> list_py|>": 152074,
+  "<|tuple_py -> list_splat_py|>": 151982,
+  "<|tuple_py -> named_expression_py|>": 152265,
+  "<|tuple_py -> none_py|>": 152141,
+  "<|tuple_py -> not_operator_py|>": 152607,
+  "<|tuple_py -> parenthesized_expression_py|>": 152688,
+  "<|tuple_py -> set_comprehension_py|>": 152681,
+  "<|tuple_py -> set_py|>": 152789,
+  "<|tuple_py -> string_literal_py|>": 152770,
+  "<|tuple_py -> subscript_py|>": 152375,
+  "<|tuple_py -> true_py|>": 152302,
+  "<|tuple_py -> tuple_py|>": 152087,
+  "<|tuple_py -> unary_operator_py|>": 151728,
+  "<|type_alias_statement_py -> type_ter left_py =_ter right_py |>": 152036,
+  "<|type_parameter_py -> ,_ter|>": 152722,
+  "<|type_parameter_py -> End |>": 151752,
+  "<|type_parameter_py -> [_ter|>": 152332,
+  "<|type_parameter_py -> ]_ter|>": 152661,
+  "<|type_parameter_py -> type_py|>": 151690,
+  "<|type_parameters_py -> type_parameter_py |>": 152823,
+  "<|type_py -> attribute_py |>": 152273,
+  "<|type_py -> await_py |>": 152916,
+  "<|type_py -> binary_operator_py |>": 152080,
+  "<|type_py -> boolean_operator_py |>": 152053,
+  "<|type_py -> call_py |>": 152021,
+  "<|type_py -> comparison_operator_py |>": 152830,
+  "<|type_py -> conditional_expression_py |>": 152960,
+  "<|type_py -> constrained_type_py |>": 152782,
+  "<|type_py -> dictionary_comprehension_py |>": 153061,
+  "<|type_py -> dictionary_py |>": 152841,
+  "<|type_py -> ellipsis_py |>": 151926,
+  "<|type_py -> false_py |>": 151710,
+  "<|type_py -> float_py |>": 152098,
+  "<|type_py -> generic_type_py |>": 152117,
+  "<|type_py -> identifier_py |>": 151665,
+  "<|type_py -> integer_py |>": 152557,
+  "<|type_py -> lambda_py |>": 153049,
+  "<|type_py -> list_comprehension_py |>": 152941,
+  "<|type_py -> list_py |>": 152270,
+  "<|type_py -> member_type_py |>": 152275,
+  "<|type_py -> none_py |>": 152175,
+  "<|type_py -> not_operator_py |>": 152059,
+  "<|type_py -> parenthesized_expression_py |>": 152353,
+  "<|type_py -> set_py |>": 152776,
+  "<|type_py -> splat_type_py |>": 152921,
+  "<|type_py -> string_literal_py |>": 151854,
+  "<|type_py -> subscript_py |>": 152881,
+  "<|type_py -> true_py |>": 151918,
+  "<|type_py -> tuple_py |>": 152442,
+  "<|type_py -> type_py |>": 151910,
+  "<|type_py -> unary_operator_py |>": 152558,
+  "<|type_py -> union_type_py |>": 152568,
+  "<|typed_default_parameter_py -> name_py :_ter type_py =_ter value_py |>": 152510,
+  "<|typed_parameter_py -> dictionary_splat_pattern_py :_ter type_py |>": 151969,
+  "<|typed_parameter_py -> identifier_py :_ter type_py |>": 152206,
+  "<|typed_parameter_py -> identifier_ter :_ter type_py |>": 151946,
+  "<|typed_parameter_py -> list_splat_pattern_py :_ter type_py |>": 152505,
+  "<|unary_operator_py -> operator_py argument_py |>": 152129,
+  "<|union_pattern_py -> -_ter|>": 152948,
+  "<|union_pattern_py -> End |>": 151909,
+  "<|union_pattern_py -> __ter|>": 152924,
+  "<|union_pattern_py -> class_pattern_py|>": 152357,
+  "<|union_pattern_py -> dict_pattern_py|>": 153051,
+  "<|union_pattern_py -> dotted_name_py|>": 152492,
+  "<|union_pattern_py -> false_py|>": 152906,
+  "<|union_pattern_py -> float_py|>": 152909,
+  "<|union_pattern_py -> integer_py|>": 152374,
+  "<|union_pattern_py -> list_pattern_py|>": 152977,
+  "<|union_pattern_py -> none_py|>": 152935,
+  "<|union_pattern_py -> string_literal_py|>": 152857,
+  "<|union_pattern_py -> true_py|>": 152926,
+  "<|union_pattern_py -> tuple_pattern_py|>": 152997,
+  "<|union_pattern_py -> |_ter|>": 152880,
+  "<|union_type_py -> type_py |_ter type_py |>": 152570,
+  "<|value_py -> as_pattern_py |>": 151803,
+  "<|value_py -> attribute_py |>": 152672,
+  "<|value_py -> await_py |>": 152255,
+  "<|value_py -> binary_operator_py |>": 152238,
+  "<|value_py -> boolean_operator_py |>": 152685,
+  "<|value_py -> call_py |>": 152224,
+  "<|value_py -> case_pattern_py |>": 151733,
+  "<|value_py -> comparison_operator_py |>": 152554,
+  "<|value_py -> conditional_expression_py |>": 152160,
+  "<|value_py -> dictionary_comprehension_py |>": 152651,
+  "<|value_py -> dictionary_py |>": 151729,
+  "<|value_py -> ellipsis_py |>": 151861,
+  "<|value_py -> false_py |>": 152590,
+  "<|value_py -> float_py |>": 152121,
+  "<|value_py -> generator_expression_py |>": 151922,
+  "<|value_py -> identifier_py |>": 152399,
+  "<|value_py -> identifier_ter |>": 152089,
+  "<|value_py -> integer_py |>": 152149,
+  "<|value_py -> lambda_py |>": 152418,
+  "<|value_py -> list_comprehension_py |>": 152678,
+  "<|value_py -> list_py |>": 151682,
+  "<|value_py -> list_splat_py |>": 152321,
+  "<|value_py -> none_py |>": 152185,
+  "<|value_py -> not_operator_py |>": 152845,
+  "<|value_py -> parenthesized_expression_py |>": 151927,
+  "<|value_py -> set_comprehension_py |>": 151754,
+  "<|value_py -> set_py |>": 151938,
+  "<|value_py -> string_literal_py |>": 152498,
+  "<|value_py -> subscript_py |>": 151826,
+  "<|value_py -> true_py |>": 151875,
+  "<|value_py -> tuple_py |>": 152345,
+  "<|value_py -> unary_operator_py |>": 151830,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652,
+  "<|while_statement_py -> while_ter condition_py :_ter body_py alternative_py |>": 152371,
+  "<|while_statement_py -> while_ter condition_py :_ter body_py |>": 152740,
+  "<|wildcard_import_py -> *_ter |>": 151747,
+  "<|with_clause_py -> (_ter|>": 152630,
+  "<|with_clause_py -> )_ter|>": 152574,
+  "<|with_clause_py -> ,_ter|>": 152693,
+  "<|with_clause_py -> End |>": 151739,
+  "<|with_clause_py -> with_item_py|>": 152077,
+  "<|with_item_py -> value_py |>": 152339,
+  "<|with_statement_py -> async_ter with_ter with_clause_py :_ter body_py |>": 151986,
+  "<|with_statement_py -> with_ter with_clause_py :_ter body_py |>": 152606,
+  "<|yield_py -> yield_ter attribute_py |>": 152180,
+  "<|yield_py -> yield_ter await_py |>": 151744,
+  "<|yield_py -> yield_ter binary_operator_py |>": 152228,
+  "<|yield_py -> yield_ter boolean_operator_py |>": 152937,
+  "<|yield_py -> yield_ter call_py |>": 152811,
+  "<|yield_py -> yield_ter comparison_operator_py |>": 152095,
+  "<|yield_py -> yield_ter conditional_expression_py |>": 152337,
+  "<|yield_py -> yield_ter dictionary_comprehension_py |>": 152616,
+  "<|yield_py -> yield_ter dictionary_py |>": 151727,
+  "<|yield_py -> yield_ter expression_list_py |>": 152654,
+  "<|yield_py -> yield_ter false_py |>": 151971,
+  "<|yield_py -> yield_ter float_py |>": 151935,
+  "<|yield_py -> yield_ter from_ter attribute_py |>": 152756,
+  "<|yield_py -> yield_ter from_ter binary_operator_py |>": 152400,
+  "<|yield_py -> yield_ter from_ter call_py |>": 152351,
+  "<|yield_py -> yield_ter from_ter conditional_expression_py |>": 151786,
+  "<|yield_py -> yield_ter from_ter dictionary_comprehension_py |>": 152954,
+  "<|yield_py -> yield_ter from_ter dictionary_py |>": 152970,
+  "<|yield_py -> yield_ter from_ter generator_expression_py |>": 151699,
+  "<|yield_py -> yield_ter from_ter identifier_py |>": 152027,
+  "<|yield_py -> yield_ter from_ter list_comprehension_py |>": 151809,
+  "<|yield_py -> yield_ter from_ter list_py |>": 152486,
+  "<|yield_py -> yield_ter from_ter parenthesized_expression_py |>": 152974,
+  "<|yield_py -> yield_ter from_ter set_py |>": 153068,
+  "<|yield_py -> yield_ter from_ter string_literal_py |>": 152966,
+  "<|yield_py -> yield_ter from_ter subscript_py |>": 152633,
+  "<|yield_py -> yield_ter from_ter tuple_py |>": 152469,
+  "<|yield_py -> yield_ter generator_expression_py |>": 152494,
+  "<|yield_py -> yield_ter identifier_py |>": 151876,
+  "<|yield_py -> yield_ter identifier_ter |>": 153031,
+  "<|yield_py -> yield_ter integer_py |>": 152239,
+  "<|yield_py -> yield_ter lambda_py |>": 152824,
+  "<|yield_py -> yield_ter list_comprehension_py |>": 152426,
+  "<|yield_py -> yield_ter list_py |>": 152860,
+  "<|yield_py -> yield_ter none_py |>": 152201,
+  "<|yield_py -> yield_ter not_operator_py |>": 152951,
+  "<|yield_py -> yield_ter parenthesized_expression_py |>": 152104,
+  "<|yield_py -> yield_ter set_comprehension_py |>": 153066,
+  "<|yield_py -> yield_ter set_py |>": 152940,
+  "<|yield_py -> yield_ter string_literal_py |>": 152601,
+  "<|yield_py -> yield_ter subscript_py |>": 152531,
+  "<|yield_py -> yield_ter true_py |>": 152870,
+  "<|yield_py -> yield_ter tuple_py |>": 152253,
+  "<|yield_py -> yield_ter unary_operator_py |>": 152694,
+  "<|yield_py -> yield_ter |>": 151962,
+  "<|}_py -> _ter |>": 152305
+}

checkpoint-100/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/share/liangqingyuan/GrammarCoder14B/Ablation/HFmodels14B/checkpoints-2500",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 153078
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

checkpoint-100/latest

@@ -0,0 +1 @@
+global_step100

checkpoint-100/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71dface7278e0c363846ebdd2369913257f9b8d6f9588ae40a1cc5c98083d9c6
+size 4996594560

checkpoint-100/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84c8d0bea630aee72d7fb22c41d29b8ad1036d771590525ce57736f001518a7
+size 4954847240

checkpoint-100/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a029dd42c0b315d9312349d7fcdaeabe5abb620e459363eda8eaac36ee5ffdad
+size 4954847280

checkpoint-100/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1193d84083846ff6bc37bed750c79a76714954e9fa69c4b83a6f4c1cdc5aabaf
+size 4954847280

checkpoint-100/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549de054a33dae92c343e09f331e4510616d3b5201cfe311c2e74d69f319ced2
+size 4954847280

checkpoint-100/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386a4df83a83187f622a394927d4026e633099e5d51265236ed5fb76c9db38ff
+size 4744916456

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29560834048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0728b56dab7abb5ef8a0d4bae3519c5767c97467bdd886d26bf19cc8599d0312
+size 15984

checkpoint-100/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:532d1ab071177c2e9d0cc3435d6314c1777a0356f9ce1a5d8f10fbe5f8fd8926
+size 15997

checkpoint-100/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a089513416d3ed447265187782ec1194ac2303155b941284463976c62bf3d9b
+size 15997

checkpoint-100/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a87db6b16c9956496c45bf5c81750dc2349e157e60e544e5d256bb957be1243
+size 15997

checkpoint-100/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d5fe5d1b92643a3c3dd35cf2f0cbfa4a92599fe3ccbd8941395c1550f088aa
+size 15997

checkpoint-100/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a08278e808af796415aac256bf0c1e8619db1f0f025ff15775cd3b8d02bd59
+size 15997

checkpoint-100/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88600b3520001a5a7e82c0e184d278b46492fda5424ea22ea243af15b40b2e82
+size 15997

checkpoint-100/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a5825e92eb7518856e88ce648529dc0597c32a5f52764f0361a119217a4dfb
+size 15997

checkpoint-100/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30bd2cfa327fb55a93d390d852db109e0a2e1f102ecabf520870cbc79ca95ad
+size 15997

checkpoint-100/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c95f2456fa4473e7231ab94b79ecbc3c126d31d3a94c61f86ee6125b547456
+size 15997

checkpoint-100/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301f380300f7ae9a581c304ac407794ecff9d66e6c9c55ff6cffcfc8d94690a4
+size 15997

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e481d4ef1546694da7337f6bb6c658b866dcb79b85deeb477da0d27ebe851e
+size 15984

checkpoint-100/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2e90afb8f9481396fa1f82913f7fb908e83e63bf2a38a6f6d2b869ca1d06db
+size 15997

checkpoint-100/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fafcbe672a0f62668f219b7ae7b88ddc86330086a2eca82505408964d61498
+size 15997

checkpoint-100/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8f851ca87ff60251262afa155c3ab50fc55615fb72c857120fd7fa3fe3177c
+size 15997

checkpoint-100/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d8cd100c48bfcfbf5c8a5164b02d5879f69b5a6276dae705a9c60de9a079c1
+size 15997

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353c60be37ea56fc992fca446598ceca5d1fd002aa3bd6dbb9ad740e6f47ebb3
+size 15984

checkpoint-100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9107fe964ba7205e354084b85210e5a5ea1c98cfd4d38adb9cd3926945dcae4
+size 15984

checkpoint-100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d1bb1abee38b92e53f3f23549b642ce0f1edcdccf7b6129847ac61636e96d5
+size 15984

checkpoint-100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd5516048e20f36959601574e29e40106085a7d3cdc7bf425ce5e84633490e6
+size 15984

checkpoint-100/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2c46927fc06939b4c976a01e4b95dec1f8b98ceaea86d31a5d756fc30ff006
+size 15984

checkpoint-100/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87544a1ecb93bba51fc38c978d8a027be1635c93e80f7f0679c1154bc76e16d3
+size 15984

checkpoint-100/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f51e1e81143bcfd2cfd36874b3b7606bb4a14aac945154b167b31a816d9f450
+size 15984

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea8f7bf259f56a56e06c38b699b5deb743822f335dcbc11126f8369cc6c25bb
+size 1064

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247bb2ab36e90831d6bad332af189c03543cde3ae90999f3be15aaedb240c1eb
+size 11726578

checkpoint-100/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.005333646240579447,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.3336462405794474e-05,
+      "grad_norm": 0.398686021566391,
+      "learning_rate": 5e-06,
+      "loss": 0.1308,
+      "step": 1
+    },
+    {
+      "epoch": 0.00010667292481158895,
+      "grad_norm": 0.46305230259895325,
+      "learning_rate": 1e-05,
+      "loss": 0.1388,
+      "step": 2
+    },
+    {
+      "epoch": 0.00016000938721738342,
+      "grad_norm": 0.3536907136440277,
+      "learning_rate": 1.5e-05,
+      "loss": 0.1216,
+      "step": 3
+    },
+    {
+      "epoch": 0.0002133458496231779,
+      "grad_norm": 0.32838913798332214,
+      "learning_rate": 2e-05,
+      "loss": 0.124,
+      "step": 4
+    },
+    {
+      "epoch": 0.00026668231202897234,
+      "grad_norm": 0.3058461546897888,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1144,
+      "step": 5
+    },
+    {
+      "epoch": 0.00032001877443476684,
+      "grad_norm": 0.3052152097225189,
+      "learning_rate": 3e-05,
+      "loss": 0.109,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003733552368405613,
+      "grad_norm": 0.3326779901981354,
+      "learning_rate": 3.5e-05,
+      "loss": 0.1233,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004266916992463558,
+      "grad_norm": 0.3231862187385559,
+      "learning_rate": 4e-05,
+      "loss": 0.1099,
+      "step": 8
+    },
+    {
+      "epoch": 0.00048002816165215024,
+      "grad_norm": 0.32896554470062256,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1199,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005333646240579447,
+      "grad_norm": 0.3078831434249878,
+      "learning_rate": 5e-05,
+      "loss": 0.1042,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005867010864637392,
+      "grad_norm": 0.2900382876396179,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1108,
+      "step": 11
+    },
+    {
+      "epoch": 0.0006400375488695337,
+      "grad_norm": 0.28514525294303894,
+      "learning_rate": 6e-05,
+      "loss": 0.1092,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006933740112753282,
+      "grad_norm": 0.30242955684661865,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.1104,
+      "step": 13
+    },
+    {
+      "epoch": 0.0007467104736811226,
+      "grad_norm": 0.3053489029407501,
+      "learning_rate": 7e-05,
+      "loss": 0.1209,
+      "step": 14
+    },
+    {
+      "epoch": 0.0008000469360869171,
+      "grad_norm": 0.32302212715148926,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1273,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008533833984927116,
+      "grad_norm": 0.29552462697029114,
+      "learning_rate": 8e-05,
+      "loss": 0.12,
+      "step": 16
+    },
+    {
+      "epoch": 0.0009067198608985061,
+      "grad_norm": 0.33688342571258545,
+      "learning_rate": 8.5e-05,
+      "loss": 0.135,
+      "step": 17
+    },
+    {
+      "epoch": 0.0009600563233043005,
+      "grad_norm": 0.29682204127311707,
+      "learning_rate": 9e-05,
+      "loss": 0.1224,
+      "step": 18
+    },
+    {
+      "epoch": 0.001013392785710095,
+      "grad_norm": 0.33479437232017517,
+      "learning_rate": 9.5e-05,
+      "loss": 0.143,
+      "step": 19
+    },
+    {
+      "epoch": 0.0010667292481158894,
+      "grad_norm": 0.3345559537410736,
+      "learning_rate": 0.0001,
+      "loss": 0.1197,
+      "step": 20
+    },
+    {
+      "epoch": 0.001120065710521684,
+      "grad_norm": 0.34470704197883606,
+      "learning_rate": 9.999999982431556e-05,
+      "loss": 0.1341,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011734021729274784,
+      "grad_norm": 0.3448582887649536,
+      "learning_rate": 9.999999929726225e-05,
+      "loss": 0.1404,
+      "step": 22
+    },
+    {
+      "epoch": 0.001226738635333273,
+      "grad_norm": 0.33284544944763184,
+      "learning_rate": 9.999999841884006e-05,
+      "loss": 0.1399,
+      "step": 23
+    },
+    {
+      "epoch": 0.0012800750977390674,
+      "grad_norm": 0.3286615014076233,
+      "learning_rate": 9.999999718904902e-05,
+      "loss": 0.1353,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013334115601448618,
+      "grad_norm": 0.3405831456184387,
+      "learning_rate": 9.999999560788912e-05,
+      "loss": 0.1527,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013867480225506564,
+      "grad_norm": 0.3199956715106964,
+      "learning_rate": 9.999999367536037e-05,
+      "loss": 0.1469,
+      "step": 26
+    },
+    {
+      "epoch": 0.0014400844849564508,
+      "grad_norm": 0.3393600881099701,
+      "learning_rate": 9.999999139146278e-05,
+      "loss": 0.1536,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014934209473622452,
+      "grad_norm": 0.3263189196586609,
+      "learning_rate": 9.99999887561964e-05,
+      "loss": 0.1498,
+      "step": 28
+    },
+    {
+      "epoch": 0.0015467574097680398,
+      "grad_norm": 0.31700044870376587,
+      "learning_rate": 9.999998576956121e-05,
+      "loss": 0.1391,
+      "step": 29
+    },
+    {
+      "epoch": 0.0016000938721738342,
+      "grad_norm": 0.33871933817863464,
+      "learning_rate": 9.999998243155724e-05,
+      "loss": 0.159,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016534303345796288,
+      "grad_norm": 0.34099170565605164,
+      "learning_rate": 9.999997874218452e-05,
+      "loss": 0.1543,
+      "step": 31
+    },
+    {
+      "epoch": 0.0017067667969854232,
+      "grad_norm": 0.33778145909309387,
+      "learning_rate": 9.999997470144308e-05,
+      "loss": 0.1566,
+      "step": 32
+    },
+    {
+      "epoch": 0.0017601032593912175,
+      "grad_norm": 0.32202789187431335,
+      "learning_rate": 9.999997030933294e-05,
+      "loss": 0.1688,
+      "step": 33
+    },
+    {
+      "epoch": 0.0018134397217970122,
+      "grad_norm": 0.3160647749900818,
+      "learning_rate": 9.999996556585412e-05,
+      "loss": 0.1645,
+      "step": 34
+    },
+    {
+      "epoch": 0.0018667761842028065,
+      "grad_norm": 0.3506312072277069,
+      "learning_rate": 9.999996047100669e-05,
+      "loss": 0.1764,
+      "step": 35
+    },
+    {
+      "epoch": 0.001920112646608601,
+      "grad_norm": 0.3370567262172699,
+      "learning_rate": 9.999995502479064e-05,
+      "loss": 0.1817,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019734491090143956,
+      "grad_norm": 0.3320629596710205,
+      "learning_rate": 9.999994922720604e-05,
+      "loss": 0.1558,
+      "step": 37
+    },
+    {
+      "epoch": 0.00202678557142019,
+      "grad_norm": 0.3061317503452301,
+      "learning_rate": 9.999994307825292e-05,
+      "loss": 0.1645,
+      "step": 38
+    },
+    {
+      "epoch": 0.0020801220338259843,
+      "grad_norm": 0.3522307276725769,
+      "learning_rate": 9.999993657793131e-05,
+      "loss": 0.1795,
+      "step": 39
+    },
+    {
+      "epoch": 0.0021334584962317787,
+      "grad_norm": 0.33675846457481384,
+      "learning_rate": 9.999992972624131e-05,
+      "loss": 0.1695,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021867949586375736,
+      "grad_norm": 0.34461385011672974,
+      "learning_rate": 9.999992252318289e-05,
+      "loss": 0.1698,
+      "step": 41
+    },
+    {
+      "epoch": 0.002240131421043368,
+      "grad_norm": 0.3509563207626343,
+      "learning_rate": 9.999991496875616e-05,
+      "loss": 0.1857,
+      "step": 42
+    },
+    {
+      "epoch": 0.0022934678834491623,
+      "grad_norm": 0.34643200039863586,
+      "learning_rate": 9.999990706296113e-05,
+      "loss": 0.1855,
+      "step": 43
+    },
+    {
+      "epoch": 0.0023468043458549567,
+      "grad_norm": 0.33536601066589355,
+      "learning_rate": 9.99998988057979e-05,
+      "loss": 0.1767,
+      "step": 44
+    },
+    {
+      "epoch": 0.002400140808260751,
+      "grad_norm": 0.3312433362007141,
+      "learning_rate": 9.99998901972665e-05,
+      "loss": 0.1922,
+      "step": 45
+    },
+    {
+      "epoch": 0.002453477270666546,
+      "grad_norm": 0.34569883346557617,
+      "learning_rate": 9.999988123736699e-05,
+      "loss": 0.1777,
+      "step": 46
+    },
+    {
+      "epoch": 0.0025068137330723403,
+      "grad_norm": 0.3153592646121979,
+      "learning_rate": 9.999987192609944e-05,
+      "loss": 0.1669,
+      "step": 47
+    },
+    {
+      "epoch": 0.0025601501954781347,
+      "grad_norm": 0.3480944037437439,
+      "learning_rate": 9.999986226346392e-05,
+      "loss": 0.1779,
+      "step": 48
+    },
+    {
+      "epoch": 0.002613486657883929,
+      "grad_norm": 0.35337212681770325,
+      "learning_rate": 9.999985224946049e-05,
+      "loss": 0.1863,
+      "step": 49
+    },
+    {
+      "epoch": 0.0026668231202897235,
+      "grad_norm": 0.3431400656700134,
+      "learning_rate": 9.999984188408922e-05,
+      "loss": 0.1983,
+      "step": 50
+    },
+    {
+      "epoch": 0.0027201595826955183,
+      "grad_norm": 0.3314003348350525,
+      "learning_rate": 9.999983116735019e-05,
+      "loss": 0.1838,
+      "step": 51
+    },
+    {
+      "epoch": 0.0027734960451013127,
+      "grad_norm": 0.3390146493911743,
+      "learning_rate": 9.999982009924345e-05,
+      "loss": 0.1826,
+      "step": 52
+    },
+    {
+      "epoch": 0.002826832507507107,
+      "grad_norm": 0.35979676246643066,
+      "learning_rate": 9.999980867976912e-05,
+      "loss": 0.1967,
+      "step": 53
+    },
+    {
+      "epoch": 0.0028801689699129015,
+      "grad_norm": 0.39572709798812866,
+      "learning_rate": 9.999979690892725e-05,
+      "loss": 0.1893,
+      "step": 54
+    },
+    {
+      "epoch": 0.002933505432318696,
+      "grad_norm": 0.3344902992248535,
+      "learning_rate": 9.999978478671794e-05,
+      "loss": 0.1905,
+      "step": 55
+    },
+    {
+      "epoch": 0.0029868418947244903,
+      "grad_norm": 0.32258379459381104,
+      "learning_rate": 9.999977231314127e-05,
+      "loss": 0.1765,
+      "step": 56
+    },
+    {
+      "epoch": 0.003040178357130285,
+      "grad_norm": 0.32133936882019043,
+      "learning_rate": 9.999975948819731e-05,
+      "loss": 0.1855,
+      "step": 57
+    },
+    {
+      "epoch": 0.0030935148195360795,
+      "grad_norm": 0.33931997418403625,
+      "learning_rate": 9.999974631188618e-05,
+      "loss": 0.1881,
+      "step": 58
+    },
+    {
+      "epoch": 0.003146851281941874,
+      "grad_norm": 0.3421045243740082,
+      "learning_rate": 9.999973278420795e-05,
+      "loss": 0.1937,
+      "step": 59
+    },
+    {
+      "epoch": 0.0032001877443476683,
+      "grad_norm": 0.337239146232605,
+      "learning_rate": 9.999971890516272e-05,
+      "loss": 0.1947,
+      "step": 60
+    },
+    {
+      "epoch": 0.0032535242067534627,
+      "grad_norm": 0.3348175585269928,
+      "learning_rate": 9.999970467475059e-05,
+      "loss": 0.2015,
+      "step": 61
+    },
+    {
+      "epoch": 0.0033068606691592575,
+      "grad_norm": 0.33285388350486755,
+      "learning_rate": 9.999969009297165e-05,
+      "loss": 0.1954,
+      "step": 62
+    },
+    {
+      "epoch": 0.003360197131565052,
+      "grad_norm": 0.33577030897140503,
+      "learning_rate": 9.999967515982604e-05,
+      "loss": 0.2033,
+      "step": 63
+    },
+    {
+      "epoch": 0.0034135335939708463,
+      "grad_norm": 0.3373951315879822,
+      "learning_rate": 9.999965987531382e-05,
+      "loss": 0.2059,
+      "step": 64
+    },
+    {
+      "epoch": 0.0034668700563766407,
+      "grad_norm": 0.3341216742992401,
+      "learning_rate": 9.99996442394351e-05,
+      "loss": 0.191,
+      "step": 65
+    },
+    {
+      "epoch": 0.003520206518782435,
+      "grad_norm": 0.3183084726333618,
+      "learning_rate": 9.999962825219002e-05,
+      "loss": 0.1917,
+      "step": 66
+    },
+    {
+      "epoch": 0.00357354298118823,
+      "grad_norm": 0.33498549461364746,
+      "learning_rate": 9.999961191357869e-05,
+      "loss": 0.1895,
+      "step": 67
+    },
+    {
+      "epoch": 0.0036268794435940243,
+      "grad_norm": 0.3271574079990387,
+      "learning_rate": 9.999959522360118e-05,
+      "loss": 0.2054,
+      "step": 68
+    },
+    {
+      "epoch": 0.0036802159059998187,
+      "grad_norm": 0.3310222923755646,
+      "learning_rate": 9.999957818225768e-05,
+      "loss": 0.2013,
+      "step": 69
+    },
+    {
+      "epoch": 0.003733552368405613,
+      "grad_norm": 0.34026429057121277,
+      "learning_rate": 9.999956078954822e-05,
+      "loss": 0.2186,
+      "step": 70
+    },
+    {
+      "epoch": 0.0037868888308114075,
+      "grad_norm": 0.3307226300239563,
+      "learning_rate": 9.999954304547301e-05,
+      "loss": 0.2007,
+      "step": 71
+    },
+    {
+      "epoch": 0.003840225293217202,
+      "grad_norm": 0.3343660533428192,
+      "learning_rate": 9.999952495003212e-05,
+      "loss": 0.2075,
+      "step": 72
+    },
+    {
+      "epoch": 0.0038935617556229967,
+      "grad_norm": 0.3603450357913971,
+      "learning_rate": 9.999950650322569e-05,
+      "loss": 0.2156,
+      "step": 73
+    },
+    {
+      "epoch": 0.003946898218028791,
+      "grad_norm": 0.335757315158844,
+      "learning_rate": 9.999948770505386e-05,
+      "loss": 0.203,
+      "step": 74
+    },
+    {
+      "epoch": 0.0040002346804345855,
+      "grad_norm": 0.3302127718925476,
+      "learning_rate": 9.999946855551675e-05,
+      "loss": 0.1992,
+      "step": 75
+    },
+    {
+      "epoch": 0.00405357114284038,
+      "grad_norm": 0.3287745714187622,
+      "learning_rate": 9.99994490546145e-05,
+      "loss": 0.2044,
+      "step": 76
+    },
+    {
+      "epoch": 0.004106907605246174,
+      "grad_norm": 0.31489625573158264,
+      "learning_rate": 9.999942920234725e-05,
+      "loss": 0.2024,
+      "step": 77
+    },
+    {
+      "epoch": 0.004160244067651969,
+      "grad_norm": 0.3128495216369629,
+      "learning_rate": 9.999940899871513e-05,
+      "loss": 0.2082,
+      "step": 78
+    },
+    {
+      "epoch": 0.004213580530057763,
+      "grad_norm": 0.31686297059059143,
+      "learning_rate": 9.999938844371829e-05,
+      "loss": 0.2145,
+      "step": 79
+    },
+    {
+      "epoch": 0.0042669169924635575,
+      "grad_norm": 0.3330387473106384,
+      "learning_rate": 9.999936753735687e-05,
+      "loss": 0.2022,
+      "step": 80
+    },
+    {
+      "epoch": 0.004320253454869353,
+      "grad_norm": 0.34814751148223877,
+      "learning_rate": 9.999934627963103e-05,
+      "loss": 0.2192,
+      "step": 81
+    },
+    {
+      "epoch": 0.004373589917275147,
+      "grad_norm": 0.3250124454498291,
+      "learning_rate": 9.999932467054089e-05,
+      "loss": 0.2029,
+      "step": 82
+    },
+    {
+      "epoch": 0.0044269263796809415,
+      "grad_norm": 0.3646756410598755,
+      "learning_rate": 9.999930271008663e-05,
+      "loss": 0.2203,
+      "step": 83
+    },
+    {
+      "epoch": 0.004480262842086736,
+      "grad_norm": 0.3267667889595032,
+      "learning_rate": 9.99992803982684e-05,
+      "loss": 0.2078,
+      "step": 84
+    },
+    {
+      "epoch": 0.00453359930449253,
+      "grad_norm": 0.32010674476623535,
+      "learning_rate": 9.999925773508634e-05,
+      "loss": 0.2041,
+      "step": 85
+    },
+    {
+      "epoch": 0.004586935766898325,
+      "grad_norm": 0.3199160695075989,
+      "learning_rate": 9.999923472054063e-05,
+      "loss": 0.2119,
+      "step": 86
+    },
+    {
+      "epoch": 0.004640272229304119,
+      "grad_norm": 0.3363480269908905,
+      "learning_rate": 9.99992113546314e-05,
+      "loss": 0.2102,
+      "step": 87
+    },
+    {
+      "epoch": 0.0046936086917099135,
+      "grad_norm": 0.3485029935836792,
+      "learning_rate": 9.999918763735886e-05,
+      "loss": 0.2146,
+      "step": 88
+    },
+    {
+      "epoch": 0.004746945154115708,
+      "grad_norm": 0.3307000994682312,
+      "learning_rate": 9.999916356872314e-05,
+      "loss": 0.2006,
+      "step": 89
+    },
+    {
+      "epoch": 0.004800281616521502,
+      "grad_norm": 0.32731881737709045,
+      "learning_rate": 9.999913914872443e-05,
+      "loss": 0.1934,
+      "step": 90
+    },
+    {
+      "epoch": 0.004853618078927297,
+      "grad_norm": 0.3216370642185211,
+      "learning_rate": 9.99991143773629e-05,
+      "loss": 0.2149,
+      "step": 91
+    },
+    {
+      "epoch": 0.004906954541333092,
+      "grad_norm": 0.3118319809436798,
+      "learning_rate": 9.999908925463872e-05,
+      "loss": 0.2066,
+      "step": 92
+    },
+    {
+      "epoch": 0.004960291003738886,
+      "grad_norm": 0.3115937411785126,
+      "learning_rate": 9.999906378055205e-05,
+      "loss": 0.2016,
+      "step": 93
+    },
+    {
+      "epoch": 0.005013627466144681,
+      "grad_norm": 0.31390756368637085,
+      "learning_rate": 9.999903795510308e-05,
+      "loss": 0.227,
+      "step": 94
+    },
+    {
+      "epoch": 0.005066963928550475,
+      "grad_norm": 0.3215806484222412,
+      "learning_rate": 9.999901177829201e-05,
+      "loss": 0.2139,
+      "step": 95
+    },
+    {
+      "epoch": 0.0051203003909562695,
+      "grad_norm": 0.32381314039230347,
+      "learning_rate": 9.9998985250119e-05,
+      "loss": 0.2119,
+      "step": 96
+    },
+    {
+      "epoch": 0.005173636853362064,
+      "grad_norm": 0.32022613286972046,
+      "learning_rate": 9.999895837058425e-05,
+      "loss": 0.2036,
+      "step": 97
+    },
+    {
+      "epoch": 0.005226973315767858,
+      "grad_norm": 0.3156028985977173,
+      "learning_rate": 9.999893113968795e-05,
+      "loss": 0.2058,
+      "step": 98
+    },
+    {
+      "epoch": 0.005280309778173653,
+      "grad_norm": 0.3254660665988922,
+      "learning_rate": 9.999890355743027e-05,
+      "loss": 0.2064,
+      "step": 99
+    },
+    {
+      "epoch": 0.005333646240579447,
+      "grad_norm": 0.3044165074825287,
+      "learning_rate": 9.999887562381143e-05,
+      "loss": 0.2081,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 37496,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3964461642486907e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b3c0753337bc9ead038e6c2b8053a712a7d54a709cb6ce97be48fead3df609
+size 7544

checkpoint-100/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

trainer_log.jsonl

@@ -0,0 +1,126 @@
+{"current_steps": 1, "total_steps": 37496, "loss": 0.1308, "lr": 5e-06, "epoch": 5.3336462405794474e-05, "percentage": 0.0, "elapsed_time": "0:03:05", "remaining_time": "80 days, 9:46:02"}
+{"current_steps": 2, "total_steps": 37496, "loss": 0.1388, "lr": 1e-05, "epoch": 0.00010667292481158895, "percentage": 0.01, "elapsed_time": "0:05:53", "remaining_time": "76 days, 18:26:52"}
+{"current_steps": 3, "total_steps": 37496, "loss": 0.1216, "lr": 1.5e-05, "epoch": 0.00016000938721738342, "percentage": 0.01, "elapsed_time": "0:08:41", "remaining_time": "75 days, 11:17:40"}
+{"current_steps": 4, "total_steps": 37496, "loss": 0.124, "lr": 2e-05, "epoch": 0.0002133458496231779, "percentage": 0.01, "elapsed_time": "0:11:29", "remaining_time": "74 days, 18:35:26"}
+{"current_steps": 5, "total_steps": 37496, "loss": 0.1144, "lr": 2.5e-05, "epoch": 0.00026668231202897234, "percentage": 0.01, "elapsed_time": "0:14:18", "remaining_time": "74 days, 12:44:06"}
+{"current_steps": 6, "total_steps": 37496, "loss": 0.109, "lr": 3e-05, "epoch": 0.00032001877443476684, "percentage": 0.02, "elapsed_time": "0:17:07", "remaining_time": "74 days, 7:11:24"}
+{"current_steps": 7, "total_steps": 37496, "loss": 0.1233, "lr": 3.5e-05, "epoch": 0.0003733552368405613, "percentage": 0.02, "elapsed_time": "0:19:54", "remaining_time": "74 days, 0:22:51"}
+{"current_steps": 8, "total_steps": 37496, "loss": 0.1099, "lr": 4e-05, "epoch": 0.0004266916992463558, "percentage": 0.02, "elapsed_time": "0:22:43", "remaining_time": "73 days, 22:58:16"}
+{"current_steps": 9, "total_steps": 37496, "loss": 0.1199, "lr": 4.5e-05, "epoch": 0.00048002816165215024, "percentage": 0.02, "elapsed_time": "0:25:33", "remaining_time": "73 days, 22:47:39"}
+{"current_steps": 10, "total_steps": 37496, "loss": 0.1042, "lr": 5e-05, "epoch": 0.0005333646240579447, "percentage": 0.03, "elapsed_time": "0:28:25", "remaining_time": "74 days, 0:16:53"}
+{"current_steps": 11, "total_steps": 37496, "loss": 0.1108, "lr": 5.500000000000001e-05, "epoch": 0.0005867010864637392, "percentage": 0.03, "elapsed_time": "0:31:14", "remaining_time": "73 days, 21:59:36"}
+{"current_steps": 12, "total_steps": 37496, "loss": 0.1092, "lr": 6e-05, "epoch": 0.0006400375488695337, "percentage": 0.03, "elapsed_time": "0:34:05", "remaining_time": "73 days, 22:46:40"}
+{"current_steps": 13, "total_steps": 37496, "loss": 0.1104, "lr": 6.500000000000001e-05, "epoch": 0.0006933740112753282, "percentage": 0.03, "elapsed_time": "0:36:55", "remaining_time": "73 days, 22:27:45"}
+{"current_steps": 14, "total_steps": 37496, "loss": 0.1209, "lr": 7e-05, "epoch": 0.0007467104736811226, "percentage": 0.04, "elapsed_time": "0:39:43", "remaining_time": "73 days, 20:23:49"}
+{"current_steps": 15, "total_steps": 37496, "loss": 0.1273, "lr": 7.500000000000001e-05, "epoch": 0.0008000469360869171, "percentage": 0.04, "elapsed_time": "0:42:31", "remaining_time": "73 days, 18:53:06"}
+{"current_steps": 16, "total_steps": 37496, "loss": 0.12, "lr": 8e-05, "epoch": 0.0008533833984927116, "percentage": 0.04, "elapsed_time": "0:45:21", "remaining_time": "73 days, 18:32:57"}
+{"current_steps": 17, "total_steps": 37496, "loss": 0.135, "lr": 8.5e-05, "epoch": 0.0009067198608985061, "percentage": 0.05, "elapsed_time": "0:48:09", "remaining_time": "73 days, 17:24:19"}
+{"current_steps": 18, "total_steps": 37496, "loss": 0.1224, "lr": 9e-05, "epoch": 0.0009600563233043005, "percentage": 0.05, "elapsed_time": "0:51:00", "remaining_time": "73 days, 18:01:53"}
+{"current_steps": 19, "total_steps": 37496, "loss": 0.143, "lr": 9.5e-05, "epoch": 0.001013392785710095, "percentage": 0.05, "elapsed_time": "0:53:48", "remaining_time": "73 days, 16:57:00"}
+{"current_steps": 20, "total_steps": 37496, "loss": 0.1197, "lr": 0.0001, "epoch": 0.0010667292481158894, "percentage": 0.05, "elapsed_time": "0:56:36", "remaining_time": "73 days, 15:51:30"}
+{"current_steps": 21, "total_steps": 37496, "loss": 0.1341, "lr": 9.999999982431556e-05, "epoch": 0.001120065710521684, "percentage": 0.06, "elapsed_time": "0:59:26", "remaining_time": "73 days, 15:48:25"}
+{"current_steps": 22, "total_steps": 37496, "loss": 0.1404, "lr": 9.999999929726225e-05, "epoch": 0.0011734021729274784, "percentage": 0.06, "elapsed_time": "1:02:15", "remaining_time": "73 days, 15:22:01"}
+{"current_steps": 23, "total_steps": 37496, "loss": 0.1399, "lr": 9.999999841884006e-05, "epoch": 0.001226738635333273, "percentage": 0.06, "elapsed_time": "1:05:04", "remaining_time": "73 days, 14:51:33"}
+{"current_steps": 24, "total_steps": 37496, "loss": 0.1353, "lr": 9.999999718904902e-05, "epoch": 0.0012800750977390674, "percentage": 0.06, "elapsed_time": "1:07:52", "remaining_time": "73 days, 14:17:36"}
+{"current_steps": 25, "total_steps": 37496, "loss": 0.1527, "lr": 9.999999560788912e-05, "epoch": 0.0013334115601448618, "percentage": 0.07, "elapsed_time": "1:10:42", "remaining_time": "73 days, 14:11:11"}
+{"current_steps": 26, "total_steps": 37496, "loss": 0.1469, "lr": 9.999999367536037e-05, "epoch": 0.0013867480225506564, "percentage": 0.07, "elapsed_time": "1:13:32", "remaining_time": "73 days, 14:17:37"}
+{"current_steps": 27, "total_steps": 37496, "loss": 0.1536, "lr": 9.999999139146278e-05, "epoch": 0.0014400844849564508, "percentage": 0.07, "elapsed_time": "1:16:21", "remaining_time": "73 days, 13:54:50"}
+{"current_steps": 28, "total_steps": 37496, "loss": 0.1498, "lr": 9.99999887561964e-05, "epoch": 0.0014934209473622452, "percentage": 0.07, "elapsed_time": "1:19:09", "remaining_time": "73 days, 13:22:54"}
+{"current_steps": 29, "total_steps": 37496, "loss": 0.1391, "lr": 9.999998576956121e-05, "epoch": 0.0015467574097680398, "percentage": 0.08, "elapsed_time": "1:21:59", "remaining_time": "73 days, 13:33:02"}
+{"current_steps": 30, "total_steps": 37496, "loss": 0.159, "lr": 9.999998243155724e-05, "epoch": 0.0016000938721738342, "percentage": 0.08, "elapsed_time": "1:24:53", "remaining_time": "73 days, 14:50:42"}
+{"current_steps": 31, "total_steps": 37496, "loss": 0.1543, "lr": 9.999997874218452e-05, "epoch": 0.0016534303345796288, "percentage": 0.08, "elapsed_time": "1:27:44", "remaining_time": "73 days, 15:11:24"}
+{"current_steps": 32, "total_steps": 37496, "loss": 0.1566, "lr": 9.999997470144308e-05, "epoch": 0.0017067667969854232, "percentage": 0.09, "elapsed_time": "1:30:36", "remaining_time": "73 days, 15:59:24"}
+{"current_steps": 33, "total_steps": 37496, "loss": 0.1688, "lr": 9.999997030933294e-05, "epoch": 0.0017601032593912175, "percentage": 0.09, "elapsed_time": "1:33:28", "remaining_time": "73 days, 16:33:40"}
+{"current_steps": 34, "total_steps": 37496, "loss": 0.1645, "lr": 9.999996556585412e-05, "epoch": 0.0018134397217970122, "percentage": 0.09, "elapsed_time": "1:36:20", "remaining_time": "73 days, 17:17:50"}
+{"current_steps": 35, "total_steps": 37496, "loss": 0.1764, "lr": 9.999996047100669e-05, "epoch": 0.0018667761842028065, "percentage": 0.09, "elapsed_time": "1:39:09", "remaining_time": "73 days, 16:50:41"}
+{"current_steps": 36, "total_steps": 37496, "loss": 0.1817, "lr": 9.999995502479064e-05, "epoch": 0.001920112646608601, "percentage": 0.1, "elapsed_time": "1:41:58", "remaining_time": "73 days, 16:28:32"}
+{"current_steps": 37, "total_steps": 37496, "loss": 0.1558, "lr": 9.999994922720604e-05, "epoch": 0.0019734491090143956, "percentage": 0.1, "elapsed_time": "1:44:47", "remaining_time": "73 days, 16:10:25"}
+{"current_steps": 38, "total_steps": 37496, "loss": 0.1645, "lr": 9.999994307825292e-05, "epoch": 0.00202678557142019, "percentage": 0.1, "elapsed_time": "1:47:38", "remaining_time": "73 days, 16:27:28"}
+{"current_steps": 39, "total_steps": 37496, "loss": 0.1795, "lr": 9.999993657793131e-05, "epoch": 0.0020801220338259843, "percentage": 0.1, "elapsed_time": "1:50:28", "remaining_time": "73 days, 16:20:47"}
+{"current_steps": 40, "total_steps": 37496, "loss": 0.1695, "lr": 9.999992972624131e-05, "epoch": 0.0021334584962317787, "percentage": 0.11, "elapsed_time": "1:53:17", "remaining_time": "73 days, 16:03:42"}
+{"current_steps": 41, "total_steps": 37496, "loss": 0.1698, "lr": 9.999992252318289e-05, "epoch": 0.0021867949586375736, "percentage": 0.11, "elapsed_time": "1:56:09", "remaining_time": "73 days, 16:41:51"}
+{"current_steps": 42, "total_steps": 37496, "loss": 0.1857, "lr": 9.999991496875616e-05, "epoch": 0.002240131421043368, "percentage": 0.11, "elapsed_time": "1:58:58", "remaining_time": "73 days, 16:22:44"}
+{"current_steps": 43, "total_steps": 37496, "loss": 0.1855, "lr": 9.999990706296113e-05, "epoch": 0.0022934678834491623, "percentage": 0.11, "elapsed_time": "2:01:47", "remaining_time": "73 days, 16:03:21"}
+{"current_steps": 44, "total_steps": 37496, "loss": 0.1767, "lr": 9.99998988057979e-05, "epoch": 0.0023468043458549567, "percentage": 0.12, "elapsed_time": "2:04:36", "remaining_time": "73 days, 15:41:44"}
+{"current_steps": 45, "total_steps": 37496, "loss": 0.1922, "lr": 9.99998901972665e-05, "epoch": 0.002400140808260751, "percentage": 0.12, "elapsed_time": "2:07:26", "remaining_time": "73 days, 15:47:33"}
+{"current_steps": 46, "total_steps": 37496, "loss": 0.1777, "lr": 9.999988123736699e-05, "epoch": 0.002453477270666546, "percentage": 0.12, "elapsed_time": "2:10:16", "remaining_time": "73 days, 15:45:12"}
+{"current_steps": 47, "total_steps": 37496, "loss": 0.1669, "lr": 9.999987192609944e-05, "epoch": 0.0025068137330723403, "percentage": 0.13, "elapsed_time": "2:13:06", "remaining_time": "73 days, 15:40:01"}
+{"current_steps": 48, "total_steps": 37496, "loss": 0.1779, "lr": 9.999986226346392e-05, "epoch": 0.0025601501954781347, "percentage": 0.13, "elapsed_time": "2:15:59", "remaining_time": "73 days, 16:12:23"}
+{"current_steps": 49, "total_steps": 37496, "loss": 0.1863, "lr": 9.999985224946049e-05, "epoch": 0.002613486657883929, "percentage": 0.13, "elapsed_time": "2:18:46", "remaining_time": "73 days, 15:36:11"}
+{"current_steps": 50, "total_steps": 37496, "loss": 0.1983, "lr": 9.999984188408922e-05, "epoch": 0.0026668231202897235, "percentage": 0.13, "elapsed_time": "2:21:35", "remaining_time": "73 days, 15:25:06"}
+{"current_steps": 51, "total_steps": 37496, "loss": 0.1838, "lr": 9.999983116735019e-05, "epoch": 0.0027201595826955183, "percentage": 0.14, "elapsed_time": "2:24:25", "remaining_time": "73 days, 15:24:19"}
+{"current_steps": 52, "total_steps": 37496, "loss": 0.1826, "lr": 9.999982009924345e-05, "epoch": 0.0027734960451013127, "percentage": 0.14, "elapsed_time": "2:27:16", "remaining_time": "73 days, 15:26:28"}
+{"current_steps": 53, "total_steps": 37496, "loss": 0.1967, "lr": 9.999980867976912e-05, "epoch": 0.002826832507507107, "percentage": 0.14, "elapsed_time": "2:30:05", "remaining_time": "73 days, 15:20:16"}
+{"current_steps": 54, "total_steps": 37496, "loss": 0.1893, "lr": 9.999979690892725e-05, "epoch": 0.0028801689699129015, "percentage": 0.14, "elapsed_time": "2:32:56", "remaining_time": "73 days, 15:26:38"}
+{"current_steps": 55, "total_steps": 37496, "loss": 0.1905, "lr": 9.999978478671794e-05, "epoch": 0.002933505432318696, "percentage": 0.15, "elapsed_time": "2:35:44", "remaining_time": "73 days, 15:05:51"}
+{"current_steps": 56, "total_steps": 37496, "loss": 0.1765, "lr": 9.999977231314127e-05, "epoch": 0.0029868418947244903, "percentage": 0.15, "elapsed_time": "2:38:34", "remaining_time": "73 days, 14:58:03"}
+{"current_steps": 57, "total_steps": 37496, "loss": 0.1855, "lr": 9.999975948819731e-05, "epoch": 0.003040178357130285, "percentage": 0.15, "elapsed_time": "2:41:25", "remaining_time": "73 days, 15:05:49"}
+{"current_steps": 58, "total_steps": 37496, "loss": 0.1881, "lr": 9.999974631188618e-05, "epoch": 0.0030935148195360795, "percentage": 0.15, "elapsed_time": "2:44:17", "remaining_time": "73 days, 15:29:05"}
+{"current_steps": 59, "total_steps": 37496, "loss": 0.1937, "lr": 9.999973278420795e-05, "epoch": 0.003146851281941874, "percentage": 0.16, "elapsed_time": "2:47:07", "remaining_time": "73 days, 15:28:23"}
+{"current_steps": 60, "total_steps": 37496, "loss": 0.1947, "lr": 9.999971890516272e-05, "epoch": 0.0032001877443476683, "percentage": 0.16, "elapsed_time": "2:49:59", "remaining_time": "73 days, 15:43:31"}
+{"current_steps": 61, "total_steps": 37496, "loss": 0.2015, "lr": 9.999970467475059e-05, "epoch": 0.0032535242067534627, "percentage": 0.16, "elapsed_time": "2:52:49", "remaining_time": "73 days, 15:36:08"}
+{"current_steps": 62, "total_steps": 37496, "loss": 0.1954, "lr": 9.999969009297165e-05, "epoch": 0.0033068606691592575, "percentage": 0.17, "elapsed_time": "2:55:38", "remaining_time": "73 days, 15:30:43"}
+{"current_steps": 63, "total_steps": 37496, "loss": 0.2033, "lr": 9.999967515982604e-05, "epoch": 0.003360197131565052, "percentage": 0.17, "elapsed_time": "2:58:29", "remaining_time": "73 days, 15:37:53"}
+{"current_steps": 64, "total_steps": 37496, "loss": 0.2059, "lr": 9.999965987531382e-05, "epoch": 0.0034135335939708463, "percentage": 0.17, "elapsed_time": "3:01:19", "remaining_time": "73 days, 15:36:28"}
+{"current_steps": 65, "total_steps": 37496, "loss": 0.191, "lr": 9.99996442394351e-05, "epoch": 0.0034668700563766407, "percentage": 0.17, "elapsed_time": "3:04:09", "remaining_time": "73 days, 15:34:04"}
+{"current_steps": 66, "total_steps": 37496, "loss": 0.1917, "lr": 9.999962825219002e-05, "epoch": 0.003520206518782435, "percentage": 0.18, "elapsed_time": "3:06:59", "remaining_time": "73 days, 15:30:30"}
+{"current_steps": 67, "total_steps": 37496, "loss": 0.1895, "lr": 9.999961191357869e-05, "epoch": 0.00357354298118823, "percentage": 0.18, "elapsed_time": "3:09:50", "remaining_time": "73 days, 15:36:02"}
+{"current_steps": 68, "total_steps": 37496, "loss": 0.2054, "lr": 9.999959522360118e-05, "epoch": 0.0036268794435940243, "percentage": 0.18, "elapsed_time": "3:12:40", "remaining_time": "73 days, 15:32:44"}
+{"current_steps": 69, "total_steps": 37496, "loss": 0.2013, "lr": 9.999957818225768e-05, "epoch": 0.0036802159059998187, "percentage": 0.18, "elapsed_time": "3:15:29", "remaining_time": "73 days, 15:15:13"}
+{"current_steps": 70, "total_steps": 37496, "loss": 0.2186, "lr": 9.999956078954822e-05, "epoch": 0.003733552368405613, "percentage": 0.19, "elapsed_time": "3:18:18", "remaining_time": "73 days, 15:02:54"}
+{"current_steps": 71, "total_steps": 37496, "loss": 0.2007, "lr": 9.999954304547301e-05, "epoch": 0.0037868888308114075, "percentage": 0.19, "elapsed_time": "3:21:07", "remaining_time": "73 days, 14:58:40"}
+{"current_steps": 72, "total_steps": 37496, "loss": 0.2075, "lr": 9.999952495003212e-05, "epoch": 0.003840225293217202, "percentage": 0.19, "elapsed_time": "3:23:59", "remaining_time": "73 days, 15:07:08"}
+{"current_steps": 73, "total_steps": 37496, "loss": 0.2156, "lr": 9.999950650322569e-05, "epoch": 0.0038935617556229967, "percentage": 0.19, "elapsed_time": "3:26:48", "remaining_time": "73 days, 15:02:42"}
+{"current_steps": 74, "total_steps": 37496, "loss": 0.203, "lr": 9.999948770505386e-05, "epoch": 0.003946898218028791, "percentage": 0.2, "elapsed_time": "3:29:38", "remaining_time": "73 days, 14:56:45"}
+{"current_steps": 75, "total_steps": 37496, "loss": 0.1992, "lr": 9.999946855551675e-05, "epoch": 0.0040002346804345855, "percentage": 0.2, "elapsed_time": "3:32:26", "remaining_time": "73 days, 14:38:46"}
+{"current_steps": 76, "total_steps": 37496, "loss": 0.2044, "lr": 9.99994490546145e-05, "epoch": 0.00405357114284038, "percentage": 0.2, "elapsed_time": "3:35:14", "remaining_time": "73 days, 14:19:47"}
+{"current_steps": 77, "total_steps": 37496, "loss": 0.2024, "lr": 9.999942920234725e-05, "epoch": 0.004106907605246174, "percentage": 0.21, "elapsed_time": "3:38:04", "remaining_time": "73 days, 14:14:39"}
+{"current_steps": 78, "total_steps": 37496, "loss": 0.2082, "lr": 9.999940899871513e-05, "epoch": 0.004160244067651969, "percentage": 0.21, "elapsed_time": "3:40:54", "remaining_time": "73 days, 14:14:07"}
+{"current_steps": 79, "total_steps": 37496, "loss": 0.2145, "lr": 9.999938844371829e-05, "epoch": 0.004213580530057763, "percentage": 0.21, "elapsed_time": "3:43:44", "remaining_time": "73 days, 14:07:52"}
+{"current_steps": 80, "total_steps": 37496, "loss": 0.2022, "lr": 9.999936753735687e-05, "epoch": 0.0042669169924635575, "percentage": 0.21, "elapsed_time": "3:46:31", "remaining_time": "73 days, 13:47:39"}
+{"current_steps": 81, "total_steps": 37496, "loss": 0.2192, "lr": 9.999934627963103e-05, "epoch": 0.004320253454869353, "percentage": 0.22, "elapsed_time": "3:49:21", "remaining_time": "73 days, 13:41:28"}
+{"current_steps": 82, "total_steps": 37496, "loss": 0.2029, "lr": 9.999932467054089e-05, "epoch": 0.004373589917275147, "percentage": 0.22, "elapsed_time": "3:52:11", "remaining_time": "73 days, 13:38:55"}
+{"current_steps": 83, "total_steps": 37496, "loss": 0.2203, "lr": 9.999930271008663e-05, "epoch": 0.0044269263796809415, "percentage": 0.22, "elapsed_time": "3:55:01", "remaining_time": "73 days, 13:38:18"}
+{"current_steps": 84, "total_steps": 37496, "loss": 0.2078, "lr": 9.99992803982684e-05, "epoch": 0.004480262842086736, "percentage": 0.22, "elapsed_time": "3:57:52", "remaining_time": "73 days, 13:43:11"}
+{"current_steps": 85, "total_steps": 37496, "loss": 0.2041, "lr": 9.999925773508634e-05, "epoch": 0.00453359930449253, "percentage": 0.23, "elapsed_time": "4:00:42", "remaining_time": "73 days, 13:45:41"}
+{"current_steps": 86, "total_steps": 37496, "loss": 0.2119, "lr": 9.999923472054063e-05, "epoch": 0.004586935766898325, "percentage": 0.23, "elapsed_time": "4:03:33", "remaining_time": "73 days, 13:44:27"}
+{"current_steps": 87, "total_steps": 37496, "loss": 0.2102, "lr": 9.99992113546314e-05, "epoch": 0.004640272229304119, "percentage": 0.23, "elapsed_time": "4:06:23", "remaining_time": "73 days, 13:45:34"}
+{"current_steps": 88, "total_steps": 37496, "loss": 0.2146, "lr": 9.999918763735886e-05, "epoch": 0.0046936086917099135, "percentage": 0.23, "elapsed_time": "4:09:14", "remaining_time": "73 days, 13:51:22"}
+{"current_steps": 89, "total_steps": 37496, "loss": 0.2006, "lr": 9.999916356872314e-05, "epoch": 0.004746945154115708, "percentage": 0.24, "elapsed_time": "4:12:04", "remaining_time": "73 days, 13:46:44"}
+{"current_steps": 90, "total_steps": 37496, "loss": 0.1934, "lr": 9.999913914872443e-05, "epoch": 0.004800281616521502, "percentage": 0.24, "elapsed_time": "4:14:55", "remaining_time": "73 days, 13:51:30"}
+{"current_steps": 91, "total_steps": 37496, "loss": 0.2149, "lr": 9.99991143773629e-05, "epoch": 0.004853618078927297, "percentage": 0.24, "elapsed_time": "4:17:44", "remaining_time": "73 days, 13:46:22"}
+{"current_steps": 92, "total_steps": 37496, "loss": 0.2066, "lr": 9.999908925463872e-05, "epoch": 0.004906954541333092, "percentage": 0.25, "elapsed_time": "4:20:35", "remaining_time": "73 days, 13:46:18"}
+{"current_steps": 93, "total_steps": 37496, "loss": 0.2016, "lr": 9.999906378055205e-05, "epoch": 0.004960291003738886, "percentage": 0.25, "elapsed_time": "4:23:26", "remaining_time": "73 days, 13:51:48"}
+{"current_steps": 94, "total_steps": 37496, "loss": 0.227, "lr": 9.999903795510308e-05, "epoch": 0.005013627466144681, "percentage": 0.25, "elapsed_time": "4:26:15", "remaining_time": "73 days, 13:43:45"}
+{"current_steps": 95, "total_steps": 37496, "loss": 0.2139, "lr": 9.999901177829201e-05, "epoch": 0.005066963928550475, "percentage": 0.25, "elapsed_time": "4:29:05", "remaining_time": "73 days, 13:38:47"}
+{"current_steps": 96, "total_steps": 37496, "loss": 0.2119, "lr": 9.9998985250119e-05, "epoch": 0.0051203003909562695, "percentage": 0.26, "elapsed_time": "4:31:54", "remaining_time": "73 days, 13:31:18"}
+{"current_steps": 97, "total_steps": 37496, "loss": 0.2036, "lr": 9.999895837058425e-05, "epoch": 0.005173636853362064, "percentage": 0.26, "elapsed_time": "4:34:42", "remaining_time": "73 days, 13:18:06"}
+{"current_steps": 98, "total_steps": 37496, "loss": 0.2058, "lr": 9.999893113968795e-05, "epoch": 0.005226973315767858, "percentage": 0.26, "elapsed_time": "4:37:32", "remaining_time": "73 days, 13:13:05"}
+{"current_steps": 99, "total_steps": 37496, "loss": 0.2064, "lr": 9.999890355743027e-05, "epoch": 0.005280309778173653, "percentage": 0.26, "elapsed_time": "4:40:21", "remaining_time": "73 days, 13:06:01"}
+{"current_steps": 100, "total_steps": 37496, "loss": 0.2081, "lr": 9.999887562381143e-05, "epoch": 0.005333646240579447, "percentage": 0.27, "elapsed_time": "4:43:11", "remaining_time": "73 days, 13:00:23"}
+{"current_steps": 101, "total_steps": 37496, "loss": 0.2299, "lr": 9.999884733883161e-05, "epoch": 0.005386982702985241, "percentage": 0.27, "elapsed_time": "4:47:23", "remaining_time": "73 days, 21:28:33"}
+{"current_steps": 102, "total_steps": 37496, "loss": 0.2032, "lr": 9.999881870249103e-05, "epoch": 0.005440319165391037, "percentage": 0.27, "elapsed_time": "4:50:11", "remaining_time": "73 days, 21:04:41"}
+{"current_steps": 103, "total_steps": 37496, "loss": 0.2232, "lr": 9.999878971478986e-05, "epoch": 0.005493655627796831, "percentage": 0.27, "elapsed_time": "4:52:58", "remaining_time": "73 days, 20:41:51"}
+{"current_steps": 104, "total_steps": 37496, "loss": 0.2153, "lr": 9.999876037572832e-05, "epoch": 0.0055469920902026255, "percentage": 0.28, "elapsed_time": "4:55:45", "remaining_time": "73 days, 20:18:59"}
+{"current_steps": 105, "total_steps": 37496, "loss": 0.2017, "lr": 9.999873068530661e-05, "epoch": 0.00560032855260842, "percentage": 0.28, "elapsed_time": "4:58:34", "remaining_time": "73 days, 20:03:01"}
+{"current_steps": 106, "total_steps": 37496, "loss": 0.2125, "lr": 9.999870064352497e-05, "epoch": 0.005653665015014214, "percentage": 0.28, "elapsed_time": "5:01:24", "remaining_time": "73 days, 19:55:50"}
+{"current_steps": 107, "total_steps": 37496, "loss": 0.2137, "lr": 9.999867025038357e-05, "epoch": 0.005707001477420009, "percentage": 0.29, "elapsed_time": "5:04:14", "remaining_time": "73 days, 19:53:01"}
+{"current_steps": 108, "total_steps": 37496, "loss": 0.2106, "lr": 9.999863950588263e-05, "epoch": 0.005760337939825803, "percentage": 0.29, "elapsed_time": "5:07:03", "remaining_time": "73 days, 19:40:36"}
+{"current_steps": 109, "total_steps": 37496, "loss": 0.2263, "lr": 9.999860841002238e-05, "epoch": 0.005813674402231597, "percentage": 0.29, "elapsed_time": "5:09:52", "remaining_time": "73 days, 19:27:57"}
+{"current_steps": 110, "total_steps": 37496, "loss": 0.2182, "lr": 9.999857696280304e-05, "epoch": 0.005867010864637392, "percentage": 0.29, "elapsed_time": "5:12:42", "remaining_time": "73 days, 19:21:02"}
+{"current_steps": 111, "total_steps": 37496, "loss": 0.2204, "lr": 9.999854516422483e-05, "epoch": 0.005920347327043186, "percentage": 0.3, "elapsed_time": "5:15:34", "remaining_time": "73 days, 19:23:46"}
+{"current_steps": 112, "total_steps": 37496, "loss": 0.2144, "lr": 9.999851301428795e-05, "epoch": 0.005973683789448981, "percentage": 0.3, "elapsed_time": "5:18:23", "remaining_time": "73 days, 19:14:02"}
+{"current_steps": 113, "total_steps": 37496, "loss": 0.2118, "lr": 9.999848051299265e-05, "epoch": 0.006027020251854776, "percentage": 0.3, "elapsed_time": "5:21:10", "remaining_time": "73 days, 18:52:13"}
+{"current_steps": 114, "total_steps": 37496, "loss": 0.2245, "lr": 9.999844766033916e-05, "epoch": 0.00608035671426057, "percentage": 0.3, "elapsed_time": "5:23:58", "remaining_time": "73 days, 18:37:09"}
+{"current_steps": 115, "total_steps": 37496, "loss": 0.204, "lr": 9.99984144563277e-05, "epoch": 0.006133693176666365, "percentage": 0.31, "elapsed_time": "5:26:45", "remaining_time": "73 days, 18:14:58"}
+{"current_steps": 116, "total_steps": 37496, "loss": 0.2034, "lr": 9.99983809009585e-05, "epoch": 0.006187029639072159, "percentage": 0.31, "elapsed_time": "5:29:36", "remaining_time": "73 days, 18:10:50"}
+{"current_steps": 117, "total_steps": 37496, "loss": 0.2103, "lr": 9.999834699423181e-05, "epoch": 0.0062403661014779534, "percentage": 0.31, "elapsed_time": "5:32:24", "remaining_time": "73 days, 17:56:46"}
+{"current_steps": 118, "total_steps": 37496, "loss": 0.2208, "lr": 9.999831273614786e-05, "epoch": 0.006293702563883748, "percentage": 0.31, "elapsed_time": "5:35:12", "remaining_time": "73 days, 17:40:44"}
+{"current_steps": 119, "total_steps": 37496, "loss": 0.2195, "lr": 9.99982781267069e-05, "epoch": 0.006347039026289542, "percentage": 0.32, "elapsed_time": "5:38:02", "remaining_time": "73 days, 17:37:02"}
+{"current_steps": 120, "total_steps": 37496, "loss": 0.2184, "lr": 9.999824316590916e-05, "epoch": 0.006400375488695337, "percentage": 0.32, "elapsed_time": "5:40:52", "remaining_time": "73 days, 17:28:53"}
+{"current_steps": 121, "total_steps": 37496, "loss": 0.2261, "lr": 9.999820785375487e-05, "epoch": 0.006453711951101131, "percentage": 0.32, "elapsed_time": "5:43:41", "remaining_time": "73 days, 17:20:45"}
+{"current_steps": 122, "total_steps": 37496, "loss": 0.2195, "lr": 9.999817219024432e-05, "epoch": 0.006507048413506925, "percentage": 0.33, "elapsed_time": "5:46:30", "remaining_time": "73 days, 17:11:04"}
+{"current_steps": 123, "total_steps": 37496, "loss": 0.2303, "lr": 9.999813617537772e-05, "epoch": 0.00656038487591272, "percentage": 0.33, "elapsed_time": "5:49:20", "remaining_time": "73 days, 17:03:49"}
+{"current_steps": 124, "total_steps": 37496, "loss": 0.2281, "lr": 9.999809980915537e-05, "epoch": 0.006613721338318515, "percentage": 0.33, "elapsed_time": "5:52:07", "remaining_time": "73 days, 16:44:42"}
+{"current_steps": 125, "total_steps": 37496, "loss": 0.212, "lr": 9.999806309157748e-05, "epoch": 0.0066670578007243094, "percentage": 0.33, "elapsed_time": "5:54:56", "remaining_time": "73 days, 16:34:56"}
+{"current_steps": 126, "total_steps": 37496, "loss": 0.2291, "lr": 9.999802602264433e-05, "epoch": 0.006720394263130104, "percentage": 0.34, "elapsed_time": "5:57:44", "remaining_time": "73 days, 16:19:34"}