Model save

README.md

@@ -0,0 +1,55 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+library_name: peft
+license: llama2
+tags:
+- generated_from_trainer
+model-index:
+- name: Instruments-7B
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Instruments-7B
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.2
+- Pytorch 2.4.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd9013c78632eb1e25c1863a10dc0f16ebec279c878d3f7c972435061aa2180
+size 699296624

added_tokens.json

@@ -0,0 +1,920 @@
+{
+  "<a_0>": 32000,
+  "<a_100>": 32001,
+  "<a_102>": 32002,
+  "<a_103>": 32003,
+  "<a_106>": 32004,
+  "<a_109>": 32005,
+  "<a_110>": 32006,
+  "<a_111>": 32007,
+  "<a_115>": 32008,
+  "<a_117>": 32009,
+  "<a_118>": 32010,
+  "<a_119>": 32011,
+  "<a_11>": 32012,
+  "<a_120>": 32013,
+  "<a_121>": 32014,
+  "<a_122>": 32015,
+  "<a_123>": 32016,
+  "<a_124>": 32017,
+  "<a_126>": 32018,
+  "<a_127>": 32019,
+  "<a_128>": 32020,
+  "<a_129>": 32021,
+  "<a_12>": 32022,
+  "<a_130>": 32023,
+  "<a_134>": 32024,
+  "<a_135>": 32025,
+  "<a_136>": 32026,
+  "<a_138>": 32027,
+  "<a_139>": 32028,
+  "<a_140>": 32029,
+  "<a_141>": 32030,
+  "<a_142>": 32031,
+  "<a_143>": 32032,
+  "<a_144>": 32033,
+  "<a_145>": 32034,
+  "<a_146>": 32035,
+  "<a_149>": 32036,
+  "<a_150>": 32037,
+  "<a_153>": 32038,
+  "<a_157>": 32039,
+  "<a_160>": 32040,
+  "<a_162>": 32041,
+  "<a_163>": 32042,
+  "<a_166>": 32043,
+  "<a_167>": 32044,
+  "<a_16>": 32045,
+  "<a_171>": 32046,
+  "<a_172>": 32047,
+  "<a_174>": 32048,
+  "<a_175>": 32049,
+  "<a_177>": 32050,
+  "<a_178>": 32051,
+  "<a_179>": 32052,
+  "<a_17>": 32053,
+  "<a_181>": 32054,
+  "<a_183>": 32055,
+  "<a_184>": 32056,
+  "<a_185>": 32057,
+  "<a_187>": 32058,
+  "<a_188>": 32059,
+  "<a_189>": 32060,
+  "<a_18>": 32061,
+  "<a_190>": 32062,
+  "<a_192>": 32063,
+  "<a_193>": 32064,
+  "<a_194>": 32065,
+  "<a_195>": 32066,
+  "<a_196>": 32067,
+  "<a_19>": 32068,
+  "<a_202>": 32069,
+  "<a_206>": 32070,
+  "<a_207>": 32071,
+  "<a_208>": 32072,
+  "<a_20>": 32073,
+  "<a_210>": 32074,
+  "<a_212>": 32075,
+  "<a_213>": 32076,
+  "<a_217>": 32077,
+  "<a_218>": 32078,
+  "<a_219>": 32079,
+  "<a_221>": 32080,
+  "<a_223>": 32081,
+  "<a_225>": 32082,
+  "<a_229>": 32083,
+  "<a_22>": 32084,
+  "<a_230>": 32085,
+  "<a_233>": 32086,
+  "<a_234>": 32087,
+  "<a_235>": 32088,
+  "<a_236>": 32089,
+  "<a_237>": 32090,
+  "<a_238>": 32091,
+  "<a_241>": 32092,
+  "<a_242>": 32093,
+  "<a_243>": 32094,
+  "<a_244>": 32095,
+  "<a_245>": 32096,
+  "<a_246>": 32097,
+  "<a_250>": 32098,
+  "<a_251>": 32099,
+  "<a_253>": 32100,
+  "<a_254>": 32101,
+  "<a_255>": 32102,
+  "<a_25>": 32103,
+  "<a_26>": 32104,
+  "<a_27>": 32105,
+  "<a_28>": 32106,
+  "<a_29>": 32107,
+  "<a_30>": 32108,
+  "<a_31>": 32109,
+  "<a_32>": 32110,
+  "<a_34>": 32111,
+  "<a_35>": 32112,
+  "<a_36>": 32113,
+  "<a_38>": 32114,
+  "<a_43>": 32115,
+  "<a_44>": 32116,
+  "<a_46>": 32117,
+  "<a_47>": 32118,
+  "<a_49>": 32119,
+  "<a_51>": 32120,
+  "<a_54>": 32121,
+  "<a_55>": 32122,
+  "<a_56>": 32123,
+  "<a_57>": 32124,
+  "<a_58>": 32125,
+  "<a_5>": 32126,
+  "<a_60>": 32127,
+  "<a_64>": 32128,
+  "<a_65>": 32129,
+  "<a_67>": 32130,
+  "<a_68>": 32131,
+  "<a_69>": 32132,
+  "<a_6>": 32133,
+  "<a_71>": 32134,
+  "<a_72>": 32135,
+  "<a_77>": 32136,
+  "<a_78>": 32137,
+  "<a_79>": 32138,
+  "<a_80>": 32139,
+  "<a_83>": 32140,
+  "<a_84>": 32141,
+  "<a_86>": 32142,
+  "<a_87>": 32143,
+  "<a_88>": 32144,
+  "<a_8>": 32145,
+  "<a_90>": 32146,
+  "<a_92>": 32147,
+  "<a_96>": 32148,
+  "<a_98>": 32149,
+  "<b_0>": 32150,
+  "<b_100>": 32151,
+  "<b_101>": 32152,
+  "<b_102>": 32153,
+  "<b_103>": 32154,
+  "<b_104>": 32155,
+  "<b_105>": 32156,
+  "<b_106>": 32157,
+  "<b_107>": 32158,
+  "<b_108>": 32159,
+  "<b_109>": 32160,
+  "<b_10>": 32161,
+  "<b_110>": 32162,
+  "<b_111>": 32163,
+  "<b_112>": 32164,
+  "<b_113>": 32165,
+  "<b_114>": 32166,
+  "<b_115>": 32167,
+  "<b_116>": 32168,
+  "<b_117>": 32169,
+  "<b_118>": 32170,
+  "<b_119>": 32171,
+  "<b_11>": 32172,
+  "<b_120>": 32173,
+  "<b_121>": 32174,
+  "<b_122>": 32175,
+  "<b_123>": 32176,
+  "<b_124>": 32177,
+  "<b_125>": 32178,
+  "<b_126>": 32179,
+  "<b_127>": 32180,
+  "<b_128>": 32181,
+  "<b_129>": 32182,
+  "<b_12>": 32183,
+  "<b_130>": 32184,
+  "<b_131>": 32185,
+  "<b_132>": 32186,
+  "<b_133>": 32187,
+  "<b_134>": 32188,
+  "<b_135>": 32189,
+  "<b_136>": 32190,
+  "<b_137>": 32191,
+  "<b_138>": 32192,
+  "<b_139>": 32193,
+  "<b_13>": 32194,
+  "<b_140>": 32195,
+  "<b_141>": 32196,
+  "<b_142>": 32197,
+  "<b_143>": 32198,
+  "<b_144>": 32199,
+  "<b_145>": 32200,
+  "<b_146>": 32201,
+  "<b_147>": 32202,
+  "<b_148>": 32203,
+  "<b_149>": 32204,
+  "<b_14>": 32205,
+  "<b_150>": 32206,
+  "<b_151>": 32207,
+  "<b_152>": 32208,
+  "<b_153>": 32209,
+  "<b_154>": 32210,
+  "<b_155>": 32211,
+  "<b_156>": 32212,
+  "<b_157>": 32213,
+  "<b_158>": 32214,
+  "<b_159>": 32215,
+  "<b_15>": 32216,
+  "<b_160>": 32217,
+  "<b_161>": 32218,
+  "<b_162>": 32219,
+  "<b_163>": 32220,
+  "<b_164>": 32221,
+  "<b_165>": 32222,
+  "<b_166>": 32223,
+  "<b_167>": 32224,
+  "<b_168>": 32225,
+  "<b_169>": 32226,
+  "<b_16>": 32227,
+  "<b_170>": 32228,
+  "<b_171>": 32229,
+  "<b_172>": 32230,
+  "<b_173>": 32231,
+  "<b_174>": 32232,
+  "<b_175>": 32233,
+  "<b_176>": 32234,
+  "<b_177>": 32235,
+  "<b_178>": 32236,
+  "<b_179>": 32237,
+  "<b_17>": 32238,
+  "<b_180>": 32239,
+  "<b_181>": 32240,
+  "<b_182>": 32241,
+  "<b_183>": 32242,
+  "<b_184>": 32243,
+  "<b_185>": 32244,
+  "<b_186>": 32245,
+  "<b_187>": 32246,
+  "<b_188>": 32247,
+  "<b_189>": 32248,
+  "<b_18>": 32249,
+  "<b_190>": 32250,
+  "<b_191>": 32251,
+  "<b_192>": 32252,
+  "<b_193>": 32253,
+  "<b_194>": 32254,
+  "<b_195>": 32255,
+  "<b_196>": 32256,
+  "<b_197>": 32257,
+  "<b_198>": 32258,
+  "<b_199>": 32259,
+  "<b_19>": 32260,
+  "<b_1>": 32261,
+  "<b_200>": 32262,
+  "<b_201>": 32263,
+  "<b_202>": 32264,
+  "<b_203>": 32265,
+  "<b_204>": 32266,
+  "<b_205>": 32267,
+  "<b_206>": 32268,
+  "<b_207>": 32269,
+  "<b_208>": 32270,
+  "<b_209>": 32271,
+  "<b_20>": 32272,
+  "<b_210>": 32273,
+  "<b_211>": 32274,
+  "<b_212>": 32275,
+  "<b_213>": 32276,
+  "<b_214>": 32277,
+  "<b_215>": 32278,
+  "<b_216>": 32279,
+  "<b_217>": 32280,
+  "<b_218>": 32281,
+  "<b_219>": 32282,
+  "<b_21>": 32283,
+  "<b_220>": 32284,
+  "<b_221>": 32285,
+  "<b_222>": 32286,
+  "<b_223>": 32287,
+  "<b_224>": 32288,
+  "<b_225>": 32289,
+  "<b_226>": 32290,
+  "<b_227>": 32291,
+  "<b_228>": 32292,
+  "<b_229>": 32293,
+  "<b_22>": 32294,
+  "<b_230>": 32295,
+  "<b_231>": 32296,
+  "<b_232>": 32297,
+  "<b_233>": 32298,
+  "<b_234>": 32299,
+  "<b_235>": 32300,
+  "<b_236>": 32301,
+  "<b_237>": 32302,
+  "<b_238>": 32303,
+  "<b_239>": 32304,
+  "<b_23>": 32305,
+  "<b_240>": 32306,
+  "<b_241>": 32307,
+  "<b_242>": 32308,
+  "<b_243>": 32309,
+  "<b_244>": 32310,
+  "<b_245>": 32311,
+  "<b_246>": 32312,
+  "<b_247>": 32313,
+  "<b_248>": 32314,
+  "<b_249>": 32315,
+  "<b_24>": 32316,
+  "<b_250>": 32317,
+  "<b_251>": 32318,
+  "<b_252>": 32319,
+  "<b_253>": 32320,
+  "<b_254>": 32321,
+  "<b_255>": 32322,
+  "<b_25>": 32323,
+  "<b_26>": 32324,
+  "<b_27>": 32325,
+  "<b_28>": 32326,
+  "<b_29>": 32327,
+  "<b_2>": 32328,
+  "<b_30>": 32329,
+  "<b_31>": 32330,
+  "<b_32>": 32331,
+  "<b_33>": 32332,
+  "<b_34>": 32333,
+  "<b_35>": 32334,
+  "<b_36>": 32335,
+  "<b_37>": 32336,
+  "<b_38>": 32337,
+  "<b_39>": 32338,
+  "<b_3>": 32339,
+  "<b_40>": 32340,
+  "<b_41>": 32341,
+  "<b_42>": 32342,
+  "<b_43>": 32343,
+  "<b_44>": 32344,
+  "<b_45>": 32345,
+  "<b_46>": 32346,
+  "<b_47>": 32347,
+  "<b_48>": 32348,
+  "<b_49>": 32349,
+  "<b_4>": 32350,
+  "<b_50>": 32351,
+  "<b_51>": 32352,
+  "<b_52>": 32353,
+  "<b_53>": 32354,
+  "<b_54>": 32355,
+  "<b_55>": 32356,
+  "<b_56>": 32357,
+  "<b_57>": 32358,
+  "<b_58>": 32359,
+  "<b_59>": 32360,
+  "<b_5>": 32361,
+  "<b_60>": 32362,
+  "<b_61>": 32363,
+  "<b_62>": 32364,
+  "<b_63>": 32365,
+  "<b_64>": 32366,
+  "<b_65>": 32367,
+  "<b_66>": 32368,
+  "<b_67>": 32369,
+  "<b_68>": 32370,
+  "<b_69>": 32371,
+  "<b_6>": 32372,
+  "<b_70>": 32373,
+  "<b_71>": 32374,
+  "<b_72>": 32375,
+  "<b_73>": 32376,
+  "<b_74>": 32377,
+  "<b_75>": 32378,
+  "<b_76>": 32379,
+  "<b_77>": 32380,
+  "<b_78>": 32381,
+  "<b_79>": 32382,
+  "<b_7>": 32383,
+  "<b_80>": 32384,
+  "<b_81>": 32385,
+  "<b_82>": 32386,
+  "<b_83>": 32387,
+  "<b_84>": 32388,
+  "<b_85>": 32389,
+  "<b_86>": 32390,
+  "<b_87>": 32391,
+  "<b_88>": 32392,
+  "<b_89>": 32393,
+  "<b_8>": 32394,
+  "<b_90>": 32395,
+  "<b_91>": 32396,
+  "<b_92>": 32397,
+  "<b_93>": 32398,
+  "<b_94>": 32399,
+  "<b_95>": 32400,
+  "<b_96>": 32401,
+  "<b_97>": 32402,
+  "<b_98>": 32403,
+  "<b_99>": 32404,
+  "<b_9>": 32405,
+  "<c_0>": 32406,
+  "<c_100>": 32407,
+  "<c_101>": 32408,
+  "<c_102>": 32409,
+  "<c_103>": 32410,
+  "<c_104>": 32411,
+  "<c_105>": 32412,
+  "<c_106>": 32413,
+  "<c_107>": 32414,
+  "<c_108>": 32415,
+  "<c_109>": 32416,
+  "<c_10>": 32417,
+  "<c_110>": 32418,
+  "<c_111>": 32419,
+  "<c_112>": 32420,
+  "<c_113>": 32421,
+  "<c_114>": 32422,
+  "<c_115>": 32423,
+  "<c_116>": 32424,
+  "<c_117>": 32425,
+  "<c_118>": 32426,
+  "<c_119>": 32427,
+  "<c_11>": 32428,
+  "<c_120>": 32429,
+  "<c_121>": 32430,
+  "<c_122>": 32431,
+  "<c_123>": 32432,
+  "<c_124>": 32433,
+  "<c_125>": 32434,
+  "<c_126>": 32435,
+  "<c_127>": 32436,
+  "<c_128>": 32437,
+  "<c_129>": 32438,
+  "<c_12>": 32439,
+  "<c_130>": 32440,
+  "<c_131>": 32441,
+  "<c_132>": 32442,
+  "<c_133>": 32443,
+  "<c_134>": 32444,
+  "<c_135>": 32445,
+  "<c_136>": 32446,
+  "<c_137>": 32447,
+  "<c_138>": 32448,
+  "<c_139>": 32449,
+  "<c_13>": 32450,
+  "<c_140>": 32451,
+  "<c_141>": 32452,
+  "<c_142>": 32453,
+  "<c_143>": 32454,
+  "<c_144>": 32455,
+  "<c_145>": 32456,
+  "<c_146>": 32457,
+  "<c_147>": 32458,
+  "<c_148>": 32459,
+  "<c_149>": 32460,
+  "<c_14>": 32461,
+  "<c_150>": 32462,
+  "<c_151>": 32463,
+  "<c_152>": 32464,
+  "<c_153>": 32465,
+  "<c_154>": 32466,
+  "<c_155>": 32467,
+  "<c_156>": 32468,
+  "<c_157>": 32469,
+  "<c_158>": 32470,
+  "<c_159>": 32471,
+  "<c_15>": 32472,
+  "<c_160>": 32473,
+  "<c_161>": 32474,
+  "<c_162>": 32475,
+  "<c_163>": 32476,
+  "<c_164>": 32477,
+  "<c_165>": 32478,
+  "<c_166>": 32479,
+  "<c_167>": 32480,
+  "<c_168>": 32481,
+  "<c_169>": 32482,
+  "<c_16>": 32483,
+  "<c_170>": 32484,
+  "<c_171>": 32485,
+  "<c_172>": 32486,
+  "<c_173>": 32487,
+  "<c_174>": 32488,
+  "<c_175>": 32489,
+  "<c_176>": 32490,
+  "<c_177>": 32491,
+  "<c_178>": 32492,
+  "<c_179>": 32493,
+  "<c_17>": 32494,
+  "<c_180>": 32495,
+  "<c_181>": 32496,
+  "<c_182>": 32497,
+  "<c_183>": 32498,
+  "<c_184>": 32499,
+  "<c_185>": 32500,
+  "<c_186>": 32501,
+  "<c_187>": 32502,
+  "<c_188>": 32503,
+  "<c_189>": 32504,
+  "<c_18>": 32505,
+  "<c_190>": 32506,
+  "<c_191>": 32507,
+  "<c_192>": 32508,
+  "<c_193>": 32509,
+  "<c_194>": 32510,
+  "<c_195>": 32511,
+  "<c_196>": 32512,
+  "<c_197>": 32513,
+  "<c_198>": 32514,
+  "<c_199>": 32515,
+  "<c_19>": 32516,
+  "<c_1>": 32517,
+  "<c_200>": 32518,
+  "<c_201>": 32519,
+  "<c_202>": 32520,
+  "<c_203>": 32521,
+  "<c_204>": 32522,
+  "<c_205>": 32523,
+  "<c_206>": 32524,
+  "<c_207>": 32525,
+  "<c_208>": 32526,
+  "<c_209>": 32527,
+  "<c_20>": 32528,
+  "<c_210>": 32529,
+  "<c_211>": 32530,
+  "<c_212>": 32531,
+  "<c_213>": 32532,
+  "<c_214>": 32533,
+  "<c_215>": 32534,
+  "<c_216>": 32535,
+  "<c_217>": 32536,
+  "<c_218>": 32537,
+  "<c_219>": 32538,
+  "<c_21>": 32539,
+  "<c_220>": 32540,
+  "<c_221>": 32541,
+  "<c_222>": 32542,
+  "<c_223>": 32543,
+  "<c_224>": 32544,
+  "<c_225>": 32545,
+  "<c_226>": 32546,
+  "<c_227>": 32547,
+  "<c_228>": 32548,
+  "<c_229>": 32549,
+  "<c_22>": 32550,
+  "<c_230>": 32551,
+  "<c_231>": 32552,
+  "<c_232>": 32553,
+  "<c_233>": 32554,
+  "<c_234>": 32555,
+  "<c_235>": 32556,
+  "<c_236>": 32557,
+  "<c_237>": 32558,
+  "<c_238>": 32559,
+  "<c_239>": 32560,
+  "<c_23>": 32561,
+  "<c_240>": 32562,
+  "<c_241>": 32563,
+  "<c_242>": 32564,
+  "<c_243>": 32565,
+  "<c_244>": 32566,
+  "<c_245>": 32567,
+  "<c_246>": 32568,
+  "<c_247>": 32569,
+  "<c_248>": 32570,
+  "<c_249>": 32571,
+  "<c_24>": 32572,
+  "<c_250>": 32573,
+  "<c_251>": 32574,
+  "<c_252>": 32575,
+  "<c_253>": 32576,
+  "<c_254>": 32577,
+  "<c_255>": 32578,
+  "<c_25>": 32579,
+  "<c_26>": 32580,
+  "<c_27>": 32581,
+  "<c_28>": 32582,
+  "<c_29>": 32583,
+  "<c_2>": 32584,
+  "<c_30>": 32585,
+  "<c_31>": 32586,
+  "<c_32>": 32587,
+  "<c_33>": 32588,
+  "<c_34>": 32589,
+  "<c_35>": 32590,
+  "<c_36>": 32591,
+  "<c_37>": 32592,
+  "<c_38>": 32593,
+  "<c_39>": 32594,
+  "<c_3>": 32595,
+  "<c_40>": 32596,
+  "<c_41>": 32597,
+  "<c_42>": 32598,
+  "<c_43>": 32599,
+  "<c_44>": 32600,
+  "<c_45>": 32601,
+  "<c_46>": 32602,
+  "<c_47>": 32603,
+  "<c_48>": 32604,
+  "<c_49>": 32605,
+  "<c_4>": 32606,
+  "<c_50>": 32607,
+  "<c_51>": 32608,
+  "<c_52>": 32609,
+  "<c_53>": 32610,
+  "<c_54>": 32611,
+  "<c_55>": 32612,
+  "<c_56>": 32613,
+  "<c_57>": 32614,
+  "<c_58>": 32615,
+  "<c_59>": 32616,
+  "<c_5>": 32617,
+  "<c_60>": 32618,
+  "<c_61>": 32619,
+  "<c_62>": 32620,
+  "<c_63>": 32621,
+  "<c_64>": 32622,
+  "<c_65>": 32623,
+  "<c_66>": 32624,
+  "<c_67>": 32625,
+  "<c_68>": 32626,
+  "<c_69>": 32627,
+  "<c_6>": 32628,
+  "<c_70>": 32629,
+  "<c_71>": 32630,
+  "<c_72>": 32631,
+  "<c_73>": 32632,
+  "<c_74>": 32633,
+  "<c_75>": 32634,
+  "<c_76>": 32635,
+  "<c_77>": 32636,
+  "<c_78>": 32637,
+  "<c_79>": 32638,
+  "<c_7>": 32639,
+  "<c_80>": 32640,
+  "<c_81>": 32641,
+  "<c_82>": 32642,
+  "<c_83>": 32643,
+  "<c_84>": 32644,
+  "<c_85>": 32645,
+  "<c_86>": 32646,
+  "<c_87>": 32647,
+  "<c_88>": 32648,
+  "<c_89>": 32649,
+  "<c_8>": 32650,
+  "<c_90>": 32651,
+  "<c_91>": 32652,
+  "<c_92>": 32653,
+  "<c_93>": 32654,
+  "<c_94>": 32655,
+  "<c_95>": 32656,
+  "<c_96>": 32657,
+  "<c_97>": 32658,
+  "<c_98>": 32659,
+  "<c_99>": 32660,
+  "<c_9>": 32661,
+  "<d_0>": 32662,
+  "<d_100>": 32663,
+  "<d_101>": 32664,
+  "<d_102>": 32665,
+  "<d_103>": 32666,
+  "<d_104>": 32667,
+  "<d_105>": 32668,
+  "<d_106>": 32669,
+  "<d_107>": 32670,
+  "<d_108>": 32671,
+  "<d_109>": 32672,
+  "<d_10>": 32673,
+  "<d_110>": 32674,
+  "<d_111>": 32675,
+  "<d_112>": 32676,
+  "<d_113>": 32677,
+  "<d_114>": 32678,
+  "<d_115>": 32679,
+  "<d_116>": 32680,
+  "<d_117>": 32681,
+  "<d_118>": 32682,
+  "<d_119>": 32683,
+  "<d_11>": 32684,
+  "<d_120>": 32685,
+  "<d_121>": 32686,
+  "<d_122>": 32687,
+  "<d_123>": 32688,
+  "<d_124>": 32689,
+  "<d_125>": 32690,
+  "<d_126>": 32691,
+  "<d_127>": 32692,
+  "<d_128>": 32693,
+  "<d_129>": 32694,
+  "<d_12>": 32695,
+  "<d_130>": 32696,
+  "<d_131>": 32697,
+  "<d_132>": 32698,
+  "<d_133>": 32699,
+  "<d_134>": 32700,
+  "<d_135>": 32701,
+  "<d_136>": 32702,
+  "<d_137>": 32703,
+  "<d_138>": 32704,
+  "<d_139>": 32705,
+  "<d_13>": 32706,
+  "<d_140>": 32707,
+  "<d_141>": 32708,
+  "<d_142>": 32709,
+  "<d_143>": 32710,
+  "<d_144>": 32711,
+  "<d_145>": 32712,
+  "<d_146>": 32713,
+  "<d_147>": 32714,
+  "<d_148>": 32715,
+  "<d_149>": 32716,
+  "<d_14>": 32717,
+  "<d_150>": 32718,
+  "<d_151>": 32719,
+  "<d_152>": 32720,
+  "<d_153>": 32721,
+  "<d_154>": 32722,
+  "<d_155>": 32723,
+  "<d_156>": 32724,
+  "<d_157>": 32725,
+  "<d_158>": 32726,
+  "<d_159>": 32727,
+  "<d_15>": 32728,
+  "<d_160>": 32729,
+  "<d_161>": 32730,
+  "<d_162>": 32731,
+  "<d_163>": 32732,
+  "<d_164>": 32733,
+  "<d_165>": 32734,
+  "<d_166>": 32735,
+  "<d_167>": 32736,
+  "<d_168>": 32737,
+  "<d_169>": 32738,
+  "<d_16>": 32739,
+  "<d_170>": 32740,
+  "<d_171>": 32741,
+  "<d_172>": 32742,
+  "<d_173>": 32743,
+  "<d_174>": 32744,
+  "<d_175>": 32745,
+  "<d_176>": 32746,
+  "<d_177>": 32747,
+  "<d_178>": 32748,
+  "<d_179>": 32749,
+  "<d_17>": 32750,
+  "<d_180>": 32751,
+  "<d_181>": 32752,
+  "<d_182>": 32753,
+  "<d_183>": 32754,
+  "<d_184>": 32755,
+  "<d_185>": 32756,
+  "<d_186>": 32757,
+  "<d_187>": 32758,
+  "<d_188>": 32759,
+  "<d_189>": 32760,
+  "<d_18>": 32761,
+  "<d_190>": 32762,
+  "<d_191>": 32763,
+  "<d_192>": 32764,
+  "<d_193>": 32765,
+  "<d_194>": 32766,
+  "<d_195>": 32767,
+  "<d_196>": 32768,
+  "<d_197>": 32769,
+  "<d_198>": 32770,
+  "<d_199>": 32771,
+  "<d_19>": 32772,
+  "<d_1>": 32773,
+  "<d_200>": 32774,
+  "<d_201>": 32775,
+  "<d_202>": 32776,
+  "<d_203>": 32777,
+  "<d_204>": 32778,
+  "<d_205>": 32779,
+  "<d_206>": 32780,
+  "<d_207>": 32781,
+  "<d_208>": 32782,
+  "<d_209>": 32783,
+  "<d_20>": 32784,
+  "<d_210>": 32785,
+  "<d_211>": 32786,
+  "<d_212>": 32787,
+  "<d_213>": 32788,
+  "<d_214>": 32789,
+  "<d_215>": 32790,
+  "<d_216>": 32791,
+  "<d_217>": 32792,
+  "<d_218>": 32793,
+  "<d_219>": 32794,
+  "<d_21>": 32795,
+  "<d_220>": 32796,
+  "<d_221>": 32797,
+  "<d_222>": 32798,
+  "<d_223>": 32799,
+  "<d_224>": 32800,
+  "<d_225>": 32801,
+  "<d_226>": 32802,
+  "<d_227>": 32803,
+  "<d_228>": 32804,
+  "<d_229>": 32805,
+  "<d_22>": 32806,
+  "<d_230>": 32807,
+  "<d_231>": 32808,
+  "<d_232>": 32809,
+  "<d_233>": 32810,
+  "<d_234>": 32811,
+  "<d_235>": 32812,
+  "<d_236>": 32813,
+  "<d_237>": 32814,
+  "<d_238>": 32815,
+  "<d_239>": 32816,
+  "<d_23>": 32817,
+  "<d_240>": 32818,
+  "<d_241>": 32819,
+  "<d_242>": 32820,
+  "<d_243>": 32821,
+  "<d_244>": 32822,
+  "<d_245>": 32823,
+  "<d_246>": 32824,
+  "<d_247>": 32825,
+  "<d_248>": 32826,
+  "<d_249>": 32827,
+  "<d_24>": 32828,
+  "<d_250>": 32829,
+  "<d_251>": 32830,
+  "<d_252>": 32831,
+  "<d_253>": 32832,
+  "<d_254>": 32833,
+  "<d_255>": 32834,
+  "<d_25>": 32835,
+  "<d_26>": 32836,
+  "<d_27>": 32837,
+  "<d_28>": 32838,
+  "<d_29>": 32839,
+  "<d_2>": 32840,
+  "<d_30>": 32841,
+  "<d_31>": 32842,
+  "<d_32>": 32843,
+  "<d_33>": 32844,
+  "<d_34>": 32845,
+  "<d_35>": 32846,
+  "<d_36>": 32847,
+  "<d_37>": 32848,
+  "<d_38>": 32849,
+  "<d_39>": 32850,
+  "<d_3>": 32851,
+  "<d_40>": 32852,
+  "<d_41>": 32853,
+  "<d_42>": 32854,
+  "<d_43>": 32855,
+  "<d_44>": 32856,
+  "<d_45>": 32857,
+  "<d_46>": 32858,
+  "<d_47>": 32859,
+  "<d_48>": 32860,
+  "<d_49>": 32861,
+  "<d_4>": 32862,
+  "<d_50>": 32863,
+  "<d_51>": 32864,
+  "<d_52>": 32865,
+  "<d_53>": 32866,
+  "<d_54>": 32867,
+  "<d_55>": 32868,
+  "<d_56>": 32869,
+  "<d_57>": 32870,
+  "<d_58>": 32871,
+  "<d_59>": 32872,
+  "<d_5>": 32873,
+  "<d_60>": 32874,
+  "<d_61>": 32875,
+  "<d_62>": 32876,
+  "<d_63>": 32877,
+  "<d_64>": 32878,
+  "<d_65>": 32879,
+  "<d_66>": 32880,
+  "<d_67>": 32881,
+  "<d_68>": 32882,
+  "<d_69>": 32883,
+  "<d_6>": 32884,
+  "<d_70>": 32885,
+  "<d_71>": 32886,
+  "<d_72>": 32887,
+  "<d_73>": 32888,
+  "<d_74>": 32889,
+  "<d_75>": 32890,
+  "<d_76>": 32891,
+  "<d_77>": 32892,
+  "<d_78>": 32893,
+  "<d_79>": 32894,
+  "<d_7>": 32895,
+  "<d_80>": 32896,
+  "<d_81>": 32897,
+  "<d_82>": 32898,
+  "<d_83>": 32899,
+  "<d_84>": 32900,
+  "<d_85>": 32901,
+  "<d_86>": 32902,
+  "<d_87>": 32903,
+  "<d_88>": 32904,
+  "<d_89>": 32905,
+  "<d_8>": 32906,
+  "<d_90>": 32907,
+  "<d_91>": 32908,
+  "<d_92>": 32909,
+  "<d_93>": 32910,
+  "<d_94>": 32911,
+  "<d_95>": 32912,
+  "<d_96>": 32913,
+  "<d_97>": 32914,
+  "<d_98>": 32915,
+  "<d_99>": 32916,
+  "<d_9>": 32917
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32918
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 0.29302138090133667,
+      "learning_rate": 9.393203883495146e-05,
+      "loss": 2.8318,
+      "step": 250
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.24823348224163055,
+      "learning_rate": 8.786407766990292e-05,
+      "loss": 2.4178,
+      "step": 500
+    },
+    {
+      "epoch": 0.7281553398058253,
+      "grad_norm": 0.2736216187477112,
+      "learning_rate": 8.179611650485438e-05,
+      "loss": 2.3486,
+      "step": 750
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.23155324161052704,
+      "learning_rate": 7.572815533980583e-05,
+      "loss": 2.321,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2135922330097086,
+      "grad_norm": 0.3087535500526428,
+      "learning_rate": 6.966019417475728e-05,
+      "loss": 2.3124,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 0.2022610604763031,
+      "learning_rate": 6.359223300970875e-05,
+      "loss": 2.307,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6990291262135924,
+      "grad_norm": 0.1987154483795166,
+      "learning_rate": 5.752427184466019e-05,
+      "loss": 2.3019,
+      "step": 1750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.16502627730369568,
+      "learning_rate": 5.145631067961165e-05,
+      "loss": 2.3073,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 0.19471481442451477,
+      "learning_rate": 4.538834951456311e-05,
+      "loss": 2.2879,
+      "step": 2250
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 0.20921674370765686,
+      "learning_rate": 3.9320388349514564e-05,
+      "loss": 2.2888,
+      "step": 2500
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 0.2216738611459732,
+      "learning_rate": 3.325242718446602e-05,
+      "loss": 2.2997,
+      "step": 2750
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.2476879507303238,
+      "learning_rate": 2.7184466019417475e-05,
+      "loss": 2.2748,
+      "step": 3000
+    },
+    {
+      "epoch": 3.1553398058252426,
+      "grad_norm": 0.2942667603492737,
+      "learning_rate": 2.111650485436893e-05,
+      "loss": 2.2749,
+      "step": 3250
+    },
+    {
+      "epoch": 3.3980582524271843,
+      "grad_norm": 0.2994736135005951,
+      "learning_rate": 1.5048543689320387e-05,
+      "loss": 2.2738,
+      "step": 3500
+    },
+    {
+      "epoch": 3.6407766990291264,
+      "grad_norm": 0.2753419876098633,
+      "learning_rate": 8.980582524271845e-06,
+      "loss": 2.2557,
+      "step": 3750
+    },
+    {
+      "epoch": 3.883495145631068,
+      "grad_norm": 0.277048796415329,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 2.2512,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "step": 4120,
+      "total_flos": 7.617568236584731e+18,
+      "train_loss": 2.3324776880949445,
+      "train_runtime": 61881.1241,
+      "train_samples_per_second": 8.522,
+      "train_steps_per_second": 0.067
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 4120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.617568236584731e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c70d7f9bd76c9140f0dda5cc4a9d828fcf638aedffbb702d6d27622ffa21aa2
+size 5240