Upload 17 files

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_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 sha256:39fb7b8dd7cbf38ed98c8998a0192ae707935e574b47b634f29f08a213ecf866
+size 369142184

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0"
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c91604770f9591f6d0d04ec73469e441795bc16dcbce4dca347ba5df9edaf5
+size 738394298

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6b495466b234737cd287d9a750cb61ee7c06797229f53c76bcd429ccf53a51
+size 698396236

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc7265acdc9d532a1eb0d24f2d3d7466eeae37808ba56319c8d2ebd4dc635f1
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2316ad5425e5b3ab31a35a8544e3379804230ad21119fcc05a3d896d9d05594f
+size 1064

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,357 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9942004971002486,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7059583067893982,
+      "learning_rate": 0.0002,
+      "loss": 1.1809,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6619198322296143,
+      "learning_rate": 0.0002,
+      "loss": 0.5511,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.37209564447402954,
+      "learning_rate": 0.0002,
+      "loss": 0.833,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5066412091255188,
+      "learning_rate": 0.0002,
+      "loss": 0.497,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5964956283569336,
+      "learning_rate": 0.0002,
+      "loss": 0.77,
+      "step": 125
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.6351748108863831,
+      "learning_rate": 0.0002,
+      "loss": 0.4792,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.33565786480903625,
+      "learning_rate": 0.0002,
+      "loss": 0.6867,
+      "step": 175
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5637449622154236,
+      "learning_rate": 0.0002,
+      "loss": 0.4725,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.29314109683036804,
+      "learning_rate": 0.0002,
+      "loss": 0.6842,
+      "step": 225
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.5340172052383423,
+      "learning_rate": 0.0002,
+      "loss": 0.4269,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.38599228858947754,
+      "learning_rate": 0.0002,
+      "loss": 0.6939,
+      "step": 275
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5987310409545898,
+      "learning_rate": 0.0002,
+      "loss": 0.4435,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3571007549762726,
+      "learning_rate": 0.0002,
+      "loss": 0.6976,
+      "step": 325
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5330923199653625,
+      "learning_rate": 0.0002,
+      "loss": 0.415,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.4177188277244568,
+      "learning_rate": 0.0002,
+      "loss": 0.6663,
+      "step": 375
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5220038890838623,
+      "learning_rate": 0.0002,
+      "loss": 0.4305,
+      "step": 400
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.40320834517478943,
+      "learning_rate": 0.0002,
+      "loss": 0.6978,
+      "step": 425
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.3986828625202179,
+      "learning_rate": 0.0002,
+      "loss": 0.392,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.3662169873714447,
+      "learning_rate": 0.0002,
+      "loss": 0.6647,
+      "step": 475
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.4708826541900635,
+      "learning_rate": 0.0002,
+      "loss": 0.4119,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.3558133840560913,
+      "learning_rate": 0.0002,
+      "loss": 0.6364,
+      "step": 525
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5110255479812622,
+      "learning_rate": 0.0002,
+      "loss": 0.3949,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.4202500581741333,
+      "learning_rate": 0.0002,
+      "loss": 0.6034,
+      "step": 575
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7778056263923645,
+      "learning_rate": 0.0002,
+      "loss": 0.389,
+      "step": 600
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.42499253153800964,
+      "learning_rate": 0.0002,
+      "loss": 0.6453,
+      "step": 625
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.4130938947200775,
+      "learning_rate": 0.0002,
+      "loss": 0.3776,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.38256368041038513,
+      "learning_rate": 0.0002,
+      "loss": 0.5631,
+      "step": 675
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.6242409944534302,
+      "learning_rate": 0.0002,
+      "loss": 0.3771,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3617693781852722,
+      "learning_rate": 0.0002,
+      "loss": 0.5804,
+      "step": 725
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.3799505829811096,
+      "learning_rate": 0.0002,
+      "loss": 0.3513,
+      "step": 750
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.32906627655029297,
+      "learning_rate": 0.0002,
+      "loss": 0.5393,
+      "step": 775
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4239194989204407,
+      "learning_rate": 0.0002,
+      "loss": 0.3636,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4123442769050598,
+      "learning_rate": 0.0002,
+      "loss": 0.5279,
+      "step": 825
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4623079001903534,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 850
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.3831407427787781,
+      "learning_rate": 0.0002,
+      "loss": 0.5286,
+      "step": 875
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.48481571674346924,
+      "learning_rate": 0.0002,
+      "loss": 0.3588,
+      "step": 900
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.36328190565109253,
+      "learning_rate": 0.0002,
+      "loss": 0.5519,
+      "step": 925
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.4488459527492523,
+      "learning_rate": 0.0002,
+      "loss": 0.3833,
+      "step": 950
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.39116260409355164,
+      "learning_rate": 0.0002,
+      "loss": 0.5035,
+      "step": 975
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.4923652410507202,
+      "learning_rate": 0.0002,
+      "loss": 0.3178,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.38706672191619873,
+      "learning_rate": 0.0002,
+      "loss": 0.5357,
+      "step": 1025
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.3919411897659302,
+      "learning_rate": 0.0002,
+      "loss": 0.3329,
+      "step": 1050
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.44446566700935364,
+      "learning_rate": 0.0002,
+      "loss": 0.4754,
+      "step": 1075
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.3222676217556,
+      "learning_rate": 0.0002,
+      "loss": 0.3128,
+      "step": 1100
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.3832922577857971,
+      "learning_rate": 0.0002,
+      "loss": 0.5655,
+      "step": 1125
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5052505135536194,
+      "learning_rate": 0.0002,
+      "loss": 0.3673,
+      "step": 1150
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.3186209797859192,
+      "learning_rate": 0.0002,
+      "loss": 0.4993,
+      "step": 1175
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5416242480278015,
+      "learning_rate": 0.0002,
+      "loss": 0.3399,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 6.735879205561958e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0f348307245d738c7913d099a36e4fdb28aa5d262f711c3aded522aef9c47f
+size 4984