Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Rakuten/RakutenAI-7B-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "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",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_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:dbb4965e724637e7c28bbfbfc1949b495751cd0e1cc8ae887d9435056047e178
+size 83946192

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99421bfaa870fd575e2cbee943487b4a4a3e7c367d709ba1bb0200123e1af38
+size 335810482

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0ad12807ac28dfc8b0f19968bc2d67c3504e2891162156cf95c8d0acc40bcd
+size 14168

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d151571d18043fd71e8a555e30e88db47c2b573382d14ae55c5df3ad38604822
+size 1056

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
+size 755169

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "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": true
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.25,
+      "learning_rate": 2.9968542393565676e-06,
+      "loss": 1.7053,
+      "step": 5
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.9616157869703894e-06,
+      "loss": 1.5958,
+      "step": 10
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.671875,
+      "learning_rate": 2.8881318444640566e-06,
+      "loss": 1.6746,
+      "step": 15
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.778325235483954e-06,
+      "loss": 1.5386,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.921875,
+      "learning_rate": 2.6350692237265428e-06,
+      "loss": 1.5512,
+      "step": 25
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.453125,
+      "learning_rate": 2.4621123294467098e-06,
+      "loss": 1.5223,
+      "step": 30
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.25,
+      "learning_rate": 2.2639802434931445e-06,
+      "loss": 1.4408,
+      "step": 35
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.28125,
+      "learning_rate": 2.0458574054452316e-06,
+      "loss": 1.551,
+      "step": 40
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.813451344546913e-06,
+      "loss": 1.4931,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.5728433331716726e-06,
+      "loss": 1.4152,
+      "step": 50
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.0,
+      "learning_rate": 1.3303292607070737e-06,
+      "loss": 1.436,
+      "step": 55
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.0922548916454855e-06,
+      "loss": 1.4471,
+      "step": 60
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 20,
+  "total_flos": 7398534869286912.0,
+  "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 sha256:20d7786bb071bc836c1d00441d040f9c857e736be6f170ff51b614b3eef70914
+size 4960