Upload 6 files

README.md

@@ -1,3 +1,3 @@
 ---
-license: apache-2.0
+library_name: peft
 ---

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "models\\Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca9aa8aa21f9fd53cd87b0f14f845fad07e07eb6def2aa27a60cc9ceeb0ebe4
+size 268481485

training_log.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name": "Llama-2-7b-chat-hf",
+  "base_model_class": "LlamaForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "q, v",
+  "loss": 0.8314,
+  "learning_rate": 7.264545643486997e-07,
+  "epoch": 2.76,
+  "current_steps": 3387,
+  "train_runtime": 13542.7743,
+  "train_samples_per_second": 0.277,
+  "train_steps_per_second": 0.002,
+  "total_flos": 1.4593684047239578e+17,
+  "train_loss": 0.9451417039941858
+}

training_parameters.json

@@ -0,0 +1,30 @@
+{
+  "lora_name": "7bV2CHATWIZARDTiny1",
+  "always_override": true,
+  "save_steps": 100.0,
+  "micro_batch_size": 1,
+  "batch_size": 128,
+  "epochs": 3.0,
+  "learning_rate": "5e-5",
+  "lr_scheduler_type": "cosine",
+  "lora_rank": 128,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "cutoff_len": 2048,
+  "dataset": "gpe4codeYoked1250v2",
+  "eval_dataset": "None",
+  "format": "alpaca-format",
+  "eval_steps": 100.0,
+  "raw_text_file": "None",
+  "overlap_len": 128,
+  "newline_favor_len": 128,
+  "higher_rank_limit": false,
+  "warmup_steps": 100.0,
+  "optimizer": "adamw_bnb_8bit",
+  "hard_cut_string": "\\n\\n\\n",
+  "train_only_after": "",
+  "stop_at_loss": 0,
+  "add_eos_token": false,
+  "min_chars": 0.0,
+  "report_to": "tensorboard"
+}

training_prompt.json

@@ -0,0 +1,5 @@
+{
+  "template_type": "dataset",
+  "template_1": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Response:\n%output%",
+  "template_2": "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n%instruction%\n\n### Input:\n%input%\n\n### Response:\n%output%"
+}