Upload 5 files

README.md

@@ -0,0 +1,3 @@
+---
+library_name: peft
+---

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "models/Neko-Institute-of-Science_LLaMA-7B-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:f13af37c5b07bee4e25f73a90f05baa714978df7ceaf09651ab6d4d5325d0ebf
+size 268481485

training_log.json

@@ -0,0 +1,10 @@
+{
+  "loss": 2.0942,
+  "learning_rate": 5.150214592274677e-07,
+  "epoch": 2.0,
+  "train_runtime": 13910.5631,
+  "train_samples_per_second": 5.396,
+  "train_steps_per_second": 0.084,
+  "total_flos": 3.844740927455232e+17,
+  "train_loss": 2.2632525492039965
+}

training_parameters.json

@@ -0,0 +1,26 @@
+{
+  "lora_name": "Olavo-LoRA",
+  "always_override": false,
+  "save_steps": 0.0,
+  "micro_batch_size": 4,
+  "batch_size": 64,
+  "epochs": 2.0,
+  "learning_rate": "3e-4",
+  "lr_scheduler_type": "linear",
+  "lora_rank": 128,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "cutoff_len": 128,
+  "dataset": "None",
+  "eval_dataset": "None",
+  "format": "None",
+  "eval_steps": 100.0,
+  "raw_text_file": "Olavo_de_Carvalho_Artigos_de_1998_ate\u0301_2016_by_Olavo_de_Carvalho",
+  "overlap_len": 48,
+  "newline_favor_len": 224,
+  "higher_rank_limit": false,
+  "warmup_steps": 100.0,
+  "optimizer": "adamw_torch",
+  "hard_cut_string": "\\n\\n\\n",
+  "train_only_after": ""
+}