Upload folder using huggingface_hub

README.md

@@ -1,16 +1,3 @@
 ---
-datasets:
-- yahma/alpaca-cleaned
-language:
-- en
-license: apache-2.0
-tags:
-- pytorch
-- causal-lm
-- llama2
-- fine-tuning
-- alpaca
-
+library_name: peft
 ---
-
-# Llama-2-7B fine-tuned on LoRA alpaca-cleaned

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "base_model_name_or_path": "georgesung/llama2_7b_chat_uncensored",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
+size 443

checkpoint-250/adapter_model/README.md

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

checkpoint-250/adapter_model/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "base_model_name_or_path": "georgesung/llama2_7b_chat_uncensored",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-250/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
+size 443

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e581b1031fd73bd8aa319fd40e6cf7e923cf8dd1479060d7d597271fb71e7e12
+size 12833221

checkpoint-250/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1818fa5f719fb87158a6e35516b0fd1f76a2c40974168c04939837ea03fa39a4
+size 21687

checkpoint-250/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c337ab7f81e61f87fd7017e4664a3c9817f6ad0af3433302aea0bf6352ce1dc6
+size 21687

checkpoint-250/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71116ed9c7a18475ffdf66abd8f4812174e0e79d75f7ccbdb45b9d94ba52498d
+size 21687

checkpoint-250/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af06d03dd3e8d8c4acb796ee953b5830bb2d38ee74eb796e44924b247f59d670
+size 21687

checkpoint-250/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e4f5a4c4c32d3e5cdcb590163526e4b0f2dc5b03fe1751612d75ca05dd1fe
+size 21687

checkpoint-250/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf8865f613c34dd93fa37eed1a94f52689f981511b59f9aeea05f89f91c983d
+size 21687

checkpoint-250/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294fb493b15be44ac8b4b85ddf84dca0e93e755ec0c925aa96790d28371dc6c4
+size 21687

checkpoint-250/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5020c2ede9dc58e51bfe0647cd46fc91fb0b8ed7ce1475bb264c7d040f802c1c
+size 21687

checkpoint-250/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ba1333be64abeb4f195c699d409a499c161897b8d08412b5bc6d7a0a5a299d
+size 557

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e484860ad00d61fa01ddff8a380ac54055a735b595749017ba960f814d6ef067
+size 627

checkpoint-250/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07727975270479134,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.949107209404665e-05,
+      "loss": 1.4438,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.60054932593026e-05,
+      "loss": 0.9005,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.943603315859101e-05,
+      "loss": 0.8217,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.073758755521505e-05,
+      "loss": 0.8408,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.077075065009433e-05,
+      "loss": 0.8358,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.1404,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.0012,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.0874,
+      "step": 160
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.1208,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 0.9762,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.0802,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 7.017858456614284e-05,
+      "loss": 1.157,
+      "step": 240
+    }
+  ],
+  "max_steps": 250,
+  "num_train_epochs": 1,
+  "total_flos": 3.76542290027479e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fce417f356d651d4546f8ccd4538e6655b6f781ef22edd36ad7c0716b8449f0
+size 3963

flyte_training_config.json

@@ -0,0 +1 @@
+{"base_model": "georgesung/llama2_7b_chat_uncensored", "data_path": "yahma/alpaca-cleaned", "instruction_key": "instruction", "input_key": "input", "output_key": "output", "output_dir": "./output", "device_map": "auto", "batch_size": 16, "micro_batch_size": 1, "num_epochs": 1, "max_steps": 250, "eval_steps": 200, "save_steps": 50, "learning_rate": 0.0001, "cutoff_len": 512, "val_set_size": 0, "lora_r": 8, "lora_alpha": 16, "lora_dropout": 0.05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "lora_target_modules": ["q_proj", "k_proj", "v_proj"], "train_on_inputs": true, "add_eos_token": true, "group_by_length": true, "resume_from_checkpoint": null, "wandb_project": "unionai-llm-fine-tuning", "wandb_run_name": "", "wandb_watch": "", "wandb_log_model": "", "debug_mode": false, "debug_train_data_size": 1024}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6794c634e96a187c1b77b9af1f6d9c73037ecd497374b3c193fe00b626674284
+size 25234701

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fce417f356d651d4546f8ccd4538e6655b6f781ef22edd36ad7c0716b8449f0
+size 3963