Add alpaca lora weights

adapter_config.json

@@ -0,0 +1,18 @@
+{
+  "base_model_name_or_path": "/home/ubuntu/models/llama_7B/",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "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 sha256:2a825d8cbde28524b285f1c1715d2582fd57f2c67bf5f19cfa41efbb0cad0915
+size 16822989

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecc364b7d27de6764568949f678a3cbf3e783792f1cb2889c4a3389be1dd35c
+size 33661637

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ee9f238fc019bac3e6d601c53840791e5579a86cfaac0b302061a21c814015
+size 16822989

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5968c09fc183ec7c9819d009d4e56d63e8e7db3959e90c2e83d3bd9605aca9c
+size 14575

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577d21ec99291b14ec22312d34683ff2133f37672ec277c6f85957f98d6f2f80
+size 557

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2cca9b236dcac259574c23e23fc7fce56c88f4f36864b866da31ca5c4faccb
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8030890822410583,
+  "best_model_checkpoint": "./lora-alpaca/checkpoint-200",
+  "epoch": 0.5144694533762058,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.2847,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 2.2109,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 1.9736,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000117,
+      "loss": 1.5818,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000147,
+      "loss": 1.2586,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 1.1373,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.9888,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000237,
+      "loss": 0.8617,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000267,
+      "loss": 0.8454,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 0.8458,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000290625,
+      "loss": 0.8341,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002802083333333333,
+      "loss": 0.8218,
+      "step": 120
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00026979166666666666,
+      "loss": 0.8304,
+      "step": 130
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.000259375,
+      "loss": 0.8161,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00024895833333333334,
+      "loss": 0.8097,
+      "step": 150
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00023854166666666663,
+      "loss": 0.8134,
+      "step": 160
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00022812499999999997,
+      "loss": 0.8214,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00021770833333333332,
+      "loss": 0.8095,
+      "step": 180
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00020729166666666663,
+      "loss": 0.8028,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00019687499999999997,
+      "loss": 0.8014,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.8030890822410583,
+      "eval_runtime": 134.5586,
+      "eval_samples_per_second": 14.863,
+      "eval_steps_per_second": 1.858,
+      "step": 200
+    }
+  ],
+  "max_steps": 388,
+  "num_train_epochs": 1,
+  "total_flos": 2.5486812238577664e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf61cff2e80d88998fcc6b744a0d1808f23975fbc1c2fc421f2ce06178efb6c
+size 3579

runs/Mar27_21-39-54_192-9-155-93/1679953194.7849967/events.out.tfevents.1679953194.192-9-155-93.76817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6316f7f77e43cb7e07dbee9a6837ef7f5d3b0aa4b9848fc2557527aca10d3d0
+size 5773

runs/Mar27_21-39-54_192-9-155-93/events.out.tfevents.1679953194.192-9-155-93.76817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b509688dbf98a825afdeb51f60a3e629bd2d5857f1f3093fdabc138388e66467
+size 10346